CN115272984A - Method, system, computer and readable storage medium for detecting lane occupation operation - Google Patents
Method, system, computer and readable storage medium for detecting lane occupation operation Download PDFInfo
- Publication number
- CN115272984A CN115272984A CN202211194975.3A CN202211194975A CN115272984A CN 115272984 A CN115272984 A CN 115272984A CN 202211194975 A CN202211194975 A CN 202211194975A CN 115272984 A CN115272984 A CN 115272984A
- Authority
- CN
- China
- Prior art keywords
- preset
- background image
- target
- actual background
- lane
- 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
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
-
- 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
- G06V20/44—Event 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method, a system, a computer and a readable storage medium for detecting lane occupation operation, wherein the method comprises the steps of marking off an illegal lane occupation operation detection area in a display picture of a monitoring video, and intercepting an actual background picture in the monitoring video at preset time intervals; when the moving target is detected, tracking the moving track of the moving target in real time, and judging whether the staying time of the moving target exceeds a preset first threshold value or not; if yes, storing the actual background picture at the current moment, and matching a corresponding target occupying path operation picture in a preset dynamic feedback library; calculating the similarity between the actual background image at the current moment and the target lane occupying management image, and judging whether the similarity is greater than a preset second threshold value or not; if yes, judging that the road occupation operation phenomenon exists in the current street, and generating corresponding alarm information. The detection device can be suitable for detection of different articles in the mode, is high in universality and is suitable for popularization and use in a large range.
Description
Technical Field
The invention relates to the technical field of visual analysis, in particular to a method, a system, a computer and a readable storage medium for detecting the occupied road operation.
Background
The street-facing store road occupation management refers to the behavior that an operator occupies a street-facing urban road to buy and sell goods or services in a profitability manner. The behavior affects urban traffic safety and causes urban environment pollution, thereby bringing inconvenience to the traveling and daily life of surrounding citizens.
At present, two modes are mainly adopted for supervision and identification of the road occupation operation behavior, one mode is a manual patrol mode, at least 3-5 workers are invested in each street in the jurisdiction every day to carry out the road occupation operation condition to carry out patrol work, however, the management mode of staring at and patrolling by manpower is low in efficiency, low in quality and extremely easy to repeat the regulation effect. The other method is to identify the objects on the road through an AI intelligent identification technology to judge whether the road occupation operation phenomenon exists according to the identified objects, however, the identification method has the problems of high misjudgment rate and non-universality, can only be applied to specific scenes, and has certain use limitation.
Therefore, in order to overcome the defects of the prior art, it is necessary to provide a lane occupation operation detection method with high universality and low misjudgment rate.
Disclosure of Invention
Based on this, the invention aims to provide a method, a system, a computer and a readable storage medium for detecting the lane occupation operation, so as to provide the lane occupation operation detection method with high universality and low misjudgment rate.
The first aspect of the embodiments of the present invention provides a method for detecting a busy operation, where the method includes:
when a monitoring video shot by a camera in a current street is acquired, marking out an illegal road occupation operation detection area in a display picture of the monitoring video, and intercepting an actual background image in the monitoring video at intervals of preset time so as to compare the actual background image with a preset standard background image;
when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, tracking the moving track of the moving target in real time, and judging whether the staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value or not;
if the residence time of the moving target in the illegal lane occupying operation detection area exceeds the preset first threshold value, storing the actual background image at the current moment, and matching a target lane occupying operation image corresponding to the actual background image at the current moment in a preset dynamic feedback library;
calculating the similarity between the actual background image at the current moment and the target lane occupying management image, and judging whether the similarity is greater than a preset second threshold value or not;
and if the similarity is judged to be larger than the preset second threshold value, judging that the road occupation operation phenomenon exists in the current street, and generating corresponding alarm information.
The beneficial effects of the invention are: marking out an illegal road occupation operation detection area in a display picture in the obtained monitoring video, and intercepting an actual background image in the monitoring video at intervals of preset time so as to compare the actual background image with a preset standard background image; further, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, the moving track of the moving target is tracked in real time, and whether the staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value is judged; specifically, if yes, the actual background image at the current moment is saved, and a target lane occupying management picture corresponding to the actual background image at the current moment is matched in a preset dynamic feedback library; on the basis, calculating the similarity between the actual background image at the current moment and the target lane occupying management image, and judging whether the similarity is greater than a preset second threshold value or not; and if the current similarity is judged to be larger than the preset second threshold value, judging that the current street occupies the street and is operated, and generating corresponding alarm information. Whether the road occupation operation phenomenon exists in the current street can be automatically judged according to the monitoring video acquired in real time in the mode, so that manual inspection operation is omitted, the judgment accuracy can be continuously improved along with continuous perfection of pictures in a dynamic feedback library, meanwhile, the method can be suitable for detection of different objects, the universality is high, and the method is suitable for popularization and use on a large scale.
Preferably, the step of intercepting an actual background map in the surveillance video at preset intervals includes:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of the illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
Preferably, the step of calculating the similarity between the actual background image at the current time and the target lane operation picture includes:
respectively acquiring a first characteristic point corresponding to the actual background image at the current moment and a second characteristic point corresponding to the target road occupation management image, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating a Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement;
and if the Hamming distance meets the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the Hamming distance.
Preferably, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background map, the step of tracking the moving track of the moving target in real time includes:
and when a moving target appears in the illegal lane occupation operation detection area, calling a Kalman filtering algorithm matched with the moving target, and tracking the moving target in real time through the Kalman filtering algorithm to obtain the moving track of the moving target.
Preferably, after the step of marking out the illegal road occupation operation detection area in the display picture of the monitoring video when the monitoring video shot by the camera in the current street is obtained, the method further comprises:
and when the monitoring video is acquired, sequentially carrying out image denoising, image contrast enhancement and filtering optimization processing on the monitoring video.
A second aspect of the embodiments of the present invention provides a system for detecting a lane occupation operation, where the system includes:
the system comprises an acquisition module, a comparison module and a comparison module, wherein the acquisition module is used for dividing an illegal road occupation operation detection area in a display picture of a monitoring video when the monitoring video shot by a camera in the current street is acquired, and intercepting an actual background image in the monitoring video at preset time intervals so as to compare the actual background image with a preset standard background image;
the first judgment module is used for tracking the moving track of the moving target in real time when the moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, and judging whether the retention time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value or not;
the matching module is used for storing the actual background image at the current moment and matching a target lane occupation operation picture corresponding to the actual background image at the current moment in a preset dynamic feedback library if the fact that the staying time of the moving target in the illegal lane occupation operation detection area exceeds the preset first threshold is judged;
the second judgment module is used for calculating the similarity between the actual background image at the current moment and the target lane occupying management image and judging whether the similarity is greater than a preset second threshold value or not;
and the processing module is used for judging that the street occupying operation phenomenon exists in the current street and generating corresponding alarm information if the similarity is judged to be greater than the preset second threshold value.
In the above system, the acquiring module is specifically configured to:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of the illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
In the above system, the second determining module is specifically configured to:
respectively acquiring a first characteristic point corresponding to the actual background picture at the current moment and a second characteristic point corresponding to the target road-occupying operation picture, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating a Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement;
and if the Hamming distance meets the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the Hamming distance.
In the above system, the first determining module is specifically configured to:
and when a moving target appears in the illegal lane occupation operation detection area, calling a Kalman filtering algorithm matched with the moving target, and tracking the moving target in real time through the Kalman filtering algorithm to obtain the moving track of the moving target.
Among the above-mentioned detection system is operated in the occupation of road, detection system is operated in the occupation of road still includes optimization module, optimization module specifically is used for:
and when the monitoring video is acquired, sequentially carrying out image denoising, image contrast enhancement and filtering optimization processing on the monitoring video.
A third aspect of an embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the lane occupation management detection method as described above.
A fourth aspect of the embodiments of the present invention provides a readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the lane occupancy detection method as described above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a lane occupancy detection method according to a first embodiment of the present invention;
fig. 2 is a block diagram of a lane occupancy detection system according to a second embodiment of the present invention.
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are presented in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for purposes of illustration only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
At present, two modes are mainly adopted for supervision and identification of the road occupation operation behavior, one mode is a manual patrol mode, at least 3-5 workers are invested in each street in the jurisdiction every day to carry out the road occupation operation condition to carry out patrol work, however, the management mode of staring at and patrolling by manpower is low in efficiency, low in quality and extremely easy to repeat the regulation effect. The other method is to identify the objects on the road through an AI intelligent identification technology to judge whether the road occupation operation phenomenon exists according to the identified objects, however, the identification method has the problems of high misjudgment rate and non-universality, can only be applied to specific scenes, and has certain use limitation.
Referring to fig. 1, a lane occupation operation detection method according to a first embodiment of the present invention is shown, and the lane occupation operation detection method according to this embodiment can automatically determine whether a lane occupation operation phenomenon exists in a current street according to a real-time acquired monitoring video, so as to omit a manual inspection operation, and as the pictures in a dynamic feedback library are continuously improved, the accuracy of determination can be continuously improved, and meanwhile, the method is suitable for detection of different objects, has high universality, and is suitable for wide-range popularization and use.
Specifically, the method for detecting the lane occupation operation provided by the embodiment specifically includes the following steps:
step S10, when a monitoring video shot by a camera in a current street is obtained, marking off an illegal road occupation operation detection area in a display picture of the monitoring video, and intercepting an actual background image in the monitoring video at preset time intervals so as to compare the actual background image with a preset standard background image;
specifically, in this embodiment, it should be noted that the method for detecting the lane occupation operation provided in this embodiment is specifically applied to a commercial street, and is used to detect whether a phenomenon of the lane occupation operation exists in a shop in the current commercial street in real time, so as to save the labor cost.
In addition, in this embodiment, it should be further noted that the method for detecting the lane occupation management provided in this embodiment is implemented based on a detection server disposed in the background, and meanwhile, a plurality of algorithms are preset in the detection server, so that the detection efficiency can be effectively improved.
Therefore, in this step, it should be noted that, in order to accurately determine whether the street is occupied by the road operation, the detection server needs to acquire the monitoring video captured by the camera in the current street in real time, and at the same time, a detection area for illegal road occupation operation is divided in a display screen of the acquired monitoring video.
Further, in this step, it should be noted that when the shops in the street are not in the operating state, the doorway of each shop is a blank area, and at this time, a certain time picture of the current monitoring video is captured as the preset standard background picture, and correspondingly, when the shops in the street are in the operating state, an actual background picture is captured from the monitoring video every preset time by the detection server, and the captured actual background picture is compared with the preset standard background picture in real time, so as to determine in real time whether an object exists in the illegal lane occupying operation detection area of the captured actual background picture. Preferably, in this embodiment, an actual background image is taken every 10 minutes.
In this step, it should be noted that the step of intercepting an actual background map in the monitoring video at preset intervals includes:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of the illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
It should be noted that the Contourlet transform is a graphic processing algorithm, which can describe two-dimensional images well, and the algorithm not only has the time-frequency analysis characteristics of wavelet transform, but also has good anisotropy, and can express images more perfectly than the wavelet algorithm.
The Laplacian Pyramid (LP) decomposition in the Contourlet transform is a method for implementing multi-resolution analysis of an image, and the high-frequency component and the low-frequency component can be effectively obtained by decomposing the image through the laplacian pyramid decomposition.
Further, the obtained high frequency components are decomposed by wavelet transform to obtain corresponding estimation components.
On the basis, the Bayesian Shrink algorithm with minimized Bayesian risk in the wavelet algorithm is utilized to adaptively estimate the threshold value according to each component.
Illumination invariant extraction: and reconstructing the estimator and the estimated component to obtain a pre-estimated value of the illumination component, obtaining an illumination invariant, vectorizing the illumination invariant, and performing dimensionality reduction on the original image by adopting Principal Component Analysis (PCA) change to obtain a corresponding illumination invariant characteristic.
Principal Component Analysis (PCA) is a statistical feature extraction method that has been widely used in recent years in the field of image Analysis and pattern recognition. Specifically, in this embodiment, the PCA is used to perform the illumination invariant dimension reduction, so that on one hand, a feature vector with a reduced dimension can be obtained, and on the other hand, the illumination effect can be further eliminated. And finally, removing the interference object in the detection target according to the length-width ratio to generate the actual background image.
In this step, it is further noted that, after the step of dividing the illegal road occupation management detection area in the display screen of the surveillance video when the surveillance video shot by the camera in the current street is acquired, the method further includes:
and when the monitoring video is acquired, sequentially carrying out image denoising, image contrast enhancement and filtering optimization processing on the monitoring video.
