CN113642412A - Method, device and equipment for detecting vehicles occupying bus lane - Google Patents
Method, device and equipment for detecting vehicles occupying bus lane Download PDFInfo
- Publication number
- CN113642412A CN113642412A CN202110804675.1A CN202110804675A CN113642412A CN 113642412 A CN113642412 A CN 113642412A CN 202110804675 A CN202110804675 A CN 202110804675A CN 113642412 A CN113642412 A CN 113642412A
- Authority
- CN
- China
- Prior art keywords
- image
- lane
- bus
- frame
- images
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 67
- 238000007781 pre-processing Methods 0.000 claims abstract description 34
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000003672 processing method Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The application provides a vehicle detection method for occupying a bus lane, which comprises the following steps: acquiring a lane video image and acquiring a plurality of frames of continuous images; carrying out image preprocessing on each frame of image in the multi-frame continuous images: zooming each frame of image, and normalizing and standardizing pixel values of pixel points of each frame of image; detecting whether the lane is a bus lane or not based on a yellow line detection and GPS (global positioning system) positioning method of the multi-frame continuous images; if the lane is a bus lane, detecting whether a non-bus target exists in the area of the bus lane or not according to the preprocessed multi-frame continuous images; and if the non-bus target exists, starting a snapshot device to snapshot the non-bus target. The application also provides a detection device and a detection device for occupying the bus lane.
Description
Technical Field
The application relates to the technical field of intelligent traffic, in particular to a method, a device and equipment for detecting vehicles occupying bus lanes.
Background
In order to facilitate the passage of citizens, special lanes for buses, namely BRT lanes, are planned in many cities. However, non-bus vehicles often occupy the bus lane on the road, which seriously affects the bus running efficiency, and can not allow the bus to arrive at the station within the estimated time, so that the travel time of citizens taking the bus is not planned and wasted by utilizing road traffic, and the traffic jam is easily caused by the fact that the non-bus vehicles occupy the bus lane.
In the monitoring management of traffic management departments on illegal vehicles occupying bus lanes, a manual on-site evidence obtaining method is adopted, or a fixed camera is adopted for auxiliary monitoring to assist law enforcement and evidence obtaining. Manual on-site evidence obtaining requires more traffic police to distribute nearby roads for on-site law enforcement, which greatly wastes labor cost; often can not take a candid photograph alone the target violating the regulations who occupies bus lane in utilizing fixed camera to assist in the prison, gather and collect the evidence image and include too much invalid target, reduce law enforcement efficiency easily. The existing electronic equipment monitoring mode of the fixed point is more suitable for monitoring intersections of complex road sections, and the monitoring effect on special lanes is common.
Disclosure of Invention
The application provides a method, a device and equipment for detecting vehicles occupying bus lanes, which can effectively detect the bus lanes and non-bus vehicles occupying the bus lanes, and snapshot the non-bus vehicles without excessive manual participation, and are beneficial to improving the law enforcement efficiency for violating regulations of the occupied bus lanes.
In a first aspect, the present application provides a method for detecting a vehicle occupying a bus lane, comprising:
acquiring a lane video image and acquiring a plurality of frames of continuous images;
carrying out image preprocessing on each frame of image in the multi-frame continuous images: zooming each frame of image, and normalizing and standardizing pixel values of pixel points of each frame of image;
detecting whether the lane is a bus lane or not based on a yellow line detection and GPS (global positioning system) positioning method of the multi-frame continuous images;
if the lane is a bus lane, detecting whether a non-bus target exists in the area of the bus lane or not according to the preprocessed multi-frame continuous images; and if the non-bus target exists, starting a snapshot device to snapshot the non-bus target.
In an application embodiment, the step of detecting whether the lane is a bus lane based on the yellow line detection and GPS positioning method of the multiple frames of continuous images includes: setting the multiple frames of continuous images as i frames of continuous images, setting a first preset value a, 1< a < i, and carrying out yellow line detection in the i frames of continuous images to judge whether the lane is a bus lane; if yellow lines are detected in the images above the frame a of the i-frame continuous images, the lane is judged to be a bus lane; and if not, detecting whether the bus lane exists in the lane video shooting range by using GPS positioning.
In an embodiment of the present application, the step of performing yellow line detection in the i-frame continuous images to determine whether the lane is a bus lane comprises:
acquiring a first frame image in the i frames of continuous images after preprocessing, recording the current frame image as a jth frame image, setting a bus lane confidence value and initializing a bus lane confidence value p as 0,
intercepting two left and right block images of the current jth frame image, and carrying out reduction operation on the two left and right block images of the current jth frame image;
respectively detecting whether yellow lines exist in the left and right block images of the current j frame image: if yellow lines exist in the left and right block images, updating the bus lane confidence value p, keeping the p equal to p +1, continuously acquiring the next frame image in the i frame continuous images, and updating the j value, wherein the j equal to j + 1; if not, directly and continuously acquiring the next frame image in the i frames of continuous images, and updating the value j, wherein j is j + 1;
judging whether j is less than or equal to i; if j is larger than i, judging whether p is larger than or equal to a first preset value a, and if p is larger than or equal to a, judging that the lane is a bus lane; if j is less than or equal to i, continuously intercepting the left and right block images of the current j frame image, reducing the left and right block images of the current j frame image, continuously and respectively detecting whether yellow lines exist in the left and right block images of the current j frame image, and updating the bus lane confidence value p and the j value according to the yellow line detection result.
In an embodiment of the application, the i-frame consecutive images are 10-frame consecutive images, and the first predetermined value a is 3.
In one embodiment of the application, the step of detecting non-bus objects in the area of the bus lane in the plurality of frames of continuous images after preprocessing comprises:
detecting all vehicle targets in each preprocessed frame image by using an SVM classifier, and intercepting all detected vehicle targets in an original image to obtain a vehicle subgraph;
zooming out each of the vehicle subgraphs;
and detecting non-bus vehicles by combining the license plate recognition result and the vehicle type recognition.
In one embodiment of the application, the step of detecting the non-bus vehicle by combining the license plate recognition result and the vehicle type recognition comprises the following steps:
performing horizontal edge detection and vertical edge detection on each reduced vehicle subgraph by using a Sobel operator, and locating a license plate area by a rectangular frame formed by connecting the horizontal edge and the vertical edge;
extracting color textures of the license plate region and analyzing the license plate background color of each vehicle sub-image;
carrying out vehicle style identification on each vehicle subgraph by using an Adaboost cascade classifier;
and identifying and judging non-bus vehicles by combining the license plate ground color result of each vehicle subgraph and the vehicle style.
In an embodiment of the application, the size of each frame of image in the lane video is 1920x1080, and in the image scaling of the image preprocessing, each frame of image is scaled to obtain a scaled image f1,f1Is 300x 300; for image f1To the left and right sidesCutting to obtain a left block image and a right block image which are both 300x128 in size; the left tile image is scaled and scaled to 56x56 and the right tile image is scaled and scaled to 56x 56.
The beneficial effects of the vehicle detection method for occupying the bus lane provided by the application are that: the method for detecting the bus lane effectively by using the yellow line detection and GPS positioning based on the multi-frame continuous images detects the non-bus vehicles occupying the bus lane in the bus lane area and captures the non-bus vehicles without excessive manual participation, and is beneficial to improving the law enforcement efficiency of violating the regulations of occupying the bus lane.
In a second aspect, the present application provides a detection device for occupying a bus lane, comprising:
the image acquisition unit is used for acquiring lane video images;
the image acquisition unit is used for receiving the data of the image acquisition unit to acquire multi-frame continuous images;
the image preprocessing unit is used for receiving the multi-frame continuous images acquired by the image acquisition unit and carrying out image preprocessing on the multi-frame continuous images, wherein the image preprocessing comprises the steps of scaling each frame of image and carrying out normalization and standardization processing on pixel values of pixel points of each frame of image;
the bus lane detection unit is used for receiving the processing result of the image preprocessing unit and detecting whether the lane is a bus lane or not based on the yellow line detection of the multi-frame continuous images and a GPS (global positioning system) positioning method;
the non-bus target detection unit is used for detecting whether a non-bus target exists in the area of the bus lane or not based on the result of the image preprocessing unit when the bus lane detection unit detects that the lane is the bus lane;
and the snapshot unit is used for snapshot of the non-bus target when the non-bus target detection unit detects the non-bus target.
The application provides a detection device who occupies bus lane's beneficial effect lies in: the detection equipment occupying the bus lane can effectively detect the bus lane, detect the non-bus target occupying the bus lane and snapshot the non-bus target, so that excessive manual participation is not needed, and the efficiency of violation enforcement on the bus lane is improved.
In a third aspect, the present application further provides a detection apparatus for occupying a bus lane, comprising a camera, an image chip, a GPS positioning device for positioning the bus lane, and a snapshot device, wherein,
the camera is used for collecting lane video images;
the image chip is used for receiving lane video images collected by the camera to acquire multi-frame continuous images, carrying out image preprocessing on the multi-frame continuous images and detecting whether the lane is a bus lane or not by combining a GPS positioning device; when the lane is detected to be a bus lane, the image chip is used for detecting whether a non-bus target exists in the area of the bus lane;
the snapshot device is used for snapshot of the non-bus target when the image chip detects the non-bus target in the area of the bus lane.
The application provides a check out test set who occupies bus lane's beneficial effect lies in: the vehicle detection equipment occupying the bus lane can effectively detect the bus lane, detect a non-bus target occupying the bus lane and snapshot the non-bus target, so that excessive manual participation is not needed, and the efficiency of violation enforcement on the occupied bus lane is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flow chart of a vehicle detection method for occupying a bus lane according to an embodiment of the present application.
FIG. 2 is a flowchart of a method for detecting the lane by using the yellow line detection and GPS positioning method of i frames of consecutive images according to the first embodiment of the present application;
FIG. 3 is a flowchart of a method for detecting non-bus targets in the area of the bus lane according to a first embodiment of the present application;
fig. 4 is a block diagram of a structure of a detection device occupying a bus lane according to a second embodiment of the present application.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.
It will be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like, as used herein, refer to an orientation or positional relationship indicated in the drawings that is solely for the purpose of facilitating the description and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be considered as limiting the present application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Example one
The test tube issuing and labeling mechanism provided by the embodiment of the application is described with reference to the accompanying drawings.
Referring to fig. 1, 2 and 3 together, the steps of the vehicle detection method for occupying a bus lane provided by the embodiment of the application include:
step S100: and collecting lane video images.
Step S200: acquiring a plurality of frames of continuous images.
Step S300: carrying out image preprocessing on each frame of image in the multi-frame continuous images: and zooming each frame of image, and normalizing and standardizing the pixel values of the pixel points of each frame of image.
Step S400: detecting whether the lane is a bus lane or not based on a yellow line detection and GPS (global positioning system) positioning method of the multi-frame continuous images; and if the lane is detected to be a bus lane, executing the step S500.
Step S500: if the lane is a bus lane, detecting whether a non-bus target exists in the area of the bus lane or not according to the preprocessed multi-frame continuous images; if a non-bus target exists, step S600 is executed.
Step S600: and starting a snapshot device to snapshot the non-bus target.
Under the normal condition, yellow lines are generally planned on two sides of a bus lane on a road, so that the purpose of detecting the bus lane can be achieved by detecting the yellow lines on the lane. Generally, a camera is disposed near a lane, and a lane video image is captured in front of a vehicle traveling direction.
In step S300, the normalization and normalization formulas of the image preprocessing are:
y ═ x- μ)/σ; wherein x is the normalized pixel value of any pixel point in each frame of image, mu is the mean value, sigma is the variance, and y is the normalized pixel value of any pixel point in the frame of image.
In the embodiment, the method for detecting the bus lane effectively by using the yellow line detection and GPS positioning based on the multi-frame continuous images is utilized to detect the non-bus vehicles occupying the bus lane in the bus lane area and snapshot the non-bus vehicles, so that excessive manual participation is not needed, and the efficiency of violation enforcement on the occupied bus lane is improved.
In step S400, the step of detecting whether the lane is a bus lane based on the yellow line detection and GPS positioning method of the multiple frames of continuous images includes: setting the multiple frames of continuous images as i frames of continuous images, setting a first preset value a, 1< a < i, and carrying out yellow line detection in the i frames of continuous images to judge whether the lane is a bus lane; if yellow lines are detected in the images above the frame a of the i-frame continuous images, the lane is judged to be a bus lane; and if not, detecting whether the bus lane exists in the lane video shooting range by using GPS positioning.
Referring to fig. 2, the step of performing yellow line detection in the i-frame continuous images to determine whether the lane is a bus lane includes steps S410 to S470, i.e., step S400 includes steps S410 to S470. The method specifically comprises the following steps:
step S410: acquiring a first frame image in the i frames of continuous images after preprocessing, recording the current frame image as a jth frame image, setting a bus lane confidence value and initializing a bus lane confidence value p as 0,
step S420: and intercepting two left and right block images of the current j frame image, and carrying out reduction operation on the two left and right block images of the current j frame image.
Step S430: respectively detecting whether yellow lines exist in the left and right block images of the current j frame image; if yellow lines exist in the left and right block images, executing step S440; otherwise, go to step S450.
Step S440: and updating the bus lane confidence value p, wherein p is p +1, and continuing to execute the step S450 after the step S440.
Step S450: continuously acquiring a next frame image in the i frames of continuous images, and updating a j value, wherein j is j + 1; after step S450, step S460 is performed.
Step S460: judging whether j is less than or equal to i; if j > i, go to step S470, if j ≦ i, go back to step S420.
Step S470: and judging whether p is greater than or equal to a first preset value a, and if p is greater than or equal to a, judging that the lane is a bus lane.
In the present embodiment, in step S100, the size of each frame image in the captured lane video image is 1920 × 1080, image scaling in the image preprocessing is performed, and each acquired frame image is scaled to obtain a scaled image f1,f1The size of the image is 300x300, and the yellow line target of the bus lane is small, so that the image is zoomed, and the yellow line target can be better obtained. In step S420, the step of capturing the left and right block images of the current jth frame image specifically includes: for image f1And (4) cutting the left side and the right side to obtain a left block image and a right block image with the sizes of 300x128, wherein the yellow lines of the bus lane are generally positioned on the left side and the right side, so that the image blocks on the left side and the right side are cut to facilitate the detection of lane yellow line targets. The left tile image is scaled and scaled to 56x56 and the right tile image is scaled and scaled to 56x 56.
In this embodiment, it is determined whether j is less than or equal to i; if j > i, go to step S470, if j ≦ i, go back to step S420, which can be understood as: judging whether j is less than or equal to i; if j is larger than i, judging whether p is larger than or equal to a first preset value a, and if p is larger than or equal to a, judging that the lane is a bus lane; if j is less than or equal to i, continuously intercepting the left and right block images of the current j frame image, reducing the left and right block images of the current j frame image, continuously and respectively detecting whether yellow lines exist in the left and right block images of the current j frame image, and updating the bus lane confidence value p and the j value according to the yellow line detection result.
With further reference to fig. 2, the step S400 further includes a step S480. Specifically, if p < a indicates that the bus lane is detected based on the yellow line detection performed in the i-frame continuous images, step S480 is executed: and judging whether the collected lane video area has a bus lane or not by using GPS positioning.
The yellow line of the bus lane may be pressed in the driving process of the vehicle driving on the lane, namely, the yellow line target is shielded by the vehicle target, so that the yellow line of the original bus lane is not reflected in the collected lane video, and at the moment, the yellow line of the bus lane cannot be effectively detected by simply adopting the yellow line detection based on the image, namely, whether the situation that the bus lane can be misjudged exists or not is judged by simply adopting the yellow line detection method based on the image. In the embodiment, the bus lane detection is carried out by combining the yellow line detection based on the multi-frame continuous images and the GPS positioning method, so that the bus lane can be effectively detected when the yellow line of the bus lane is shielded, the missing detection condition is favorably avoided, and the accuracy of the detection of the bus lane is favorably improved.
In this embodiment, a higher value of the first predetermined value a indicates a higher accuracy of a result of detecting a bus lane based on yellow line detection in the i-frame continuous image.
In one embodiment, the i-frame consecutive images are 10-frame consecutive images, the first predetermined value a is set to 3, and when p is greater than or equal to 3, it means that: the left and right yellow lines of the bus lane are detected in more than 3 frames of images in 10 frames of continuous images, namely: and detecting the bus lane by using a method for detecting yellow lines in the i-frame continuous images. In a further embodiment, the i-frame continuous image may be 10 or more continuous images, and the first predetermined value a may be set to a value of 3 or more. In other embodiments, the values of i and a may be set as appropriate.
Referring to fig. 3, the following steps S510 to S530 of detecting a non-bus object in the region of the bus lane, that is, the step S500 includes the following steps S510 to S530.
Step S510: and detecting all vehicle targets in each preprocessed frame image by using an SVM classifier, and intercepting all detected vehicle targets in the original image to obtain a vehicle subgraph.
Step S520: and narrowing each vehicle subgraph to better obtain the target in the vehicle subgraph, so as to facilitate subsequent detection of license plate recognition and vehicle type recognition.
Step S530: and detecting non-bus vehicles by combining the license plate recognition result and the vehicle type recognition.
In step S510, when an SVM classifier is used to detect a vehicle target, a large number of positive and negative samples are collected from an actual vehicle target and Harr feature extraction is performed on the positive and negative samples as features of SVM training, an SVM classifier is trained by using an SVM training algorithm, and then the trained SVM classifier is used to perform vehicle target recognition.
With further reference to fig. 3, the step S530 of detecting a non-bus vehicle by combining the license plate recognition result and the vehicle type recognition includes the following steps:
step S531: performing horizontal edge detection and vertical edge detection on each reduced vehicle subgraph by using a Sobel operator, and locating a license plate area by a rectangular frame formed by connecting the horizontal edge and the vertical edge;
step S532: extracting color textures of the license plate region and analyzing the license plate background color of each vehicle sub-image;
step S533: carrying out vehicle style identification on each vehicle subgraph by using an Adaboost cascade classifier;
step S534: and (4) identifying and judging non-bus vehicles by combining the license plate ground color result and the vehicle style of each vehicle subgraph, and judging non-bus targets by combining the results of the step (S532) and the step (S533).
