CN111291632B - Pedestrian state detection method, device and equipment - Google Patents
Pedestrian state detection method, device and equipment Download PDFInfo
- Publication number
- CN111291632B CN111291632B CN202010054088.0A CN202010054088A CN111291632B CN 111291632 B CN111291632 B CN 111291632B CN 202010054088 A CN202010054088 A CN 202010054088A CN 111291632 B CN111291632 B CN 111291632B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- image
- attribute
- state detection
- detection model
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a pedestrian state detection method, a device and equipment, which comprise the following steps: acquiring an existing pedestrian image; establishing a pedestrian state detection model, and processing the existing pedestrian image by using the pedestrian state detection model; inputting the processed pedestrian image into a pedestrian state detection model for training to obtain a trained pedestrian state detection model; and inputting the real-time pedestrian image into a trained pedestrian state detection model, and outputting a judgment result of the pedestrian state by the pedestrian state detection model. According to the pedestrian state detection method, the pedestrian state detection model is established, and the acquired human body detection image, human face attribute detection image and pedestrian attribute detection image are input into the pedestrian state detection model, so that the pedestrian state detection model can comprehensively judge the state information of the pedestrian, the defect that the pedestrian comprehensive condition cannot be judged in the existing pedestrian state detection method is overcome, and the pedestrian state detection method has important significance in practical application.
Description
Technical Field
The present invention relates to the field of pedestrian detection technologies, and in particular, to a method, an apparatus, and a device for detecting a pedestrian state.
Background
Along with the development of science and technology, people can identify various information in images, but at present, image identification is also applied to the security field on a large scale, and state information of passers-by, security gates, barrier gates and the like are obtained through images. However, in the prior art, the number of pedestrians can only be judged by acquiring the state information of the pedestrians through the images, and whether the pedestrians carry luggage, children and the age states of the pedestrians can not be comprehensively detected, so that when the pedestrians pass through the security check channel, the pedestrians can not be guided by the staff, the pedestrians can not be reminded to put the luggage into the luggage band, or priority channels can not be provided for the seniors.
In summary, the method for detecting the pedestrian state in the prior art has the defect that the comprehensive situation of the pedestrian cannot be judged.
Disclosure of Invention
The invention provides a pedestrian state detection method, a pedestrian state detection device and pedestrian state detection equipment, which solve the defect that the comprehensive pedestrian condition cannot be judged in the pedestrian state detection method in the prior art.
The invention provides a pedestrian state detection method, which comprises the following steps:
step S1: acquiring an existing pedestrian image;
step S2: establishing a pedestrian state detection model, and processing the existing pedestrian image by using the pedestrian state detection model;
step S3: inputting the processed pedestrian image into a pedestrian state detection model for training to obtain a trained pedestrian state detection model;
step S4: and inputting the real-time pedestrian image into a trained pedestrian state detection model, and outputting a judgment result of the pedestrian state by the pedestrian state detection model.
Preferably, the step S2 specifically includes the following steps:
step S201: inputting the pedestrian image into a pedestrian state detection model, and detecting a human body in the pedestrian image by the pedestrian state detection model to obtain a human body detection image;
step S202: normalizing the human body detection image by the pedestrian state detection model to obtain a pedestrian attribute detection image;
step S203: the pedestrian state detection model performs face detection on the human body detection image and aligns the human body detection image to obtain a face attribute detection image.
Preferably, attribute labeling is performed on the human body detection image, the human face attribute detection image and the pedestrian attribute detection image respectively.
Preferably, the attribute of the human body detection image is the number of pedestrians; the attribute categories of the face attribute detection image include: gender, age, expression, face pose, and face wear; the attribute category of the pedestrian attribute detection image includes: backpack, bag, satchel, trunk, carrying child, wheelchair, and stroller.
Preferably, in step S3, the method specifically includes the following steps:
step S301: dividing the human body detection image, the human face attribute detection image and the pedestrian attribute detection image into a training set and a testing set according to a certain proportion;
step S302: sequentially inputting the training set of the human body detection image, the training set of the human face attribute detection image and the training set of the pedestrian attribute detection image into the pedestrian state detection model to optimize the weight parameters of the pedestrian state detection model;
step S303: and inputting the test set into the trained pedestrian state detection model to obtain the optimal weight parameters of the pedestrian state detection model.
Preferably, the face attribute detection training set of the face attribute detection images uses the attribute of each face attribute detection image as a class, and the pedestrian attribute training set of the pedestrian attribute detection images uses the attribute of each pedestrian attribute detection image as a class.
Preferably, in step S301, the human body detection image is used as a positive sample of a human body detection training set, the image without the pedestrian in the existing image is used as a negative sample of the human body detection training set, the human face attribute detection training set includes all the categories of the attribute of the human face attribute detection image and the number of each category is equal, and the pedestrian attribute training set includes all the categories of the pedestrian attribute detection image and the number of each category is equal.
Preferably, the pedestrian state detection model comprises a human body detection model, a human face attribute detection model and a pedestrian attribute detection model, wherein the human face attribute detection model and the pedestrian attribute detection model are formed by a convolutional neural network, at least one deconvolution layer and at least one index layer are arranged between a first layer of the convolutional neural network and a last layer of the convolutional neural network, and a plurality of convolution kernels with different sizes are adopted when the index is convolved; the human body detection model adopts a faceboxes algorithm.
The pedestrian state detection device comprises a pedestrian image acquisition module, an image preprocessing module and a pedestrian state detection model module;
the pedestrian image acquisition module is used for acquiring images of pedestrians;
the image preprocessing module is used for preprocessing images of pedestrians;
the pedestrian state detection model module is used for establishing a pedestrian state detection model and outputting a pedestrian state detection result.
A pedestrian status detection device, the device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute a pedestrian status detection method according to any one of claims 1-8 according to instructions in the program code.
From the above technical scheme, the invention has the following advantages:
according to the embodiment of the invention, the pedestrian state detection model is established, and the acquired human body detection image, human face attribute detection image and pedestrian attribute detection image are input into the pedestrian state detection model, so that the pedestrian state detection model can comprehensively judge the state information of the pedestrians, the defect that the pedestrian comprehensive condition cannot be judged in the pedestrian state detection method in the prior art is overcome, the pedestrian passing through the security inspection channel is guided by security inspection personnel, and the pedestrian detection method has important significance in practical application.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart of a method, an apparatus, and a device for detecting a pedestrian state according to an embodiment of the present invention.
Fig. 2 is a device frame diagram of a pedestrian status detection method, device and equipment according to an embodiment of the present invention.
Fig. 3 is an apparatus frame diagram of a pedestrian status detection method, apparatus and device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a pedestrian state detection method, a pedestrian state detection device and pedestrian state detection equipment, which are used for solving the technical problem that the comprehensive pedestrian condition cannot be judged in the pedestrian state detection method in the prior art.
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of a method, an apparatus, and a device for detecting a pedestrian status according to an embodiment of the present invention.
As shown in fig. 1, the pedestrian state detection method provided by the invention comprises the following steps:
step S1: acquiring an existing pedestrian image;
the existing pedestrian image can be selected from historical images obtained by shooting through a camera of the security check ramp, and the pedestrian image in the security check ramp covers most types of pedestrian state images, so that the subsequent pedestrian detection model is beneficial to learning and detecting the pedestrian image.
Step S2: establishing a pedestrian state detection model, and processing the existing pedestrian image by using the pedestrian state detection model;
step S3: inputting the processed pedestrian image into a pedestrian state detection model for training, and optimizing the pedestrian state detection model to obtain a trained pedestrian state detection model;
the processed existing pedestrian images are input into a pedestrian state detection model for training, the pedestrian state detection model detects and identifies images of different types and images of different attribute types of the same type, and the images are optimized, so that a trained pedestrian state detection model is obtained.