Step S20, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, tracking the moving track of the moving target in real time, and judging whether the staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value or not;
specifically, in this step, it should be noted that, when the detection server detects that a moving target appears in the illegal lane occupancy detection area in the actual background map, the current detection server tracks the moving track of the moving target in real time, and simultaneously determines whether the staying time of the current moving target in the illegal lane occupancy detection area exceeds a preset first threshold, preferably, in this embodiment, determines whether the staying time of the current moving target in the illegal lane occupancy detection area exceeds 30 minutes.
In this step, it should be noted that, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background map, the step of tracking the moving track of the moving target in real time includes:
and when a moving target appears in the illegal lane occupation operation detection area, calling a Kalman filtering algorithm matched with the moving target, and tracking the moving target in real time through the Kalman filtering algorithm to obtain the moving track of the moving target.
Specifically, the present embodiment assumes that the true state in the kalman filter state space at time t can be transformed from the state at time (t-1), and the system state and the measured value can be represented by the following formulas:
wherein, the formula
Representing the transition of the state of the system from time (t-1) to time t, X t Representing the system state at time t, A representing the state transition matrix, and B representing the action on the control vector U t An input control matrix of t Is the noise introduced during the transformation process, and the random variable follows a gaussian distribution.
Formula (II)
Indicating the transition from the system state to the real state, Z t Representing the measured value of the real state at time t, H is a system measurement matrix, and the real state space is mapped into an observation space, V t Is observed noise that follows a gaussian distribution, each instant of the noise being relatively independent.
Step S30, if the residence time of the moving target in the illegal lane occupying management detection area is judged to exceed the preset first threshold, the actual background image at the current moment is stored, and a target lane occupying management image corresponding to the actual background image at the current moment is matched in a preset dynamic feedback library;
further, in this step, it should be noted that, if the detection server determines that the residence time of the moving target in the illegal lane operation detection area exceeds the preset first threshold, the actual background image at the current time is saved, and a target lane operation image corresponding to the actual background image at the current time is matched in a dynamic feedback library that is preset in the detection server, where it is noted that the target lane operation image indicates an image in which a lane operation phenomenon has occurred.
Step S40, calculating the similarity between the actual background image at the current moment and the target lane occupying management image, and judging whether the similarity is greater than a preset second threshold value or not;
specifically, in this step, it should be noted that, after the detection server matches the corresponding target occupying-road business picture through the above steps, the current detection server immediately calculates, through an ORB algorithm preset in the current detection server, a similarity between the actual background picture at the current time and the current target occupying-road business picture, and simultaneously determines whether the calculated similarity is greater than a preset second threshold.
In this step, it should be noted that the step of calculating the similarity between the actual background image at the current time and the target lane operation picture includes:
respectively acquiring a first characteristic point corresponding to the actual background image at the current moment and a second characteristic point corresponding to the target road occupation management image, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating a Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement;
and if the hamming distance is judged to meet the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the hamming distance.
It should be noted that the feature points of the image may be simply understood as relatively salient points in the image, such as contour points, bright points in darker areas, dark points in lighter areas, and the like.
Specifically, the detection server detects the feature point by using a FAST (features from accessed segment test) algorithm in the ORB algorithm. Firstly, candidate characteristic points are obtained, then a circle of pixel values around the candidate characteristic points are detected, and if the gray value difference between enough pixel points in the field around the candidate characteristic points and the candidate characteristic points is large enough, the candidate characteristic points are selected as one characteristic point.
After the feature point is determined, a descriptor corresponding to the feature point needs to be calculated, and a descriptor of a feature point is further calculated through a BRIEF algorithm in the ORB algorithm. The core idea of the BRIEF algorithm is to select N point pairs in a certain pattern around the key point P, and combine the comparison results of the N point pairs as the descriptor.
The method comprises the following specific steps:
(1) and D is taken as the radius to make a circle O by taking the key point P as the center of the circle.
(2) N point pairs are selected for a pattern within the circle O. Here, for convenience of explanation, N =4, and N may be 512 in practical application. Suppose that the currently selected 4 points are respectively marked as:
P 1 （C，D）、P 2 （C，D）、P 3 （C，D）、P 4 (C, D), wherein C and D respectively represent coordinate values of each point;
(3) defining operation T:
wherein T (P (C, D)) represents for each point pairComparison result, I C And I D All represent point values;
(4) and respectively carrying out T operation on the selected point pairs, and combining the obtained results.