It can be understood that the domestic bus type and the private bus type are different. Compared with a private car license plate, most of the bottom colors of the bus license plates are yellow bottom license plates or yellow-green bottom combined license plates, the yellow-green bottom combined license plates are new energy bus license plates, and non-bus targets can be effectively detected by utilizing license plate recognition analysis and vehicle type recognition.
In this embodiment, in step S533, extracting Haar features and sift features of each vehicle subgraph to form a training feature vector of an Adaboost cascade classifier, collecting positive and negative samples for a certain type of vehicle, training the Adaboost cascade classifier by using an Adaboost algorithm, and then performing vehicle type identification by using the trained Adaboost cascade classifier. Utilizing Haar and sift fusion features advantageously enhances the robustness of the algorithm.
In one embodiment, step S533 requires Adaboost cascade classifier training and Adaboost cascade classifier recognition for all models of vehicles.
In another embodiment, the license plate background color of each vehicle sub-image is analyzed by using the step S532, the vehicle sub-image can be preliminarily judged to be a bus for each vehicle sub-image of the license plates with the yellow background plate and the yellow-green background plate, and then the vehicle style identification is carried out on each vehicle sub-image by using the step S533, so that the vehicle target representing the bus style is identified by only aiming at the bus style identification; and when each vehicle subgraph is identified to be a bus target in the steps S532 and S533, judging that the vehicle subgraph represents the bus target, and indicating that other vehicle subgraphs in the bus lane area are non-bus targets. In the example, all vehicle styles do not need to be identified, the algorithm running time is saved, and the identification accuracy of identifying the non-bus targets is ensured through double identification of license plate ground color analysis and vehicle style identification.
Example two
Referring to fig. 4, an embodiment of the present application further provides a detection apparatus 10 for occupying a bus lane, which includes an image acquisition unit 1, an image acquisition unit 2, an image preprocessing unit 3, a bus lane detection unit 4, a non-bus target detection unit 5, and a snapshot unit 6.
Specifically, the image capturing unit 1 is used for capturing lane video images. The image acquiring unit 2 is used for receiving the data of the image acquiring unit 1 to acquire a plurality of frames of continuous images. The image preprocessing unit 3 is configured to receive the multiple frames of continuous images acquired by the image acquiring unit 2, and perform image preprocessing on the multiple frames of continuous images, where the image preprocessing includes scaling each frame of image and normalizing and standardizing pixel values of pixels of each frame of image. The bus lane detection unit 4 is configured to receive the processing result of the image preprocessing unit 3, and detect whether the lane is a bus lane based on the yellow line detection of the multiple frames of continuous images and a GPS positioning method. The non-bus target detection unit 5 is used for detecting whether a non-bus target exists in the region of the bus lane or not and detecting whether a non-bus target exists in the region of the bus lane or not based on the result of the image preprocessing unit 3 when the bus lane detection unit 4 detects that the lane is the bus lane. The snapshot unit 6 is used for taking a snapshot of the non-bus target when the non-bus target detection unit 5 detects the non-bus target.
The processing method of the image preprocessing unit 3 is the same as the processing method of the step S300 in the embodiment, the processing method of the bus lane detection unit 4 is the same as the processing method of the step S400 in the embodiment, and the processing method of the traffic target detection unit 5 is the same as the processing method of the step S500 in the embodiment.
In this embodiment, the detection device 10 occupying the bus lane can effectively detect the bus lane, detect the non-bus target occupying the bus lane, and snapshot the non-bus target, without excessive manual participation, and is beneficial to improving the law enforcement efficiency for violating the regulations of the occupied bus lane.
EXAMPLE III
The embodiment of the application further provides vehicle detection equipment occupying a bus lane, which comprises a camera, an image chip, a GPS positioning device and a snapshot device. The camera is used for acquiring lane video images;
the image chip is used for receiving lane video images collected by the camera to acquire multi-frame continuous images, carrying out image preprocessing on the multi-frame continuous images and detecting whether the lane is a bus lane or not by combining a GPS positioning device; and when the lane is detected to be a bus lane, the image chip is used for detecting whether a non-bus target exists in the area of the bus lane. The snapshot device is used for snapshot of the non-bus target when the image chip detects the non-bus target in the area of the bus lane.
In this embodiment, the camera is a high definition camera, and the capturing device is a bayonet camera. The image chip is a DPS processing chip. The image preprocessing process in the image chip is the same as the step S300 in the first embodiment, the method for detecting whether the lane is a bus lane in the image chip is the same as the step S400 in the first embodiment, and the method for detecting whether a non-bus target exists in the area of the bus lane in the image chip is the same as the step S500 in the first embodiment.