Step S4: and inputting the real-time pedestrian image into a trained pedestrian state detection model, and outputting a judgment result of the pedestrian state by the pedestrian state detection model.
The real-time pedestrian image is input into a trained pedestrian state detection model, and the pedestrian state detection model can directly detect and judge the real-time pedestrian image, so that the comprehensive state of the pedestrian is directly judged.
As a preferred embodiment, step S2 specifically includes the steps of:
step S201: inputting the pedestrian image into a pedestrian state detection model, and detecting a human body in the pedestrian image by the pedestrian state detection model to obtain a human body detection image;
step S202: normalizing the human body detection image by the pedestrian state detection model to obtain a pedestrian attribute detection image;
step S203: the pedestrian state detection model performs face detection on the human body detection image and aligns the human body detection image to obtain a face attribute detection image.
Dividing the existing pedestrian image into human body detection images, so that the pedestrian state detection model only focuses on human bodies in the images; the existing pedestrian image is divided into human face attribute detection images, so that the pedestrian state detection model only pays attention to human faces in the images; the existing pedestrian image is divided into pedestrian attribute detection images, so that the pedestrian state detection model only pays attention to the attribute of the pedestrian; the existing pedestrian images are divided into different categories, so that the pedestrian state detection model is beneficial to focusing on only a specific point in the images, and the learning efficiency of the pedestrian state detection model is improved.
The pedestrian state detection model detects a pedestrian image to obtain a sub-image formed by a human matrix, normalizes the sub-image to obtain 128×256 human matrix sub-images, obtains a human face image on the basis of the human matrix sub-images by using a human face detection algorithm (namely mtcnn or faceboxes), and aligns the human face image to obtain a human face attribute detection image, wherein the size of the human face attribute detection image is 96×112.
As a preferred embodiment, attribute labeling is performed on the human body detection image, the human face attribute detection image, and the pedestrian attribute detection image, respectively.
By labeling the attributes in the human body detection image, the human face attribute detection image and the pedestrian attribute detection image, the characteristics which need to be identified by the pedestrian state detection model in different types of images can be highlighted, interference items in the images can be reduced, and the learning speed of the pedestrian state detection model can be improved.
As a preferred embodiment, the attribute of the human body detection image is the number of pedestrians; the attribute categories of the face attribute detection image include: gender, age, expression, face pose, and face wear; the attribute category of the pedestrian attribute detection image includes: backpack, bag, satchel, trunk, child-carrying, wheelchair, and stroller.
Gender, age, expression, facial pose and facial wear are the most intuitive attributes of a human face, and the pedestrian state detection model can infer the comprehensive information of the appearance of the pedestrian by learning the attributes. The attribute of the pedestrian attribute detection image can enable the pedestrian state detection model to infer the comprehensive information of the appearance of the pedestrian, so that whether the pedestrian is a knapsack, carries luggage or a handicapped person sitting on a wheelchair or not is judged, and the pedestrian is conveniently guided by staff.
As a preferred embodiment, in step S3, the following steps are specifically included:
step S301: dividing images in the human body detection image, images in the human face attribute detection image and images in the pedestrian attribute detection image into a training set and a testing set according to a certain proportion; dividing the image into a training set to train the pedestrian state detection model, and testing the detection effect of the pedestrian state detection model by a testing set.
Step S302: sequentially inputting the training set of the human body detection image, the training set of the human face attribute detection image and the training set of the pedestrian attribute detection image into the pedestrian state detection model to optimize the weight parameters of the pedestrian state detection model;
the training set in the human body detection image, the training set in the human face attribute detection image and the training set in the pedestrian attribute detection image are sequentially input into a pedestrian state detection model, and the pedestrian state detection model adjusts weight parameters of the human body detection image and the pedestrian state detection model according to the three training sets.