Calculating the Hamming distance between descriptors of feature points of the two pictures, and returning two optimal matching points, wherein the shorter the Hamming distance is, the higher the similarity of surface detection points is;
specifically, when the hamming distance of the nearest neighbor matching point in the two best matching points is less than 0.75 times of the hamming distance of the next-neighbor matching point, the detecting point is considered as the same point, and the proportion of the same point in the detecting point is calculated, and the obtained result is the similarity of the two pictures.
And S50, if the similarity is judged to be larger than the preset second threshold value, judging that the road occupation operation phenomenon exists in the current street, and generating corresponding alarm information.
Finally, in this step, it should be noted that, if the detection server determines that the magnitude of the similarity calculated in real time is greater than the preset second threshold, it is immediately determined that the current street is occupied by the operation, and corresponding warning information is immediately generated, preferably, in this embodiment, the warning information may include a voice prompt, a text prompt, and the like, and in addition, the preset second threshold is set to 80%. Further, the current detection server transmits the alarm information generated in real time to a mobile terminal of a street maintenance worker, so that the street maintenance worker maintains the current street.
When the method is used, an illegal occupying-road operation detection area is marked out in a display picture in an obtained monitoring video, and an actual background image is captured in the monitoring video at preset time intervals so as to compare the actual background image with a preset standard background image; further, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, the moving track of the moving target is tracked in real time, and whether the staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value is judged; specifically, if yes, the actual background image at the current moment is saved, and a target account management picture corresponding to the actual background image at the current moment is matched in a preset dynamic feedback library; on the basis, calculating the similarity between the actual background image at the current moment and the target lane occupying management image, and judging whether the similarity is greater than a preset second threshold value or not; and if the current similarity is judged to be larger than the preset second threshold value, judging that the road occupation operation phenomenon exists in the current street, and generating corresponding alarm information. Whether the road occupation operation phenomenon exists in the current street can be automatically judged according to the monitoring video acquired in real time in the mode, so that manual inspection operation is omitted, the judgment accuracy can be continuously improved along with continuous perfection of pictures in a dynamic feedback library, meanwhile, the method can be suitable for detection of different objects, the universality is high, and the method is suitable for popularization and use on a large scale.
It should be noted that the above implementation process is only for illustrating the applicability of the present application, but this does not mean that the occupation management detection method of the present application is only the above one implementation process, and on the contrary, the occupation management detection method of the present application can be incorporated into the feasible embodiments of the present application as long as the occupation management detection method of the present application can be implemented.
In summary, the method for detecting the lane occupation operation according to the embodiment of the present invention can automatically determine whether a lane occupation operation phenomenon exists in a current street according to a real-time acquired monitoring video, so as to omit a manual inspection operation, and as the pictures in the dynamic feedback library are continuously improved, the accuracy of the determination can be continuously improved, and meanwhile, the method can be applied to detection of different articles, has high universality, and is suitable for wide popularization and use.
Referring to fig. 2, a system for detecting a lane occupation operation according to a second embodiment of the present invention is shown, and the system includes:
the acquisition module 12 is configured to, when a surveillance video shot by a camera in a current street is acquired, mark out an illegal road occupation operation detection area in a display picture of the surveillance video, and capture an actual background image in the surveillance video at intervals of a preset time, so as to compare the actual background image with a preset standard background image;
the first judging module 22 is configured to, when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background map, track a moving track of the moving target in real time, and judge whether a staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold;
the matching module 32 is configured to, if it is determined that the residence time of the moving target in the illegal lane operation detection area exceeds the preset first threshold, store the actual background image at the current moment, and match a target lane operation image corresponding to the actual background image at the current moment in a preset dynamic feedback library;
the second judging module 42 is configured to calculate a similarity between the actual background image at the current time and the target lane occupying management picture, and judge whether the similarity is greater than a preset second threshold;
and the processing module 52 is configured to, if it is determined that the similarity is greater than the preset second threshold, determine that a road occupation operation phenomenon exists in the current street, and generate corresponding warning information.
In the above system for detecting a lane occupation operation, the obtaining module 12 is specifically configured to:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of the illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
In the above system for detecting a lane operation, the second determining module 42 is specifically configured to:
respectively acquiring a first characteristic point corresponding to the actual background image at the current moment and a second characteristic point corresponding to the target road occupation management image, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating a Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement;
and if the Hamming distance meets the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the Hamming distance.
In the above system for detecting a lane operation, the first determining module 22 is specifically configured to:
and when a moving target appears in the illegal lane occupation operation detection area, calling a Kalman filtering algorithm matched with the moving target, and tracking the moving target in real time through the Kalman filtering algorithm to obtain the moving track of the moving target.
In the above detection system for track occupation operation, the detection system for track occupation operation further includes an optimization module 62, where the optimization module 62 is specifically configured to:
and when the monitoring video is acquired, sequentially carrying out image denoising, image contrast enhancement and filtering optimization processing on the monitoring video.
A third embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lane occupancy detection method provided in the first embodiment.
A fourth embodiment of the present invention provides a readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the lane occupancy detection method as provided in the first embodiment above.
In summary, the method, the system, the computer and the readable storage medium for detecting the lane occupation operation provided by the embodiments of the present invention can automatically determine whether the lane occupation operation phenomenon exists in the current street according to the real-time acquired monitoring video, thereby saving the manual inspection operation, continuously improving the accuracy of the determination along with the continuous perfection of the pictures in the dynamic feedback library, being suitable for the detection of different articles, having high universality, and being suitable for large-scale popularization and use.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules may be located in different processors in any combination.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for detecting a lane occupancy, the method comprising:
when a monitoring video shot by a camera in a current street is acquired, marking out an illegal road occupation operation detection area in a display picture of the monitoring video, and intercepting an actual background image in the monitoring video at intervals of preset time so as to compare the actual background image with a preset standard background image;
when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, tracking the moving track of the moving target in real time, and judging whether the staying time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value or not;
if the residence time of the moving target in the illegal lane occupation operation detection area is judged to exceed the preset first threshold, the actual background image at the current moment is stored, and a target lane occupation operation image corresponding to the actual background image at the current moment is matched in a preset dynamic feedback library;
calculating the similarity between the actual background image at the current moment and the target lane occupying management picture, and judging whether the similarity is greater than a preset second threshold value or not;
and if the similarity is judged to be larger than the preset second threshold value, judging that the road occupation operation phenomenon exists in the current street, and generating corresponding alarm information.
2. The duty management detection method according to claim 1, characterized in that: the step of intercepting an actual background image in the monitoring video at preset time intervals comprises the following steps:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of the illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
3. The duty management detection method according to claim 1, characterized in that: the step of calculating the similarity between the actual background image at the current moment and the target lane occupying management picture comprises the following steps:
respectively acquiring a first characteristic point corresponding to the actual background image at the current moment and a second characteristic point corresponding to the target road occupation management image, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating a Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement;
and if the Hamming distance meets the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the Hamming distance.
4. The duty management detection method according to claim 1, characterized in that: when a moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, the step of tracking the moving track of the moving target in real time comprises the following steps:
and when a moving target appears in the illegal lane occupation operation detection area, calling a Kalman filtering algorithm matched with the moving target, and tracking the moving target in real time through the Kalman filtering algorithm to obtain the moving track of the moving target.
5. The duty management detection method according to claim 1, characterized in that: after the step of dividing an illegal road occupation operation detection area in a display picture of the monitoring video when the monitoring video shot by the camera in the current street is obtained, the method further comprises the following steps:
and when the monitoring video is acquired, sequentially carrying out image denoising, image contrast enhancement and filtering optimization processing on the monitoring video.
6. A lane occupancy detection system, the system comprising:
the system comprises an acquisition module, a comparison module and a comparison module, wherein the acquisition module is used for dividing an illegal road occupation operation detection area in a display picture of a monitoring video when the monitoring video shot by a camera in the current street is acquired, and intercepting an actual background image in the monitoring video at preset time intervals so as to compare the actual background image with a preset standard background image;
the first judgment module is used for tracking the moving track of the moving target in real time when the moving target is detected to appear in the illegal lane occupation operation detection area in the actual background image, and judging whether the retention time of the moving target in the illegal lane occupation operation detection area exceeds a preset first threshold value or not;
the matching module is used for storing the actual background image at the current moment and matching a target lane occupation operation picture corresponding to the actual background image at the current moment in a preset dynamic feedback library if the fact that the staying time of the moving target in the illegal lane occupation operation detection area exceeds the preset first threshold is judged;
the second judgment module is used for calculating the similarity between the actual background image at the current moment and the target lane occupying management image and judging whether the similarity is greater than a preset second threshold value or not;
and the processing module is used for judging that the street occupying management phenomenon exists in the current street and generating corresponding alarm information if the similarity is judged to be greater than the preset second threshold value.
7. The lane occupancy detection system of claim 6, wherein: the acquisition module is specifically configured to:
carrying out decomposition processing on the display picture through Contoutlet transformation to obtain a high-frequency component and a low-frequency component;
performing Shearlet transform decomposition on the low-frequency component to obtain a corresponding estimation quantity, and performing decomposition processing on the high-frequency component through wavelet transform to obtain a corresponding estimation component;
constructing a pre-estimated value of an illumination component according to the estimated quantity and the estimated component based on an illumination invariant quantity extraction algorithm, and segmenting a detection target in the display picture according to the pre-estimated value and a background difference method;
and removing the interference objects in the detection target according to a preset length-width ratio to generate the actual background image.
8. The lane occupancy detection system of claim 6, wherein: the second judgment module is specifically configured to:
respectively acquiring a first characteristic point corresponding to the actual background image at the current moment and a second characteristic point corresponding to the target road occupation management image, and respectively calculating a first descriptor corresponding to the first characteristic point and a second descriptor corresponding to the second characteristic point;
calculating the Hamming distance between the first descriptor and the second descriptor, and judging whether the Hamming distance meets a preset requirement or not;
and if the hamming distance is judged to meet the preset requirement, calculating the similarity between the first characteristic point and the second characteristic point according to the hamming distance.
9. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the preemption detection method of any of claims 1-5.
10. A readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the preemption detection method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194975.3A CN115272984B (en) | 2022-09-29 | 2022-09-29 | Method, system, computer and readable storage medium for detecting lane occupation operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194975.3A CN115272984B (en) | 2022-09-29 | 2022-09-29 | Method, system, computer and readable storage medium for detecting lane occupation operation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272984A true CN115272984A (en) | 2022-11-01 |
| CN115272984B CN115272984B (en) | 2022-12-20 |
Family
ID=83757187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211194975.3A Active CN115272984B (en) | 2022-09-29 | 2022-09-29 | Method, system, computer and readable storage medium for detecting lane occupation operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272984B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106373426A (en) * | 2016-09-29 | 2017-02-01 | 成都通甲优博科技有限责任公司 | Computer vision-based parking space and illegal lane occupying parking monitoring method |
| CN109359563A (en) * | 2018-09-29 | 2019-02-19 | 江南大学 | A kind of road occupying phenomenon real-time detection method based on Digital Image Processing |
| CN110189355A (en) * | 2019-05-05 | 2019-08-30 | 暨南大学 | Safe escape channel occupies detection method, device, electronic equipment and storage medium |
| CN112102623A (en) * | 2020-08-24 | 2020-12-18 | 深圳云天励飞技术股份有限公司 | Traffic violation identification method and device and intelligent wearable device |
| CN112633179A (en) * | 2020-12-25 | 2021-04-09 | 杭州祐全科技发展有限公司 | Farmer market aisle object occupying channel detection method based on video analysis |
| CN113095301A (en) * | 2021-05-21 | 2021-07-09 | 南京甄视智能科技有限公司 | Road occupation operation monitoring method, system and server |
| CN113378659A (en) * | 2021-05-24 | 2021-09-10 | 上海可深信息科技有限公司 | Method for identifying busy operation |
| CN113887304A (en) * | 2021-09-01 | 2022-01-04 | 的卢技术有限公司 | Road occupation operation monitoring method based on target detection and pedestrian tracking |
| CN114463389A (en) * | 2022-04-14 | 2022-05-10 | 广州联客信息科技有限公司 | Moving target detection method and detection system |
| WO2022105243A1 (en) * | 2020-11-23 | 2022-05-27 | 北京旷视科技有限公司 | Event detection method, apparatus, electronic device, and storage medium |
| CN114648718A (en) * | 2022-03-28 | 2022-06-21 | 重庆紫光华山智安科技有限公司 | Road occupation detection method, system, electronic device and readable storage medium |
-
2022
- 2022-09-29 CN CN202211194975.3A patent/CN115272984B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106373426A (en) * | 2016-09-29 | 2017-02-01 | 成都通甲优博科技有限责任公司 | Computer vision-based parking space and illegal lane occupying parking monitoring method |
| CN109359563A (en) * | 2018-09-29 | 2019-02-19 | 江南大学 | A kind of road occupying phenomenon real-time detection method based on Digital Image Processing |
| CN110189355A (en) * | 2019-05-05 | 2019-08-30 | 暨南大学 | Safe escape channel occupies detection method, device, electronic equipment and storage medium |
| CN112102623A (en) * | 2020-08-24 | 2020-12-18 | 深圳云天励飞技术股份有限公司 | Traffic violation identification method and device and intelligent wearable device |
| WO2022105243A1 (en) * | 2020-11-23 | 2022-05-27 | 北京旷视科技有限公司 | Event detection method, apparatus, electronic device, and storage medium |
| CN112633179A (en) * | 2020-12-25 | 2021-04-09 | 杭州祐全科技发展有限公司 | Farmer market aisle object occupying channel detection method based on video analysis |
| CN113095301A (en) * | 2021-05-21 | 2021-07-09 | 南京甄视智能科技有限公司 | Road occupation operation monitoring method, system and server |
| CN113378659A (en) * | 2021-05-24 | 2021-09-10 | 上海可深信息科技有限公司 | Method for identifying busy operation |
| CN113887304A (en) * | 2021-09-01 | 2022-01-04 | 的卢技术有限公司 | Road occupation operation monitoring method based on target detection and pedestrian tracking |
| CN114648718A (en) * | 2022-03-28 | 2022-06-21 | 重庆紫光华山智安科技有限公司 | Road occupation detection method, system, electronic device and readable storage medium |
| CN114463389A (en) * | 2022-04-14 | 2022-05-10 | 广州联客信息科技有限公司 | Moving target detection method and detection system |
Non-Patent Citations (1)
| Title |
|---|
| 吴玉枝等: "基于卷积神经网络的违章停车事件检测", 《现代计算机(专业版)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272984B (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564814B (en) | Image-based parking lot parking space detection method and device | |
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| CN111563469A (en) | Method and device for identifying irregular parking behaviors | |
| CN114372983B (en) | Shielding box coating quality detection method and system based on image processing | |
| CN109635656A (en) | Vehicle attribute recognition methods, device, equipment and medium neural network based | |
| Bedruz et al. | Real-time vehicle detection and tracking using a mean-shift based blob analysis and tracking approach | |
| Kortli et al. | A novel illumination-invariant lane detection system | |
| Li et al. | Lane detection based on connection of various feature extraction methods | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| Bharadwaj Sundra Murthy et al. | Detection of potholes in autonomous vehicle | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN111079621B (en) | Method, device, electronic equipment and storage medium for detecting object | |
| Naufal et al. | Preprocessed mask RCNN for parking space detection in smart parking systems | |
| CN109063669B (en) | Bridge area ship navigation situation analysis method and device based on image recognition | |
| Zhang et al. | Counting vehicles in urban traffic scenes using foreground time‐spatial images | |
| CN109255792B (en) | Video image segmentation method and device, terminal equipment and storage medium | |
| CN104732510A (en) | Camera lens black spot detecting method and device | |
| FAN et al. | Robust lane detection and tracking based on machine vision | |
| Shi et al. | License plate localization in complex environments based on improved GrabCut algorithm | |
| Vargas et al. | A shadow removal algorithm for vehicle detection based on reflectance ratio and edge density | |
| CN115272984B (en) | Method, system, computer and readable storage medium for detecting lane occupation operation | |
| Wang et al. | A robust vehicle detection approach | |
| CN114022468B (en) | Method for detecting article left-over and lost in security monitoring | |
| CN113505860B (en) | Screening method and device for blind area detection training set, server and storage medium | |
| CN111027560B (en) | Text detection method and related device |
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 |