In this embodiment, the vehicle detection equipment occupying the bus lane can effectively detect the bus lane, detect the non-bus target occupying the bus lane, and snapshot the non-bus target, without excessive manual participation, and is favorable for improving the law enforcement efficiency of violating regulations on occupying the bus lane.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (9)
1. A vehicle detection method for occupying a bus lane is characterized by comprising the following steps:
acquiring a lane video image and acquiring a plurality of frames of continuous images;
carrying out image preprocessing on each frame of image in the multi-frame continuous images: zooming each frame of image, and normalizing and standardizing pixel values of pixel points of each frame of image;
detecting whether the lane is a bus lane or not based on a yellow line detection and GPS (global positioning system) positioning method of the multi-frame continuous images;
if the lane is a bus lane, detecting whether a non-bus target exists in the area of the bus lane or not according to the preprocessed multi-frame continuous images; and if the non-bus target exists, starting a snapshot device to snapshot the non-bus target.
2. The method for detecting vehicles occupying bus lanes according to claim 1, wherein the step of detecting whether the lane is a bus lane based on the yellow line detection of the plurality of frames of continuous images and the GPS positioning method comprises: setting the multi-frame continuous image as an i-frame continuous image, setting a first preset value a, wherein a is more than 1 and less than i, and performing yellow line detection in the i-frame continuous image to judge whether the lane is a bus lane; if yellow lines are detected in the images above the frame a of the i-frame continuous images, the lane is judged to be a bus lane; and if not, detecting whether the bus lane exists in the lane video shooting range by using GPS positioning.
3. The method as claimed in claim 2, wherein the step of performing yellow line detection in the i-frame continuous images to determine whether the lane is a bus lane comprises:
acquiring a first frame image in the i frames of continuous images after preprocessing, recording the current frame image as a jth frame image, setting a bus lane confidence value and initializing a bus lane confidence value p as 0,
intercepting two left and right block images of the current jth frame image, and carrying out reduction operation on the two left and right block images of the current jth frame image;
respectively detecting whether yellow lines exist in the left and right block images of the current j frame image: if yellow lines exist in the left and right block images, updating the bus lane confidence value p, keeping the p equal to p +1, continuously acquiring the next frame image in the i frame continuous images, and updating the j value, wherein the j equal to j + 1; if not, directly and continuously acquiring the next frame image in the i frames of continuous images, and updating the value j, wherein j is j + 1;
judging whether j is less than or equal to i; if j is larger than i, judging whether p is larger than or equal to a first preset value a, and if p is larger than or equal to a, judging that the lane is a bus lane; if j is less than or equal to i, continuously intercepting the left and right block images of the current j frame image, reducing the left and right block images of the current j frame image, continuously and respectively detecting whether yellow lines exist in the left and right block images of the current j frame image, and updating the bus lane confidence value p and the j value according to the yellow line detection result.
4. The method as claimed in claim 3, wherein said i-frame continuous images are 10-frame continuous images, and said first predetermined value a is 3.
5. The method of claim 1, wherein the step of detecting non-bus objects within the area of the bus lane in the plurality of frames of consecutive images after preprocessing comprises:
detecting all vehicle targets in each preprocessed frame image by using an SVM classifier, and intercepting all detected vehicle targets in an original image to obtain a vehicle subgraph;
zooming out each of the vehicle subgraphs;
and detecting non-bus vehicles by combining the license plate recognition result and the vehicle type recognition.
6. The method of claim 5, wherein the step of detecting non-bus vehicles by combining the plate recognition result and the vehicle type recognition comprises:
performing horizontal edge detection and vertical edge detection on each reduced vehicle subgraph by using a Sobel operator, and locating a license plate area by a rectangular frame formed by connecting the horizontal edge and the vertical edge;
extracting color textures of the license plate region and analyzing the license plate background color of each vehicle sub-image;
carrying out vehicle style identification on each vehicle subgraph by using an Adaboost cascade classifier;
and identifying and judging non-bus vehicles by combining the license plate ground color result of each vehicle subgraph and the vehicle style.
7. The method of claim 3, wherein the size of each frame of image in the lane video is 1920x1080, and in the image scaling of the image preprocessing, each frame of image is scaled to obtain a scaled image f1,f1Is 300x 300; for image f1Cutting the left side and the right side to obtain a left block image and a right block image which are both 300x128 in size; for the left divisionThe tile image is scaled and scaled to 56x56 and the right tile image is scaled and scaled to 56x 56.
8. The utility model provides an occupy detection device in public transit lane which characterized in that includes:
the image acquisition unit is used for acquiring lane video images;
the image acquisition unit is used for receiving the data of the image acquisition unit to acquire multi-frame continuous images;
the image preprocessing unit is used for receiving the multi-frame continuous images acquired by the image acquisition unit and carrying out image preprocessing on the multi-frame continuous images, wherein the image preprocessing comprises the steps of scaling each frame of image and carrying out normalization and standardization processing on pixel values of pixel points of each frame of image;
the bus lane detection unit is used for receiving the processing result of the image preprocessing unit and detecting whether the lane is a bus lane or not based on the yellow line detection of the multi-frame continuous images and a GPS (global positioning system) positioning method;
the non-bus target detection unit is used for detecting whether a non-bus target exists in the area of the bus lane or not based on the result of the image preprocessing unit when the bus lane detection unit detects that the lane is the bus lane;
and the snapshot unit is used for snapshot of the non-bus target when the non-bus target detection unit detects the non-bus target.
9. A detection device for occupying a bus lane is characterized by comprising a camera, an image chip, a GPS positioning device for positioning the bus lane and a snapshot device, wherein,
the camera is used for collecting lane video images;
the image chip is used for receiving lane video images collected by the camera to acquire multi-frame continuous images, carrying out image preprocessing on the multi-frame continuous images and detecting whether the lane is a bus lane or not by combining a GPS positioning device; when the lane is detected to be a bus lane, the image chip is used for detecting whether a non-bus target exists in the area of the bus lane;
the snapshot device is used for snapshot of the non-bus target when the image chip detects the non-bus target in the area of the bus lane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110804675.1A CN113642412B (en) | 2021-07-16 | 2021-07-16 | Method, device and equipment for detecting vehicle occupying bus lane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110804675.1A CN113642412B (en) | 2021-07-16 | 2021-07-16 | Method, device and equipment for detecting vehicle occupying bus lane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642412A true CN113642412A (en) | 2021-11-12 |
| CN113642412B CN113642412B (en) | 2023-12-26 |
Family
ID=78417554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110804675.1A Active CN113642412B (en) | 2021-07-16 | 2021-07-16 | Method, device and equipment for detecting vehicle occupying bus lane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642412B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030050725A (en) * | 2001-12-19 | 2003-06-25 | 현대자동차주식회사 | Management and observation method of bus exclusive line |
| KR20110132096A (en) * | 2010-06-01 | 2011-12-07 | 주식회사 디아이랩 | Control method and apparatus for exclusive road |
| CN103164958A (en) * | 2011-12-15 | 2013-06-19 | 无锡中星微电子有限公司 | Method and system for vehicle monitoring |
| CN103268471A (en) * | 2013-04-17 | 2013-08-28 | 深圳市锐明视讯技术有限公司 | Vehicle illegal land occupying detection method and device |
| CN104424801A (en) * | 2013-08-29 | 2015-03-18 | 杭州海康威视***技术有限公司 | System and method for snapping bus road occupation |
| CN105389561A (en) * | 2015-11-13 | 2016-03-09 | 深圳华中科技大学研究院 | Method for detecting bus lane based on video |
| CN106503640A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | A kind of detection method for taking bus zone |
| CN108021879A (en) * | 2017-11-30 | 2018-05-11 | 天津天地基业科技有限公司 | A kind of vehicular traffic kind identification method based on video image |
| CN108263387A (en) * | 2016-12-30 | 2018-07-10 | 意法半导体股份有限公司 | For generating the method for lane departure warning, related system in the car |
| WO2018209470A1 (en) * | 2017-05-15 | 2018-11-22 | 深圳市卓希科技有限公司 | License plate identification method and system |
| CN109726717A (en) * | 2019-01-02 | 2019-05-07 | 西南石油大学 | A kind of vehicle comprehensive information detection system |
| CN109948416A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal occupancy bus zone automatic auditing method based on deep learning |
| US20190236942A1 (en) * | 2018-01-29 | 2019-08-01 | Siemens Industry, Inc. | Bus lane prioritization |
| CN110659539A (en) * | 2018-06-28 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Information processing method and device |
| CN211062206U (en) * | 2020-02-13 | 2020-07-21 | 盛视科技股份有限公司 | Snapshot device for occupying bus lane |
| CN112633062A (en) * | 2020-11-18 | 2021-04-09 | 合肥湛达智能科技有限公司 | Deep learning bus lane occupation detection method based on embedded terminal |
| WO2021120776A1 (en) * | 2020-05-28 | 2021-06-24 | 平安科技（深圳）有限公司 | Real-time vehicle violation detection method, apparatus, device, and storage medium |
-
2021
- 2021-07-16 CN CN202110804675.1A patent/CN113642412B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030050725A (en) * | 2001-12-19 | 2003-06-25 | 현대자동차주식회사 | Management and observation method of bus exclusive line |
| KR20110132096A (en) * | 2010-06-01 | 2011-12-07 | 주식회사 디아이랩 | Control method and apparatus for exclusive road |
| CN103164958A (en) * | 2011-12-15 | 2013-06-19 | 无锡中星微电子有限公司 | Method and system for vehicle monitoring |
| CN103268471A (en) * | 2013-04-17 | 2013-08-28 | 深圳市锐明视讯技术有限公司 | Vehicle illegal land occupying detection method and device |
| CN104424801A (en) * | 2013-08-29 | 2015-03-18 | 杭州海康威视***技术有限公司 | System and method for snapping bus road occupation |
| CN105389561A (en) * | 2015-11-13 | 2016-03-09 | 深圳华中科技大学研究院 | Method for detecting bus lane based on video |
| CN106503640A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | A kind of detection method for taking bus zone |
| CN108263387A (en) * | 2016-12-30 | 2018-07-10 | 意法半导体股份有限公司 | For generating the method for lane departure warning, related system in the car |
| WO2018209470A1 (en) * | 2017-05-15 | 2018-11-22 | 深圳市卓希科技有限公司 | License plate identification method and system |
| CN108021879A (en) * | 2017-11-30 | 2018-05-11 | 天津天地基业科技有限公司 | A kind of vehicular traffic kind identification method based on video image |
| US20190236942A1 (en) * | 2018-01-29 | 2019-08-01 | Siemens Industry, Inc. | Bus lane prioritization |
| CN110659539A (en) * | 2018-06-28 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Information processing method and device |
| CN109948416A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal occupancy bus zone automatic auditing method based on deep learning |
| CN109726717A (en) * | 2019-01-02 | 2019-05-07 | 西南石油大学 | A kind of vehicle comprehensive information detection system |
| CN211062206U (en) * | 2020-02-13 | 2020-07-21 | 盛视科技股份有限公司 | Snapshot device for occupying bus lane |
| WO2021120776A1 (en) * | 2020-05-28 | 2021-06-24 | 平安科技（深圳）有限公司 | Real-time vehicle violation detection method, apparatus, device, and storage medium |
| CN112633062A (en) * | 2020-11-18 | 2021-04-09 | 合肥湛达智能科技有限公司 | Deep learning bus lane occupation detection method based on embedded terminal |
Non-Patent Citations (3)
| Title |
|---|
| 韩昆: "车载的占用公交车道电子警察***的研究与实现", 中国优秀硕士学位论文全文数据库, pages 3 * |
| 顾占冰;陶海涛;潘燕;张银霞;: "快速公交专用车道上非公交车辆抓拍***", 数据采集与处理, no. 06 * |
| 高上: "基于数字图像处理的公交车识别研究高", 中国优秀硕士学位论文全文数据库, pages 5 - 6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642412B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bibi et al. | Automatic parking space detection system | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| WO2019196130A1 (en) | Classifier training method and device for vehicle-mounted thermal imaging pedestrian detection | |
| CN103235938B (en) | The method and system of car plate detection and indentification | |
| CN109191830B (en) | Road congestion detection method based on video image processing | |
| WO2019196131A1 (en) | Method and apparatus for filtering regions of interest for vehicle-mounted thermal imaging pedestrian detection | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| Atkočiūnas et al. | Image processing in road traffic analysis | |
| WO2019223655A1 (en) | Detection of non-motor vehicle carrying passenger | |
| CN105825696A (en) | Driving assistance system based on signal lamp information prompts | |
| CN103544481A (en) | Road gate monitoring method and system based on human face recognition | |
| CN110838230B (en) | Mobile video monitoring method, monitoring center and system | |
| CN104616502A (en) | License plate identification and positioning system based on combined type vehicle-road video network | |
| CN104537360A (en) | Method and system for detecting vehicle violation of not giving way | |
| US20170243067A1 (en) | Side window detection through use of spatial probability maps | |
| CN105741559A (en) | Emergency vehicle lane illegal occupation detection method based on lane line model | |
| CN111783671A (en) | Intelligent city ground parking space image processing method based on artificial intelligence and CIM | |
| CN110070729A (en) | It is a kind of that vehicle detecting system and method are stopped based on the separated of mist calculating | |
| WO2018068312A1 (en) | Device and method for detecting abnormal traffic event | |
| CN110610153A (en) | Lane recognition method and system for automatic driving | |
| CN116434159A (en) | Traffic flow statistics method based on improved YOLO V7 and Deep-Sort | |
| CN112509325A (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN110399766A (en) | Smoking testing and analysis system based on deep learning | |
| CN117876232B (en) | Intelligent traffic accident insurance processing method and system based on large model | |
| CN106327876B (en) | A kind of fake-licensed car capture system and method based on automobile data recorder |
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 |