Step S303: and inputting the test set into the pedestrian state detection model to obtain the optimal weight parameters of the pedestrian state detection model.
The method comprises the steps of inputting a test set in a human body detection image, a test set in a human face attribute detection image and a test set in a pedestrian attribute detection image into a trained pedestrian state detection model, and further adjusting parameters of the pedestrian state detection model by the pedestrian state detection model to find out optimal weight parameters of the pedestrian state detection model.
As a preferred embodiment, in step S301, the human body detection image is taken as a positive sample of the human body detection training set, the image without the pedestrian in the existing image is taken as a negative sample of the human body detection training set, the number of the negative samples is three times that of the positive sample, the number of the human face attribute detection training set includes all the categories of the attribute of the human face attribute detection image and the number of each category is equal, and the number of the pedestrian attribute training set includes all the categories of the attribute of the pedestrian attribute detection image and the number of each category is equal.
As a preferred embodiment, the face attribute detection training set of the face attribute detection image is classified as an attribute of each face attribute detection image, and the pedestrian attribute training set of the pedestrian attribute detection image is classified as an attribute of each pedestrian.
As a preferred embodiment, the pedestrian state detection model is formed by a convolutional neural network, the pedestrian state detection model comprises a human body detection model, a human face attribute detection model and a pedestrian attribute detection model, the human face attribute detection model and the pedestrian attribute detection model are formed by the convolutional neural network, at least one deconvolution layer and at least one acceptance layer are arranged between the first layer of the convolutional neural network and the last layer of the convolutional neural network, and a plurality of convolution kernels with different sizes are adopted when the acceptance carries out convolution; the human body detection model adopts a faceboxes algorithm.
The face attribute detection model and the convolutional neural network in the pedestrian attribute detection model are provided with at least one deconvolution layer and at least one index layer between the first layer of the convolutional neural network and the last layer of the convolutional neural network, the convolutional neural network can be better adapted to the change of the size of an input image through the index layer, meanwhile, the diversity of the characteristic images is increased, the characteristic images are fused in a multi-scale mode, the operation amount is reduced, the size of the characteristic images can be restored through the deconvolution layer, the characteristic images are subjected to complementary expansion, the characteristics of higher level can be learned, the model parameters of the network can be reduced, the pedestrian state detection model can be adapted to the change of the size of the input image, and the convolutional layer learns the problem of richer characteristics.
After the real-time pedestrian image is input to the pedestrian state detection model, the human body detection model firstly detects the real-time pedestrian image, the number of pedestrians in the image is detected, then the shared characteristic sub-networks (such as a convolution layer, a deconvolution layer and an acceptance layer) in the convolutional neural network in the human face attribute detection model and the pedestrian attribute detection model can extract attribute characteristics of the real-time pedestrian image, for example, a full-link layer can extract attribute of the real-time pedestrian image, and an output layer calculates attribute of the human face attribute detection image and attribute of the pedestrian attribute detection image of the pedestrian image to be real-time through the characteristic of the shared attribute to obtain identification results of comprehensive states of all pedestrians in the real-time pedestrian image.
Example 2
The embodiment 2 of the present application provides a face attribute recognition device, for convenience of explanation, only the part related to the present application is shown, as shown in fig. 2, a pedestrian status detection device includes a pedestrian image acquisition module 401, an image preprocessing module 402, and a pedestrian status detection model module 403;
the pedestrian image acquisition module 401 is configured to acquire an image of a pedestrian;
the image preprocessing module 402 is used for preprocessing an image of a pedestrian;
the pedestrian state detection model module 403 is configured to establish a pedestrian state detection model and output a result of pedestrian state detection.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein again.
Example 3
As shown in fig. 3, a pedestrian status detection device 50 includes a processor 500 and a memory 501;
the memory 501 is used for storing the program code 502 and transmitting the program code 502 to the processor;
the processor 500 is configured to perform the steps of one of the pedestrian status detection method embodiments described above, such as steps S1 through S5 shown in fig. 1, according to instructions in the program code 502. Alternatively, the processor 500 may perform the functions of the modules/units of the apparatus embodiments described above, such as the functions of the modules 401 to 403 shown in fig. 2, when executing the computer program 502.
Illustratively, the computer program 502 may be partitioned into one or more modules/units that are stored in the memory 501 and executed by the processor 500 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program 502 in the terminal device 50. For example, the computer program 502 may be segmented to include a pedestrian image acquisition module, an image preprocessing module, and a pedestrian state detection model module;
the pedestrian image acquisition module is used for acquiring images of pedestrians;
the image preprocessing module is used for preprocessing images of pedestrians;
the pedestrian state detection model module is used for establishing a pedestrian state detection model and outputting a pedestrian state detection result.
The terminal device 50 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The terminal device may include, but is not limited to, a processor 500, a memory 501. It will be appreciated by those skilled in the art that fig. 3 is merely an example of the terminal device 50 and is not limiting of the terminal device 50, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The processor 500 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 501 may be an internal storage unit of the terminal device 50, for example, a hard disk or a memory of the terminal device 50. The memory 501 may also be an external storage device of the terminal device 50, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device 50. Further, the memory 501 may also include both an internal storage unit and an external storage device of the terminal device 50. The memory 501 is used for storing the computer program and other programs and data required by the terminal device. The memory 501 may also be used to temporarily store data that has been output or is to be output.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A pedestrian state detection method characterized by comprising the steps of:
step S1: acquiring an existing pedestrian image;
step S2: establishing a pedestrian state detection model, and processing the existing pedestrian image by using the pedestrian state detection model;
the step S2 specifically comprises the following steps:
step S201: inputting the pedestrian image into a pedestrian state detection model, and detecting a human body in the pedestrian image by the pedestrian state detection model to obtain a human body detection image;
step S202: normalizing the human body detection image by the pedestrian state detection model to obtain a pedestrian attribute detection image;
step S203: the pedestrian state detection model performs face detection on the human body detection image and aligns the human body detection image to obtain a human face attribute detection image; respectively carrying out attribute labeling on the human body detection image, the human face attribute detection image and the pedestrian attribute detection image; the attribute of the human body detection image is the number of pedestrians; the attribute categories of the face attribute detection image include: gender, age, expression, face pose, and face wear; the attribute category of the pedestrian attribute detection image includes: backpack, bag, satchel, trunk, carrying child, wheelchair, and stroller;
step S3: inputting the processed pedestrian image into a pedestrian state detection model for training to obtain a trained pedestrian state detection model;
in step S3, the method specifically includes the following steps:
step S301: dividing the human body detection image, the human face attribute detection image and the pedestrian attribute detection image into a training set and a testing set according to a certain proportion;
step S302: sequentially inputting the training set of the human body detection image, the training set of the human face attribute detection image and the training set of the pedestrian attribute detection image into the pedestrian state detection model to optimize the weight parameters of the pedestrian state detection model;
step S303: inputting the test set into the trained pedestrian state detection model to obtain the optimal weight parameters of the pedestrian state detection model;
step S4: inputting the real-time pedestrian image into a trained pedestrian state detection model, and outputting a judgment result of the pedestrian state by the pedestrian state detection model for guiding the pedestrian passing through the security inspection channel by security inspection personnel;
the pedestrian state detection model comprises a human body detection model, a human face attribute detection model and a pedestrian attribute detection model, wherein the human face attribute detection model and the pedestrian attribute detection model are composed of a convolutional neural network, and at least one deconvolution layer and at least one index layer are arranged between a first layer of the convolutional neural network and a last layer of the convolutional neural network;
the full-connection layer extracts the attribute of the real-time pedestrian image, and the output layer calculates the attribute of the face attribute detection image and the attribute of the pedestrian attribute detection image of the real-time pedestrian image through the characteristic of the shared attribute to obtain the recognition result of the comprehensive state of each pedestrian in the real-time pedestrian image.
2. The pedestrian state detection method according to claim 1, wherein the attribute of each face attribute detection image is classified in a face attribute detection training set of the face attribute detection images, and the attribute of each pedestrian attribute detection image is classified in a pedestrian attribute training set of the pedestrian attribute detection images.
3. The pedestrian state detection method according to claim 2, wherein in step S301, the human body detection image is used as a positive sample of a human body detection training set, the image containing no pedestrian in the existing image is used as a negative sample of the human body detection training set, the human face attribute detection training set contains all the categories of the attributes of the human face attribute detection image and the number of each category is equal, and the pedestrian attribute training set contains all the categories of the attributes of the pedestrian attribute detection image and the number of each category is equal.
4. The pedestrian state detection method of claim 1 wherein the convolution layer convolves with a plurality of convolution kernels of different sizes; the human body detection model adopts a faceboxes algorithm.
5. The pedestrian state detection device is characterized by comprising a pedestrian image acquisition module, an image preprocessing module and a pedestrian state detection model module;
the pedestrian image acquisition module is used for acquiring images of pedestrians;
the image preprocessing module is used for preprocessing images of pedestrians, and specifically comprises the following steps:
inputting the pedestrian image into a pedestrian state detection model, and detecting a human body in the pedestrian image by the pedestrian state detection model to obtain a human body detection image;
normalizing the human body detection image by the pedestrian state detection model to obtain a pedestrian attribute detection image;
the pedestrian state detection model performs face detection on the human body detection image and aligns the human body detection image to obtain a human face attribute detection image; respectively carrying out attribute labeling on the human body detection image, the human face attribute detection image and the pedestrian attribute detection image; the attribute of the human body detection image is the number of pedestrians; the attribute categories of the face attribute detection image include: gender, age, expression, face pose, and face wear; the attribute category of the pedestrian attribute detection image includes: backpack, bag, satchel, trunk, carrying child, wheelchair, and stroller;
the pedestrian state detection model module is used for establishing a pedestrian state detection model and outputting a pedestrian state detection result, and is used for guiding pedestrians passing through a security inspection channel by security inspection personnel, and specifically comprises the following steps of;
dividing the human body detection image, the human face attribute detection image and the pedestrian attribute detection image into a training set and a testing set according to a certain proportion;
sequentially inputting the training set of the human body detection image, the training set of the human face attribute detection image and the training set of the pedestrian attribute detection image into the pedestrian state detection model to optimize the weight parameters of the pedestrian state detection model;
inputting the test set into the trained pedestrian state detection model to obtain the optimal weight parameters of the pedestrian state detection model;
inputting the real-time pedestrian image into a trained pedestrian state detection model, and outputting a judgment result of the pedestrian state by the pedestrian state detection model for guiding the pedestrian passing through the security inspection channel by security inspection personnel;
the pedestrian state detection model comprises a human body detection model, a human face attribute detection model and a pedestrian attribute detection model, wherein the human face attribute detection model and the pedestrian attribute detection model are composed of a convolutional neural network, and at least one deconvolution layer and at least one index layer are arranged between a first layer of the convolutional neural network and a last layer of the convolutional neural network;
the full-connection layer is used for extracting the attribute of the real-time pedestrian image, and the output layer is used for calculating the attribute of the face attribute detection image of the real-time pedestrian image and the attribute of the pedestrian attribute detection image through the characteristic of the shared attribute to obtain the recognition result of the comprehensive state of each pedestrian in the real-time pedestrian image.
6. A pedestrian state detection apparatus, characterized in that the apparatus comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute a pedestrian status detection method according to any one of claims 1-4 in accordance with instructions in the program code.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010054088.0A CN111291632B (en) | 2020-01-17 | 2020-01-17 | Pedestrian state detection method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010054088.0A CN111291632B (en) | 2020-01-17 | 2020-01-17 | Pedestrian state detection method, device and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111291632A CN111291632A (en) | 2020-06-16 |
CN111291632B true CN111291632B (en) | 2023-07-11 |
Family
ID=71023422
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010054088.0A Active CN111291632B (en) | 2020-01-17 | 2020-01-17 | Pedestrian state detection method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111291632B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116188919B (en) * | 2023-04-25 | 2023-07-14 | 之江实验室 | Test method and device, readable storage medium and electronic equipment |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516512B (en) * | 2018-05-21 | 2023-08-25 | 北京中科奥森数据科技有限公司 | Training method of pedestrian attribute analysis model, pedestrian attribute identification method and device |
CN109961009B (en) * | 2019-02-15 | 2023-10-31 | 平安科技(深圳)有限公司 | Pedestrian detection method, system, device and storage medium based on deep learning |
CN110110611A (en) * | 2019-04-16 | 2019-08-09 | 深圳壹账通智能科技有限公司 | Portrait attribute model construction method, device, computer equipment and storage medium |
CN110110693A (en) * | 2019-05-17 | 2019-08-09 | 北京字节跳动网络技术有限公司 | The method and apparatus of face character for identification |
CN110222625A (en) * | 2019-06-03 | 2019-09-10 | 上海眼控科技股份有限公司 | A kind of method and system that the identifying rows in video monitoring image are humanized |
-
2020
- 2020-01-17 CN CN202010054088.0A patent/CN111291632B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111291632A (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Singh et al. | Image classification: a survey | |
US10936919B2 (en) | Method and apparatus for detecting human face | |
CN110378235B (en) | Fuzzy face image recognition method and device and terminal equipment | |
CN111008640B (en) | Image recognition model training and image recognition method, device, terminal and medium | |
Ali et al. | Boosted NNE collections for multicultural facial expression recognition | |
CN113159147B (en) | Image recognition method and device based on neural network and electronic equipment | |
CN110659723B (en) | Data processing method and device based on artificial intelligence, medium and electronic equipment | |
CN111860588A (en) | Training method for graph neural network and related equipment | |
CN110222718B (en) | Image processing method and device | |
CN111954250B (en) | Lightweight Wi-Fi behavior sensing method and system | |
CN115937655B (en) | Multi-order feature interaction target detection model, construction method, device and application thereof | |
WO2022012668A1 (en) | Training set processing method and apparatus | |
CN113822209A (en) | Hyperspectral image recognition method and device, electronic equipment and readable storage medium | |
CN111860056B (en) | Blink-based living body detection method, blink-based living body detection device, readable storage medium and blink-based living body detection equipment | |
Chen et al. | Image classification based on convolutional denoising sparse autoencoder | |
CN111291632B (en) | Pedestrian state detection method, device and equipment | |
Viedma et al. | Relevant features for gender classification in NIR periocular images | |
Sabater et al. | Event Transformer+. A multi-purpose solution for efficient event data processing | |
CN112766176A (en) | Training method of lightweight convolutional neural network and face attribute recognition method | |
Sridhar et al. | An Enhanced Haar Cascade Face Detection Schema for Gender Recognition | |
CN111914772A (en) | Method for identifying age, and training method and device of age identification model | |
KR101961462B1 (en) | Object recognition method and the device thereof | |
Sang et al. | Image recognition based on multiscale pooling deep convolution neural networks | |
Sravanthi et al. | An efficient classifier using machine learning technique for individual action identification | |
CN114943695A (en) | Medical sequence image anomaly detection method, device, equipment and storage medium |
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 | ||
CB02 | Change of applicant information |
Address after: Room 1301, No.132, Fengqi Road, phase III, software park, Xiamen City, Fujian Province Applicant after: Xiamen Entropy Technology Co.,Ltd. Address before: 361000, Xiamen three software park, Fujian Province, 8 North Street, room 2001 Applicant before: XIAMEN ZKTECO INFORMATION TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |