CN110795999A - Garbage delivery behavior analysis method and related product - Google Patents

Garbage delivery behavior analysis method and related product Download PDF

Info

Publication number
CN110795999A
CN110795999A CN201910895418.6A CN201910895418A CN110795999A CN 110795999 A CN110795999 A CN 110795999A CN 201910895418 A CN201910895418 A CN 201910895418A CN 110795999 A CN110795999 A CN 110795999A
Authority
CN
China
Prior art keywords
target
garbage
delivery
video
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910895418.6A
Other languages
Chinese (zh)
Other versions
CN110795999B (en
Inventor
田岱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wanyi Technology Co Ltd
Original Assignee
Wanyi Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wanyi Technology Co Ltd filed Critical Wanyi Technology Co Ltd
Priority to CN201910895418.6A priority Critical patent/CN110795999B/en
Publication of CN110795999A publication Critical patent/CN110795999A/en
Application granted granted Critical
Publication of CN110795999B publication Critical patent/CN110795999B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W30/00—Technologies for solid waste management
    • Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Software Systems (AREA)
  • Educational Administration (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Development Economics (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the application discloses a garbage delivery behavior analysis method and a related product, which are applied to a garbage delivery monitoring system, wherein the method comprises the following steps: acquiring video clips of a target user when delivering garbage through at least one camera; analyzing the video clips to obtain multi-frame video images; performing target extraction on a plurality of frames of video images to obtain a plurality of target area images; performing target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object; determining a target delivery garbage can of a target object according to a plurality of frames of video images, wherein the target delivery garbage can comprises at least one garbage delivery type; when at least one garbage delivery type comprises a target garbage type, confirming that a delivery behavior of a target user is legal; and confirming that the target user delivery is illegal when the at least one garbage delivery type does not comprise the target garbage type. By adopting the method and the device, the garbage delivery behavior of the user can be monitored.

Description

Garbage delivery behavior analysis method and related product
Technical Field
The application relates to the technical field of face recognition, in particular to a garbage delivery behavior analysis method and a related product.
Background
The garbage classification refers to a general term of a series of activities for classifying, storing, putting and carrying garbage according to a certain rule or standard so as to convert the garbage into public resources. The classification aims to improve the resource value and the economic value of the garbage and strive for making the best use of the garbage.
With the popularization of the garbage classification policy, the garbage classification walks into the visual field of people, and therefore, the problem of how to monitor the garbage classification needs to be solved urgently.
Disclosure of Invention
The embodiment of the application provides a garbage delivery behavior analysis method and a related product, which can monitor the garbage classification behavior of a user.
In a first aspect, an embodiment of the present application provides a method for analyzing a garbage delivery behavior, which is applied to a garbage delivery monitoring system, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, and each garbage can is used for containing a type of garbage, and the method includes:
acquiring a video clip of a target user when delivering garbage through the at least one camera;
analyzing the video clips to obtain multi-frame video images;
performing target extraction on the multi-frame video image to obtain a plurality of target area images;
performing target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
determining a target delivery garbage can of the target object according to the multi-frame video image, wherein the target delivery garbage can comprises at least one garbage delivery type;
when the at least one garbage delivery type comprises the target garbage type, confirming that the target user delivery behavior is legal;
confirming that the target user delivery is illegal when the at least one spam delivery type does not include the target spam type.
In a second aspect, an embodiment of the present application provides a garbage delivery behavior analysis device, which is applied to a garbage delivery monitoring system, the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is used for monitoring a designated area, the designated area includes a plurality of garbage cans therein, each garbage can is used for containing one type of garbage, the device includes:
the acquisition unit is used for acquiring video clips of the target user when delivering the garbage through the at least one camera;
the analysis unit is used for analyzing the video clips to obtain multi-frame video images;
the extraction unit is used for carrying out target extraction on the multi-frame video images to obtain a plurality of target area images;
the identification unit is used for carrying out target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
a determining unit, configured to determine a target delivery trash can of the target object according to the multiple frames of video images, where the target delivery trash can includes at least one trash delivery type;
the analysis unit is used for confirming that the target user delivery behavior is legal when the at least one garbage delivery type comprises the target garbage type; and confirming that the target user delivery is illegal when the at least one spam delivery type does not comprise the target spam type.
In a third aspect, an embodiment of the present application provides a system for monitoring spam delivery, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for performing the steps in the first aspect of the embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program enables a computer to perform some or all of the steps described in the first aspect of the embodiment of the present application.
In a fifth aspect, embodiments of the present application provide a computer program product, where the computer program product includes a non-transitory computer-readable storage medium storing a computer program, where the computer program is operable to cause a computer to perform some or all of the steps as described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.
The embodiment of the application has the following beneficial effects:
it can be seen that the method for analyzing garbage delivery behavior and the related products described in the embodiments of the present application are applied to a garbage delivery monitoring system, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, each garbage can is configured to hold a type of garbage, a video clip of a target user when delivering the garbage is obtained through the at least one camera, the video clip is analyzed to obtain a plurality of frames of video images, the plurality of frames of video images are subjected to target extraction to obtain a plurality of target area images, target identification is performed according to the plurality of target area images to obtain a target object and a target garbage type corresponding to the target object, and the target delivery garbage can of the target object is determined according to the plurality of frames of video images, the target delivery garbage can comprises at least one garbage delivery type, when the at least one garbage delivery type comprises the target garbage type, the delivery behavior of the target user is confirmed to be legal, and when the at least one garbage delivery type does not comprise the target garbage type, the delivery of the target user is confirmed to be illegal.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1A is a schematic diagram of a garbage delivery monitoring system according to an embodiment of the present application;
FIG. 1B is a schematic flow chart illustrating a method for analyzing spam delivery behavior according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart diagram of another method for analyzing spam delivery behavior according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a garbage delivery monitoring system according to an embodiment of the present application;
fig. 4A is a block diagram illustrating functional units of a garbage delivery behavior analysis device according to an embodiment of the present application;
FIG. 4B is a block diagram of functional units of another garbage delivery behavior analysis device provided in the embodiments of the present application;
fig. 4C is a block diagram of functional units of another apparatus for analyzing spam delivery behavior according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The system for monitoring the garbage delivery according to the embodiment of the application can be a server, a monitoring platform and the like.
The following describes embodiments of the present application in detail.
Referring to fig. 1A, fig. 1A is a schematic diagram of an architecture of a garbage delivery monitoring system for implementing a garbage delivery behavior analysis method according to an embodiment of the present application, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor a designated area, the designated area includes a plurality of garbage cans, and each garbage can is used for holding a type of garbage.
In an embodiment of the present application, the garbage delivery monitoring system may include a control platform, and the control platform may include a control circuit, a storage circuit, and a processing circuit. The storage circuit may be a memory, such as a hard disk drive memory, a non-volatile memory (e.g., a flash memory or other electronically programmable read-only memory used to form a solid state drive, etc.), a volatile memory (e.g., a static or dynamic random access memory, etc.), etc., and the embodiments of the present application are not limited thereto. The processing circuitry may be used to control the operation of the waste delivery monitoring system. The processing circuitry may be implemented based on one or more microprocessors, microcontrollers, digital signal processors, baseband processors, power management units, audio codec chips, application specific integrated circuits, display driver integrated circuits, and the like.
Referring to fig. 1B, fig. 1B is a schematic flow chart of a method for analyzing a garbage delivery behavior according to an embodiment of the present application, and is applied to the garbage delivery monitoring system shown in fig. 1A, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor a designated area, the designated area includes a plurality of garbage cans, and each garbage can is used for holding a type of garbage, as shown in the figure, the method for analyzing a garbage delivery behavior includes:
101. and acquiring video clips of the target user when delivering the garbage through the at least one camera.
The garbage delivery monitoring system may be applied to public places, such as communities, campuses, hospitals, museum, bus platforms, parks, tourist attractions, railway stations, airports, office buildings, pedestrian streets, shopping malls, supermarkets, and the like, without limitation. In the embodiment of the present application, the designated area may be set by the user or default by the system. The designated area may be a fixed area or a dynamically changing area. In the embodiment of the application, at least one camera can shoot, but images are not required to be stored at all times, and shooting can be carried out only when someone is in a shooting range.
In the concrete implementation, the garbage delivery monitoring system comprises at least one camera, and the garbage delivery monitoring system comprises a plurality of garbage cans for monitoring a designated area, wherein each garbage can is used for containing one type of garbage, for example, the garbage cans can be the following garbage cans: dry garbage bin, wet garbage bin, harmful substance garbage bin etc. can further divide, if: the dry garbage bin can be waste paper garbage bin, plastic garbage bin, glass garbage bin, metal object garbage bin, cloth garbage bin etc. do not do the restriction here, and wherein, waste paper garbage can be used for following rubbish of splendid attire: newspapers, periodicals, books, various wrapping papers, and the like; the plastic garbage can contain the following garbage: various plastic bags, plastic foams, plastic packages, disposable plastic meal box tableware, hard plastics, plastic toothbrushes, plastic cups, mineral water bottles and the like; the glass garbage can be used for containing the following garbage: various glass bottles, broken glass pieces, mirrors, thermos bottles, and the like; the metal garbage can be used for containing the following garbage: pop-top cans, can boxes, and the like. The cloth garbage bin can be used for containing the following garbage: waste clothes, tablecloths, washcloths, school bags, shoes, etc.
Of course, the at least one camera may be one camera responsible for monitoring one trash can, or may be multiple cameras responsible for monitoring one trash can, which is not limited herein.
In a possible example, the step 101 of obtaining, by the at least one camera, a video clip of the target user when the target user delivers spam may include the following steps:
21. detecting a distance between the target user and each of the plurality of trash cans to obtain a plurality of distance values;
22. and when the average value among the plurality of distance values is within a preset range, controlling the at least one camera to shoot the target user to obtain a video clip of the target user when delivering the garbage.
Wherein, the preset range can be set by the user or the default of the system. In concrete the realization, each camera can set up range finding sensor, and then, can detect the distance between each garbage bin in target user and a plurality of garbage bins through range finding sensor, obtain a plurality of distance values, when the mean value between a plurality of distance values is in the scope of predetermineeing, control at least one camera and shoot target user, video clip when obtaining target user and delivering rubbish.
102. And analyzing the video clips to obtain multi-frame video images.
The video clip is formed by one frame and one frame of image, so the garbage delivery monitoring system can analyze the video clip to obtain a plurality of frames of video images.
103. And performing target extraction on the multi-frame video image to obtain a plurality of target area images.
In a specific implementation, because each frame of the multi-frame video images does not necessarily include a target, or one frame of the video images may include a plurality of targets, the garbage delivery monitoring system can extract the targets of the multi-frame video images, and can obtain a plurality of target area images.
In a possible example, in step 103, performing target extraction on the multiple frames of video images to obtain multiple target area images, may include the following steps:
31. performing image segmentation on the video image i to obtain a target area image, wherein the video image i is any one frame of video image in the multi-frame video images;
32. analyzing the characteristic points of the target area image;
33. dividing the target area image into a plurality of areas, wherein the areas of the areas are equal;
34. determining the distribution density of the characteristic points of each area in the plurality of areas to obtain a plurality of distribution density values of the characteristic points;
35. selecting a characteristic point distribution density value smaller than a preset characteristic point distribution density value from the plurality of characteristic point distribution density values to obtain at least one characteristic point distribution density value;
36. determining at least one target image enhancement parameter corresponding to the at least one characteristic point distribution density value according to a preset mapping relation between the characteristic point distribution density value and the image enhancement parameter, wherein each characteristic point distribution density value corresponds to one target image enhancement parameter;
37. and performing image enhancement processing on the region corresponding to the at least one characteristic point distribution density value according to the at least one target image enhancement parameter to obtain a target region image after the image enhancement processing.
In a specific implementation, the preset feature point distribution density value may be set by a user or default by a system. Taking the video image i as an example, the video image i is any one frame of video images in a plurality of frames of video images, the video image i can be subjected to image segmentation to obtain a target area image, the target area image is subjected to feature point analysis to divide the target area image into a plurality of areas, the area of each area can be equal, and further, the distribution density of the feature points of each of the plurality of regions may be determined to obtain a plurality of distribution densities of the feature points, a distribution density value of the feature points smaller than a preset distribution density value of the feature points is selected from the plurality of distribution density values to obtain at least one distribution density value of the feature points, a mapping relationship between the preset distribution density value of the feature points and the image enhancement parameter may be pre-stored in the electronic device, the image enhancement parameters may include an image enhancement algorithm identification and corresponding control parameters, and the image enhancement algorithm may be at least one of: the method includes the steps of gray level stretching, histogram equalization, smoothing, wavelet transformation and the like, which are not limited herein, and further, at least one target image enhancement parameter corresponding to at least one feature point distribution density value can be determined according to the mapping relation, each feature point distribution density value corresponds to one target image enhancement parameter, and an image enhancement processing is performed on a region corresponding to at least one feature point distribution density value according to the at least one target image enhancement parameter to obtain a target region image after the image enhancement processing.
In a possible example, between the step 102 and the step 103, the following steps may be further included:
a1, carrying out forward person detection on the multiple frames of video images to obtain a frame of video image of the target user appearing for the first time in the video clip as a starting frame video image;
a2, carrying out reverse person detection on the multi-frame video image to obtain a frame of video image of the target user appearing at the last time in the video clip as an end frame video image;
a3, intercepting a segment between the starting frame video image and the ending frame video image from the multi-frame video image to obtain a multi-frame first target video image;
a4, evaluating the image quality of the multiple frames of first target video images to obtain multiple image quality evaluation values, wherein each first target video image corresponds to one image quality evaluation value;
a5, selecting a target image quality evaluation value larger than a preset image quality evaluation value from the plurality of image quality evaluation values, and acquiring a video image corresponding to the target image quality evaluation value to obtain a plurality of second target video images;
then, in step 104, performing target extraction on the multiple frames of video images to obtain multiple target area images, which may be implemented as follows:
and performing target extraction on the multiple frames of second target video images to obtain multiple target area images.
The preset image quality evaluation value can be set by the user or defaulted by the system. The garbage delivery monitoring system can perform forward character detection on multiple frames of video images to obtain one frame of video image of a target user appearing for the first time in a video segment as an initial frame of video image, and then perform reverse character detection on multiple frames of video images to obtain one frame of video image of the target user appearing for the last time in the video segment as an end frame of video image, and further can intercept segments between the initial frame of video image from the multiple frames of video image to obtain multiple frames of first target video images, and further can perform image quality evaluation on the multiple frames of first target video images, and specifically can perform image quality evaluation on each frame of first target video images by using at least one of the following image quality evaluation indexes, such as: the information entropy, the distribution density of the feature points, the mean square error and the like are not limited herein, a plurality of image quality evaluation values are obtained, each first target video image corresponds to one image quality evaluation value, further, a target image quality evaluation value larger than a preset image quality evaluation value can be selected from the plurality of image quality evaluation values, a video image corresponding to the target image quality evaluation value is obtained, a plurality of second target video images are obtained, target extraction can be performed on a plurality of frames of second target video images, a plurality of target area images are obtained, and thus, the number of images extracted by the target can be reduced, and the target extraction efficiency can be improved.
104. And carrying out target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object.
The garbage delivery monitoring system can perform target identification on the images of the plurality of curtain areas to obtain target objects (such as garbage) contained in the images, and each target object corresponds to one target garbage type.
In specific implementation, a preset image library can be prestored in a memory of the garbage delivery monitoring system, the preset image library can include a plurality of images, each image corresponds to a type of garbage, each image corresponds to a garbage type, a plurality of target area images can be matched with the images in the preset image library to obtain successfully matched target images, and the garbage types corresponding to the target images are used as the target garbage types corresponding to the target objects.
105. And determining a target delivery garbage can of the target object according to the multi-frame video image, wherein the target delivery garbage can comprises at least one garbage delivery type.
The garbage delivery monitoring system can determine which garbage can the target user puts the target object into finally through a plurality of frames of video images to obtain the target delivery garbage can, and the target delivery garbage can comprises at least one garbage delivery type. In this application embodiment, different garbage bins correspond to different garbage delivery types, for example, the garbage delivery type that the wastepaper garbage bin corresponds is at least one of the following: newspapers, periodicals, books, various wrapping papers, and the like, without limitation. The corresponding garbage delivery type of the plastic garbage can be at least one of the following types: various plastic bags, plastic foams, plastic packages, disposable plastic meal box tableware, hard plastics, plastic toothbrushes, plastic cups, mineral water bottles and the like, which are not limited herein; the corresponding garbage delivery type of the glass garbage can be at least one of the following types: mainly comprises various glass bottles, broken glass sheets, mirrors, thermos bottles and the like, and is not limited herein; the corresponding garbage delivery type of the metal garbage can be at least one of the following types: pop-top cans, can boxes, and the like, without limitation; the garbage delivery type corresponding to the distributing garbage can be at least one of the following types: waste clothes, tablecloths, washcloths, school bags, shoes, etc., are not limited herein.
106. And when the at least one garbage delivery type comprises the target garbage type, confirming that the target user delivery behavior is legal.
And when the at least one garbage delivery type comprises a target garbage type corresponding to the target object, confirming that the delivery behavior of the target user is legal. Of course, when the target user delivery behavior is legal, the target user behavior can be prompted to be legal through voice, or integration operation can be performed on the target user.
107. Confirming that the target user delivery is illegal when the at least one spam delivery type does not include the target spam type.
In a specific implementation, when at least one of the spam delivery types does not include the target spam type, it is determined that the target user is not delivering the spam, and of course, the target user may be prompted to be unlawful in behavior by voice, or the target user may be deducted from the spam delivery type, or the target user is warned.
For example, 5 trash cans are placed in a cell: the three waste paper garbage cans, the plastic garbage cans, the glass garbage cans, the metal garbage cans and the cloth garbage cans are legal in behavior if the mineral water bottles are still needed, if the mineral water bottles are thrown into the cloth garbage cans, the mineral water bottles are illegal in behavior, and if the mineral water bottles are thrown into the plastic garbage cans, the mineral water bottles are legal in behavior.
In one possible example, after the step 107, the following steps may be further included:
b1, when the target object does not fall into any garbage can of the plurality of garbage cans, acquiring a face image of the target user;
b2, determining a registered user corresponding to the face image and a current score corresponding to the registered user;
b3, acquiring a behavior score corresponding to the target object;
b4, determining the target score of the registered user according to the current score and the behavior score;
b5, when the target score is lower than a preset threshold value, fine information is sent to the registered user;
and B6, when the target score is larger than or equal to the preset threshold value, sending warning information to the registered user.
In the specific implementation, the face image of the registered user can be pre-entered in the garbage delivery monitoring system to obtain the registration information base. In the embodiment of the application, when the garbage delivery monitoring system detects that a target object does not fall into any of a plurality of garbage cans, a face image of a target user can be obtained, the registered user corresponding to the face image and a current score corresponding to the registered user can be obtained according to the face image, and a behavior score corresponding to the target object is obtained, for example, legal garbage throwing is 0 score, illegal head garbage throwing is-1 score, garbage is not thrown into the garbage can for-3 score, and further, the target score of the registered user can be determined according to the current score and the behavior score, for example, the target score is the current score plus the behavior score; when the target score is lower than the preset threshold value, fine information can be sent to the registered user, and when the target score is larger than or equal to the preset threshold value, warning information can be sent to the registered user, and the like, so that the user can be effectively supervised to actively classify the garbage, and the environmental sanitation quality is improved.
In one possible example, the step B1 of acquiring the facial image of the target user may include the following steps:
b11, determining a face angle between each camera in the at least one camera and the target user to obtain a plurality of face angles;
b12, determining absolute values of differences between the face angles and a preset face angle to obtain a plurality of absolute values;
b13, determining a target camera corresponding to the minimum value in the plurality of absolute values;
b14, acquiring a target shooting distance between the target user and the target camera;
b15, determining a target zooming parameter according to the target shooting distance;
b16, acquiring target weather parameters;
b17, determining target shooting parameters corresponding to the target weather parameters;
b18, shooting according to the target zooming parameters and the target shooting parameters to obtain the target face image.
The preset face angle can be set by the user or defaulted by the system. The garbage delivery monitoring system can determine a face angle between each camera and a target user in at least one camera, obtain a plurality of face angles, further can determine absolute values of differences between the plurality of face angles and preset face angles, obtain a plurality of absolute values, further can select a target camera corresponding to a minimum value in the plurality of absolute values, and obtain a target shooting distance between the target user and the target camera, the garbage delivery monitoring system can determine a target zooming parameter corresponding to the target shooting distance according to a mapping relation between the preset distance and the zooming parameter, further, can obtain a target weather parameter, in the embodiment of the present application, the weather parameter can include one of: ultraviolet intensity, weather conditions (e.g., sunny, rainy, snowy, rainstorm, etc.), humidity, temperature, wind direction, sky brightness, etc., without limitation. The shooting parameter may be at least one of: white balance parameters, sensitivity ISO, exposure duration, defogging algorithm control parameters, and the like, which are not limited herein. In the specific implementation, the memory of the garbage delivery monitoring system can pre-store the mapping relation between the weather parameters and the shooting parameters, further, the target shooting parameters corresponding to the target weather parameters can be determined according to the mapping relation, and shooting is performed according to the target zooming parameters and the target shooting parameters to obtain the target face image.
It can be seen that the method for analyzing garbage delivery behavior described in the embodiment of the present application is applied to a garbage delivery monitoring system, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, each garbage can is configured to hold a type of garbage, the at least one camera is used to obtain a video clip when a target user delivers the garbage, analyze the video clip to obtain a plurality of frames of video images, perform target extraction on the plurality of frames of video images to obtain a plurality of target area images, perform target identification according to the plurality of target area images to obtain a target object and a target garbage type corresponding to the target object, determine a target delivery garbage can of the target object according to the plurality of frames of video images, and the target delivery garbage can includes at least one garbage delivery type, when the at least one garbage delivery type comprises the target garbage type, the target user delivery behavior is confirmed to be legal, and when the at least one garbage delivery type does not comprise the target garbage type, the target user delivery is confirmed to be illegal.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for analyzing a garbage delivery behavior according to an embodiment of the present application, and the method is applied to a garbage delivery monitoring system, where the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor a designated area, the designated area includes a plurality of garbage cans, and each garbage can is used for holding a type of garbage, and as shown in the figure, the method for analyzing a garbage delivery behavior includes:
201. acquiring a video clip of a target user when delivering garbage through the at least one camera;
202. analyzing the video clips to obtain multi-frame video images;
203. performing target extraction on the multi-frame video image to obtain a plurality of target area images;
204. performing target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
205. determining a target delivery garbage can of the target object according to the multi-frame video image, wherein the target delivery garbage can comprises at least one garbage delivery type;
206. when the at least one garbage delivery type comprises the target garbage type, confirming that the target user delivery behavior is legal;
207. confirming that the target user delivery is illegal when the at least one spam delivery type does not include the target spam type.
208. When the target object does not fall into any one of the plurality of trash cans, acquiring a face image of the target user;
209. determining a registered user corresponding to the face image and a current score corresponding to the registered user;
210. acquiring a behavior score corresponding to the target object;
211. determining a target score of the registered user according to the current score and the behavior score;
212. sending fine information to the registered user when the target score is lower than a preset threshold value;
213. and when the target score is greater than or equal to the preset threshold value, sending warning information to the registered user.
For the detailed description of the steps 201 to 213, reference may be made to the corresponding steps of the garbage delivery behavior analysis method described in the above fig. 1B, which are not described herein again.
It can be seen that the method for analyzing the garbage delivery behavior described in the embodiment of the present application is applied to a garbage delivery monitoring system, the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, each garbage can is configured to hold a type of garbage, and not only can identify whether the garbage delivered by a user is delivered to the corresponding garbage can when the user delivers the garbage, but also can score and alarm the user when the user does not put into the garbage can, so that the garbage delivery behavior of the user can be effectively monitored, and the garbage classification behavior of the user can be standardized.
Referring to fig. 3, in accordance with the above-mentioned embodiment, fig. 3 is a schematic structural diagram of a spam delivery monitoring system provided in this application, as shown in the figure, the spam delivery monitoring system includes a processor, a memory, a communication interface, and one or more programs, and may further include at least one camera, the one or more programs are stored in the memory and configured to be executed by the processor, and in this application, the programs include instructions for performing the following steps:
acquiring a video clip of a target user when delivering garbage through the at least one camera;
analyzing the video clips to obtain multi-frame video images;
performing target extraction on the multi-frame video image to obtain a plurality of target area images;
performing target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
determining a target delivery garbage can of the target object according to the multi-frame video image, wherein the target delivery garbage can comprises at least one garbage delivery type;
when the at least one garbage delivery type comprises the target garbage type, confirming that the target user delivery behavior is legal;
confirming that the target user delivery is illegal when the at least one spam delivery type does not include the target spam type.
It can be seen that the garbage delivery monitoring system described in the embodiment of the present application is applied to a garbage delivery monitoring system, the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, each garbage can is configured to contain a type of garbage, a video clip of a target user when delivering the garbage is obtained through the at least one camera, the video clip is analyzed to obtain a plurality of frames of video images, the plurality of frames of video images are subjected to target extraction to obtain a plurality of target area images, target identification is performed according to the plurality of target area images to obtain a target object and a target garbage type corresponding to the target object, the target delivery garbage can of the target object is determined according to the plurality of frames of video images, the target delivery garbage can includes at least one garbage delivery type, when the at least one garbage delivery type comprises the target garbage type, the target user delivery behavior is confirmed to be legal, and when the at least one garbage delivery type does not comprise the target garbage type, the target user delivery is confirmed to be illegal.
In one possible example, in the aspect of obtaining the video clip of the target user when delivering the spam through the at least one camera, in the embodiment of the present application, the program includes instructions for performing the following steps:
detecting a distance between the target user and each of the plurality of trash cans to obtain a plurality of distance values;
and when the average value among the plurality of distance values is within a preset range, controlling the at least one camera to shoot the target user to obtain a video clip of the target user when delivering the garbage.
In one possible example, the program further includes instructions for performing the steps of:
carrying out forward character detection on the multiple frames of video images to obtain a frame of video image of the target user appearing for the first time in the video clip as an initial frame of video image;
carrying out reverse character detection on the multiple frames of video images to obtain a frame of video image of the target user appearing at the last time in the video clip as an end frame of video image;
capturing a segment between the initial frame video image and the ending frame video image from the multi-frame video image to obtain a plurality of frames of first target video images;
performing image quality evaluation on the multiple frames of first target video images to obtain multiple image quality evaluation values, wherein each first target video image corresponds to one image quality evaluation value;
selecting a target image quality evaluation value larger than a preset image quality evaluation value threshold from the plurality of image quality evaluation values, and acquiring a video image corresponding to the target image quality evaluation value to obtain a plurality of second target video images;
the target extraction of the multi-frame video image to obtain a plurality of target area images comprises the following steps:
and performing target extraction on the multiple frames of second target video images to obtain multiple target area images.
In one possible example, the program further includes instructions for performing the steps of:
when the target object does not fall into any one of the plurality of trash cans, acquiring a face image of the target user;
determining a registered user corresponding to the face image and a current score corresponding to the registered user;
acquiring a behavior score corresponding to the target object;
determining a target score of the registered user according to the current score and the behavior score;
sending fine information to the registered user when the target score is lower than a preset threshold value;
and when the target score is greater than or equal to the preset threshold value, sending warning information to the registered user.
In one possible example, in the acquiring the face image of the target user, the program includes instructions for performing the following steps:
determining a face angle between each camera in the at least one camera and the target user to obtain a plurality of face angles;
determining absolute values of differences between the plurality of face angles and a preset face angle to obtain a plurality of absolute values;
determining a target camera corresponding to the minimum value in the plurality of absolute values;
acquiring a target shooting distance between the target user and the target camera;
determining a target zooming parameter according to the target shooting distance;
acquiring a target weather parameter;
determining target shooting parameters corresponding to the target weather parameters;
shooting according to the target zooming parameters and the target shooting parameters to obtain the target face image.
The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It will be appreciated that the spam delivery monitoring system, in order to achieve the above functionality, may include corresponding hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the present application is capable of hardware or a combination of hardware and computer software implementing the various illustrative elements and algorithm steps described in connection with the embodiments provided herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiment of the present application, the functional units of the garbage delivery monitoring system may be divided according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
Fig. 4A is a block diagram of functional units of a spam delivery behavior analyzing apparatus 400 according to an embodiment of the present application. This rubbish delivery action analysis device 400 is applied to rubbish delivery monitored control system, rubbish delivery monitored control system includes at least one camera, rubbish delivery monitored control system is used for monitoring appointed area, including a plurality of garbage bins in the appointed area, each garbage bin is used for a kind of rubbish of splendid attire, the device includes: an acquisition unit 401, a parsing unit 402, an extraction unit 403, a recognition unit 404, a determination unit 405, and an analysis unit 406, wherein,
an obtaining unit 401, configured to obtain, through the at least one camera, a video clip when a target user delivers spam;
an analyzing unit 402, configured to analyze the video segment to obtain multiple frames of video images;
an extracting unit 403, configured to perform target extraction on the multiple frames of video images to obtain multiple target area images;
an identifying unit 404, configured to perform target identification according to the multiple target area images to obtain a target object and a target garbage type corresponding to the target object;
a determining unit 405, configured to determine a target delivery trash can of the target object according to the multiple frames of video images, where the target delivery trash can includes at least one trash delivery type;
an analyzing unit 406, configured to confirm that the target user delivery behavior is legal when the at least one spam delivery type includes the target spam type; and confirming that the target user delivery is illegal when the at least one spam delivery type does not comprise the target spam type.
It can be seen that the device for analyzing garbage delivery behavior described in the embodiment of the present application is applied to a garbage delivery monitoring system, the garbage delivery monitoring system includes at least one camera, the garbage delivery monitoring system is configured to monitor an assigned area, the assigned area includes a plurality of garbage cans, each garbage can is configured to hold a type of garbage, the at least one camera is used to obtain a video clip when a target user delivers the garbage, analyze the video clip to obtain a plurality of frames of video images, perform target extraction on the plurality of frames of video images to obtain a plurality of target area images, perform target identification according to the plurality of target area images to obtain a target object and a target garbage type corresponding to the target object, determine a target delivery garbage can of the target object according to the plurality of frames of video images, the target delivery garbage can includes at least one garbage delivery type, when the at least one garbage delivery type comprises the target garbage type, the target user delivery behavior is confirmed to be legal, and when the at least one garbage delivery type does not comprise the target garbage type, the target user delivery is confirmed to be illegal.
In one possible example, in terms of the acquiring, by the at least one camera, the video clip of the target user when delivering the spam, the acquiring unit 401 is specifically configured to:
detecting a distance between the target user and each of the plurality of trash cans to obtain a plurality of distance values;
and when the average value among the plurality of distance values is within a preset range, controlling the at least one camera to shoot the target user to obtain a video clip of the target user when delivering the garbage.
In one possible example, as shown in fig. 4B, fig. 4B is a further modified structure of the garbage delivery behavior analyzing apparatus 400 shown in fig. 4A, which may further include, compared with fig. 4A: the detection unit 407, the interception unit 408, the evaluation unit 409 and the selection unit 410 are specifically as follows:
a detecting unit 407, configured to perform forward person detection on the multiple frames of video images, to obtain a frame of video image in which the target user appears for the first time in the video segment as a start frame video image; carrying out reverse person detection on the multiple frames of video images to obtain a frame of video image of the target user appearing in the video clip at the last time as an end frame of video image;
an intercepting unit 408, configured to intercept, from the multiple frames of video images, a segment between the start frame video image and the end frame video image to obtain multiple frames of first target video images;
an evaluation unit 409, configured to perform image quality evaluation on the multiple frames of first target video images to obtain multiple image quality evaluation values, where each first target video image corresponds to one image quality evaluation value;
a selecting unit 410, configured to select a target image quality evaluation value larger than a preset image quality evaluation value threshold from the multiple image quality evaluation values, and obtain a video image corresponding to the target image quality evaluation value, so as to obtain multiple second target video images;
in the aspect of performing target extraction on the multiple frames of video images to obtain multiple target area images, the extracting unit 403 is specifically configured to:
and performing target extraction on the multiple frames of second target video images to obtain multiple target area images.
In one possible example, as shown in fig. 4C, fig. 4C is a further modified structure of the garbage delivery behavior analyzing apparatus 400 shown in fig. 4A, which may further include, compared with fig. 4A: the sending unit 411 specifically includes:
the obtaining unit 401 is further specifically configured to obtain a face image of the target user when the target object does not fall into any of the plurality of trash cans;
the determining unit 405 is further specifically configured to determine a registered user corresponding to the face image and a current score corresponding to the registered user;
the obtaining unit 401 is further configured to obtain a behavior score corresponding to the target object;
the determining unit 405 is further specifically configured to determine a target score of the registered user according to the current score and the behavior score;
a sending unit 411, configured to send fine information to the registered user when the target score is lower than a preset threshold; and sending warning information to the registered user when the target score is greater than or equal to the preset threshold value.
In a possible example, in terms of acquiring the face image of the target user, the acquiring unit 401 is specifically configured to:
determining a face angle between each camera in the at least one camera and the target user to obtain a plurality of face angles;
determining absolute values of differences between the plurality of face angles and a preset face angle to obtain a plurality of absolute values;
determining a target camera corresponding to the minimum value in the plurality of absolute values;
acquiring a target shooting distance between the target user and the target camera;
determining a target zooming parameter according to the target shooting distance;
acquiring a target weather parameter;
determining target shooting parameters corresponding to the target weather parameters;
shooting according to the target zooming parameters and the target shooting parameters to obtain the target face image.
It can be understood that the functions of each program module of the spam delivery behavior analyzing apparatus according to this embodiment can be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process thereof can refer to the related description of the foregoing method embodiment, which is not described herein again.
Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, the computer program enables a computer to execute part or all of the steps of any one of the methods as described in the above method embodiments, and the computer includes a spam delivery monitoring system.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package, said computer comprising a spam delivery monitoring system.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-mentioned method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A garbage delivery behavior analysis method is applied to a garbage delivery monitoring system, the garbage delivery monitoring system comprises at least one camera, the garbage delivery monitoring system is used for monitoring a designated area, a plurality of garbage cans are arranged in the designated area, each garbage can is used for containing a type of garbage, and the method comprises the following steps:
acquiring a video clip of a target user when delivering garbage through the at least one camera;
analyzing the video clips to obtain multi-frame video images;
performing target extraction on the multi-frame video image to obtain a plurality of target area images;
performing target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
determining a target delivery garbage can of the target object according to the multi-frame video image, wherein the target delivery garbage can comprises at least one garbage delivery type;
when the at least one garbage delivery type comprises the target garbage type, confirming that the target user delivery behavior is legal;
confirming that the target user delivery is illegal when the at least one spam delivery type does not include the target spam type.
2. The method according to claim 1, wherein the obtaining of the video clip of the target user when delivering the garbage through the at least one camera comprises:
detecting a distance between the target user and each of the plurality of trash cans to obtain a plurality of distance values;
and when the average value among the plurality of distance values is within a preset range, controlling the at least one camera to shoot the target user to obtain a video clip of the target user when delivering the garbage.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
carrying out forward character detection on the multiple frames of video images to obtain a frame of video image of the target user appearing for the first time in the video clip as an initial frame of video image;
carrying out reverse character detection on the multiple frames of video images to obtain a frame of video image of the target user appearing at the last time in the video clip as an end frame of video image;
capturing a segment between the initial frame video image and the ending frame video image from the multi-frame video image to obtain a plurality of frames of first target video images;
performing image quality evaluation on the multiple frames of first target video images to obtain multiple image quality evaluation values, wherein each first target video image corresponds to one image quality evaluation value;
selecting a target image quality evaluation value larger than a preset image quality evaluation value threshold from the plurality of image quality evaluation values, and acquiring a video image corresponding to the target image quality evaluation value to obtain a plurality of second target video images;
the target extraction of the multi-frame video image to obtain a plurality of target area images comprises the following steps:
and performing target extraction on the multiple frames of second target video images to obtain multiple target area images.
4. The method according to any one of claims 1-3, further comprising:
when the target object does not fall into any one of the plurality of trash cans, acquiring a face image of the target user;
determining a registered user corresponding to the face image and a current score corresponding to the registered user;
acquiring a behavior score corresponding to the target object;
determining a target score of the registered user according to the current score and the behavior score;
sending fine information to the registered user when the target score is lower than a preset threshold value;
and when the target score is greater than or equal to the preset threshold value, sending warning information to the registered user.
5. The method of claim 4, wherein the obtaining the facial image of the target user comprises:
determining a face angle between each camera in the at least one camera and the target user to obtain a plurality of face angles;
determining absolute values of differences between the plurality of face angles and a preset face angle to obtain a plurality of absolute values;
determining a target camera corresponding to the minimum value in the plurality of absolute values;
acquiring a target shooting distance between the target user and the target camera;
determining a target zooming parameter according to the target shooting distance;
acquiring a target weather parameter;
determining target shooting parameters corresponding to the target weather parameters;
shooting according to the target zooming parameters and the target shooting parameters to obtain the target face image.
6. A garbage delivery behavior analysis device is applied to a garbage delivery monitoring system, the garbage delivery monitoring system comprises at least one camera, the garbage delivery monitoring system is used for monitoring a designated area, a plurality of garbage cans are arranged in the designated area, each garbage can is used for containing one type of garbage, and the device comprises:
the acquisition unit is used for acquiring video clips of the target user when delivering the garbage through the at least one camera;
the analysis unit is used for analyzing the video clips to obtain multi-frame video images;
the extraction unit is used for carrying out target extraction on the multi-frame video images to obtain a plurality of target area images;
the identification unit is used for carrying out target identification according to the target area images to obtain a target object and a target rubbish type corresponding to the target object;
a determining unit, configured to determine a target delivery trash can of the target object according to the multiple frames of video images, where the target delivery trash can includes at least one trash delivery type;
the analysis unit is used for confirming that the target user delivery behavior is legal when the at least one garbage delivery type comprises the target garbage type; and confirming that the target user delivery is illegal when the at least one spam delivery type does not comprise the target spam type.
7. The apparatus according to claim 6, wherein in the aspect of acquiring the video clip of the target user while delivering the spam through the at least one camera, the acquiring unit is specifically configured to:
detecting a distance between the target user and each of the plurality of trash cans to obtain a plurality of distance values;
and when the average value among the plurality of distance values is within a preset range, controlling the at least one camera to shoot the target user to obtain a video clip of the target user when delivering the garbage.
8. The apparatus of claim 6 or 7, wherein the method further comprises:
the detection unit is used for carrying out forward character detection on the multiple frames of video images to obtain a frame of video image of the target user appearing for the first time in the video clip as a starting frame of video image; carrying out reverse person detection on the multiple frames of video images to obtain a frame of video image of the target user appearing in the video clip at the last time as an end frame of video image;
the intercepting unit is used for intercepting a segment between the starting frame video image and the ending frame video image from the multi-frame video image to obtain a multi-frame first target video image;
the evaluation unit is used for evaluating the image quality of the multiple frames of first target video images to obtain a plurality of image quality evaluation values, and each first target video image corresponds to one image quality evaluation value;
the selecting unit is used for selecting a target image quality evaluation value larger than a preset image quality evaluation value threshold from the plurality of image quality evaluation values, acquiring a video image corresponding to the target image quality evaluation value and obtaining a plurality of second target video images;
in the aspect of performing target extraction on the multiple frames of video images to obtain multiple target area images, the extraction unit is specifically configured to:
and performing target extraction on the multiple frames of second target video images to obtain multiple target area images.
9. A spam monitoring system comprising a processor, a memory for storing one or more programs and configured for execution by the processor, the programs comprising instructions for carrying out the steps of the method according to any one of claims 1-5.
10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-5.
CN201910895418.6A 2019-09-21 2019-09-21 Garbage delivery behavior analysis method and related product Active CN110795999B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910895418.6A CN110795999B (en) 2019-09-21 2019-09-21 Garbage delivery behavior analysis method and related product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910895418.6A CN110795999B (en) 2019-09-21 2019-09-21 Garbage delivery behavior analysis method and related product

Publications (2)

Publication Number Publication Date
CN110795999A true CN110795999A (en) 2020-02-14
CN110795999B CN110795999B (en) 2022-07-12

Family

ID=69438741

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910895418.6A Active CN110795999B (en) 2019-09-21 2019-09-21 Garbage delivery behavior analysis method and related product

Country Status (1)

Country Link
CN (1) CN110795999B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111498327A (en) * 2020-04-13 2020-08-07 广州东软科技有限公司 System and method for improving garbage classification accuracy based on block chain technology
CN111723772A (en) * 2020-06-30 2020-09-29 平安国际智慧城市科技股份有限公司 Perishable garbage identification method and device based on image identification and computer equipment
CN111814757A (en) * 2020-08-20 2020-10-23 许昌学院 Garbage classification simulation system based on computer software
CN112257489A (en) * 2020-07-10 2021-01-22 上海森元原环保科技有限公司 Automatic detection system and method for garbage bag throwing
CN112836655A (en) * 2021-02-07 2021-05-25 上海卓繁信息技术股份有限公司 Method and device for identifying identity of illegal actor and electronic equipment
CN113111769A (en) * 2021-04-09 2021-07-13 平安国际智慧城市科技股份有限公司 Garbage illegal putting behavior monitoring method and device and computer equipment
CN114077877A (en) * 2022-01-19 2022-02-22 人民中科(济南)智能技术有限公司 Newly added garbage identification method and device, computer equipment and storage medium
CN114120136A (en) * 2022-01-27 2022-03-01 人民中科(济南)智能技术有限公司 Method and device for classifying garbage and storage medium
EP4187500A1 (en) * 2021-11-30 2023-05-31 Beijing Baidu Netcom Science Technology Co., Ltd. Method and apparatus of detecting event, device, storage medium and program product

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5552853A (en) * 1992-01-09 1996-09-03 Nikon Corporation Auto focusing apparatus in a camera
US20130070115A1 (en) * 2011-09-20 2013-03-21 Altek Corporation Feature Data Compression Device, Multi-Directional Face Detection System and Detection Method Thereof
CN105007413A (en) * 2015-06-30 2015-10-28 广东欧珀移动通信有限公司 Shooting control method and user terminal
CN204979922U (en) * 2015-06-15 2016-01-20 深圳市德立信环境工程有限公司 Waste classification operation management system
CN105678267A (en) * 2016-01-08 2016-06-15 浙江宇视科技有限公司 Scene recognition method and device
CN106516490A (en) * 2017-01-11 2017-03-22 克立尔(北京)环境科技发展有限公司 Novel intelligent garbage collection station
CN107640480A (en) * 2017-10-19 2018-01-30 广东拜登网络技术有限公司 The method and apparatus and storage medium and terminal device of refuse classification retrospect
CN107832675A (en) * 2017-10-16 2018-03-23 广东欧珀移动通信有限公司 Processing method of taking pictures and Related product
CN108706246A (en) * 2018-05-31 2018-10-26 深圳市零度智控科技有限公司 Intelligent refuse classification reclaimer, control method, device and storage medium
CN108861238A (en) * 2018-09-14 2018-11-23 金威建设集团有限公司 A kind of dustbin with identification garbage classification function
CN108922016A (en) * 2018-05-07 2018-11-30 北京三辰环卫机械有限公司 Recovery method and device, garbage reclamation cabinet and garbage retrieving system
CN208165794U (en) * 2017-11-14 2018-11-30 中国矿业大学 A kind of intelligent classification dustbin
CN109040603A (en) * 2018-10-15 2018-12-18 Oppo广东移动通信有限公司 High-dynamic-range image acquisition method, device and mobile terminal
CN109018773A (en) * 2018-08-06 2018-12-18 百度在线网络技术（北京）有限公司 Refuse classification method, device and storage medium
CN109292312A (en) * 2018-09-28 2019-02-01 宁波暇客物联科技有限公司 A kind of accessible garbage recovery device used, recycling excitation method and system
CN208647731U (en) * 2018-05-07 2019-03-26 北京三辰环卫机械有限公司 Garbage reclamation cabinet and garbage retrieving system
CN109684979A (en) * 2018-12-18 2019-04-26 深圳云天励飞技术有限公司 A kind of refuse classification method based on image recognition technology, device and electronic equipment
CN109857007A (en) * 2018-12-04 2019-06-07 杭州电子科技大学 A kind of Intelligent refuse classification system and working method based on technology of Internet of things
CN110053903A (en) * 2019-04-25 2019-07-26 重庆左岸环境服务股份有限公司 Categorized consumer waste retrieval management system and method

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5552853A (en) * 1992-01-09 1996-09-03 Nikon Corporation Auto focusing apparatus in a camera
US20130070115A1 (en) * 2011-09-20 2013-03-21 Altek Corporation Feature Data Compression Device, Multi-Directional Face Detection System and Detection Method Thereof
CN204979922U (en) * 2015-06-15 2016-01-20 深圳市德立信环境工程有限公司 Waste classification operation management system
CN105007413A (en) * 2015-06-30 2015-10-28 广东欧珀移动通信有限公司 Shooting control method and user terminal
CN105678267A (en) * 2016-01-08 2016-06-15 浙江宇视科技有限公司 Scene recognition method and device
CN106516490A (en) * 2017-01-11 2017-03-22 克立尔(北京)环境科技发展有限公司 Novel intelligent garbage collection station
CN107832675A (en) * 2017-10-16 2018-03-23 广东欧珀移动通信有限公司 Processing method of taking pictures and Related product
CN107640480A (en) * 2017-10-19 2018-01-30 广东拜登网络技术有限公司 The method and apparatus and storage medium and terminal device of refuse classification retrospect
CN208165794U (en) * 2017-11-14 2018-11-30 中国矿业大学 A kind of intelligent classification dustbin
CN208647731U (en) * 2018-05-07 2019-03-26 北京三辰环卫机械有限公司 Garbage reclamation cabinet and garbage retrieving system
CN108922016A (en) * 2018-05-07 2018-11-30 北京三辰环卫机械有限公司 Recovery method and device, garbage reclamation cabinet and garbage retrieving system
CN108706246A (en) * 2018-05-31 2018-10-26 深圳市零度智控科技有限公司 Intelligent refuse classification reclaimer, control method, device and storage medium
CN109018773A (en) * 2018-08-06 2018-12-18 百度在线网络技术（北京）有限公司 Refuse classification method, device and storage medium
CN108861238A (en) * 2018-09-14 2018-11-23 金威建设集团有限公司 A kind of dustbin with identification garbage classification function
CN109292312A (en) * 2018-09-28 2019-02-01 宁波暇客物联科技有限公司 A kind of accessible garbage recovery device used, recycling excitation method and system
CN109040603A (en) * 2018-10-15 2018-12-18 Oppo广东移动通信有限公司 High-dynamic-range image acquisition method, device and mobile terminal
CN109857007A (en) * 2018-12-04 2019-06-07 杭州电子科技大学 A kind of Intelligent refuse classification system and working method based on technology of Internet of things
CN109684979A (en) * 2018-12-18 2019-04-26 深圳云天励飞技术有限公司 A kind of refuse classification method based on image recognition technology, device and electronic equipment
CN110053903A (en) * 2019-04-25 2019-07-26 重庆左岸环境服务股份有限公司 Categorized consumer waste retrieval management system and method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吴新华等: "基于二维码识别的垃圾分类投放***设计", 《江苏工程职业技术学院学报》, no. 01, 25 March 2019 (2019-03-25) *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111498327A (en) * 2020-04-13 2020-08-07 广州东软科技有限公司 System and method for improving garbage classification accuracy based on block chain technology
CN111723772A (en) * 2020-06-30 2020-09-29 平安国际智慧城市科技股份有限公司 Perishable garbage identification method and device based on image identification and computer equipment
CN111723772B (en) * 2020-06-30 2024-03-19 平安国际智慧城市科技股份有限公司 Perishable garbage identification method and device based on image identification and computer equipment
CN112257489A (en) * 2020-07-10 2021-01-22 上海森元原环保科技有限公司 Automatic detection system and method for garbage bag throwing
CN111814757A (en) * 2020-08-20 2020-10-23 许昌学院 Garbage classification simulation system based on computer software
CN111814757B (en) * 2020-08-20 2024-01-09 许昌学院 Garbage classification simulation system based on computer software
CN112836655A (en) * 2021-02-07 2021-05-25 上海卓繁信息技术股份有限公司 Method and device for identifying identity of illegal actor and electronic equipment
CN112836655B (en) * 2021-02-07 2024-05-28 上海卓繁信息技术股份有限公司 Method and device for identifying identity of illegal actor and electronic equipment
CN113111769A (en) * 2021-04-09 2021-07-13 平安国际智慧城市科技股份有限公司 Garbage illegal putting behavior monitoring method and device and computer equipment
EP4187500A1 (en) * 2021-11-30 2023-05-31 Beijing Baidu Netcom Science Technology Co., Ltd. Method and apparatus of detecting event, device, storage medium and program product
CN114077877B (en) * 2022-01-19 2022-05-13 人民中科(北京)智能技术有限公司 Newly-added garbage identification method and device, computer equipment and storage medium
CN114077877A (en) * 2022-01-19 2022-02-22 人民中科(济南)智能技术有限公司 Newly added garbage identification method and device, computer equipment and storage medium
CN114120136A (en) * 2022-01-27 2022-03-01 人民中科(济南)智能技术有限公司 Method and device for classifying garbage and storage medium

Also Published As

Publication number Publication date
CN110795999B (en) 2022-07-12

Similar Documents

Publication Publication Date Title
CN110795999B (en) Garbage delivery behavior analysis method and related product
CN105564864B (en) Dustbin, the refuse classification method of dustbin and system
CN109684979B (en) Image recognition technology-based garbage classification method and device and electronic equipment
CN109858371B (en) Face recognition method and device
CN111008571B (en) Indoor garbage treatment method and related product
CN107808358B (en) Automatic detection method for image watermark
CN110991271B (en) Garbage classification processing method and related products
CN110479638B (en) Garbage classification method and system
US11335086B2 (en) Methods and electronic devices for automated waste management
CN110796098B (en) Method, device, equipment and storage medium for training and auditing content auditing model
Uy et al. Automated traffic violation apprehension system using genetic algorithm and artificial neural network
CN112488021A (en) Monitoring video-based garbage delivery violation detection method and system
CN111814517B (en) Garbage delivery detection method and related product
AU2008200967A1 (en) Spatio-activity based mode matching
CN112926431A (en) Garbage detection method, device, equipment and computer storage medium
RU2019136604A (en) PLATFORM FOR MANAGING AND VERIFICATION OF VIDEO CONTENT, PHOTOS OR SIMILAR CONTENT GENERATED BY DIFFERENT DEVICES
CN110921154A (en) Method and device for controlling garbage collection patrol car and garbage collection patrol car
CN110852236A (en) Target event determination method and device, storage medium and electronic device
CN112298844A (en) Garbage classification monitoring method and device
CN107123076A (en) A kind of waste management system and waste management method
CN111832749A (en) Garbage bag identification method and related device
CN212048939U (en) Intelligent garbage recycling device for community
CN107472768A (en) A kind of refuse classification identifier
CN110775483A (en) Community intelligent garbage recycling device and method, electronic equipment and storage medium
CN111126314A (en) Passenger flow statistical visual method and system based on 3D point cloud data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant