Method for discovering motor vehicles not passing alternately according to regulations
By using high-definition cameras and pixel-level segmentation algorithms to identify lanes and vehicles, calculate lane density, and dynamically number them, the system solves the problem of congestion and accidents caused by drivers' unfamiliarity with the rules for alternating traffic in sections with reduced lanes. It achieves high accuracy in automatically identifying illegal behavior and low-cost law enforcement support.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TRAFFIC MANAGEMENT RES INST OF THE MIN OF PUBLIC SECURITY
- Filing Date
- 2026-01-30
- Publication Date
- 2026-05-05
AI Technical Summary
Congestion and accidents frequently occur at road sections or intersections where lanes are reduced due to drivers' unfamiliarity with alternating traffic rules, and existing technologies are unable to automatically identify violations of alternating traffic rules.
By capturing images with high-definition cameras, using pixel-level segmentation algorithms to identify lanes and vehicles, calculating lane density, dynamically numbering vehicles, and determining whether vehicles comply with alternating traffic rules, the system can automatically identify illegal behavior.
It achieves high-accuracy automatic identification of non-compliant alternating traffic in merging sections without traffic lights, reducing deployment costs and improving the objectivity and accuracy of law enforcement evidence.
Smart Images
Figure CN121982903A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent traffic control technology, and more specifically, to a method for detecting motor vehicles that fail to take turns passing as required. Background Technology
[0002] Alternating traffic, also known as zipper traffic, refers to a traffic pattern where vehicles from both sides of a road lane take turns entering the merging lane in a "one right, one left" or "one main, one auxiliary" sequence at road sections or intersections where lanes are reduced, or at intersections without traffic signals and where vehicles are queuing or moving slowly. Its core logic is to balance the right-of-way between vehicles in different lanes by clearly defining the order of passage, avoiding the efficiency losses caused by disorderly competition. Article 45 of the "Road Traffic Safety Law of the People's Republic of China" stipulates that "at road sections or intersections where lanes are reduced, or at intersections without traffic lights, traffic signs, traffic markings, or traffic police direction, when encountering queuing or slow-moving traffic, motor vehicles shall alternate in sequence." Article 53 of the "Regulations for the Implementation of the Road Traffic Safety Law" further refines the requirements, specifying that "one vehicle per lane must alternate in sequence" at road sections where lanes are reduced. However, because intersections requiring zipper traffic are relatively few, drivers are less likely to encounter such scenarios and are unfamiliar with how to drive normally in these situations, leading to congestion, frequent accidents, and threats to driver safety and vehicle property. Summary of the Invention
[0003] The present invention aims to overcome the above-mentioned defects and provides a method for detecting motor vehicles that fail to take turns passing as required. This method can automatically identify the illegal behavior of "failure to take turns passing as required" and provide a reliable basis for traffic law enforcement.
[0004] As a first aspect of the present invention, a method for detecting motor vehicles failing to alternate passage as required is provided, comprising the following steps: Step S1: Acquire a captured image through a camera; wherein, the camera's capture range only covers the rightmost lane and merging lane of the main road and the corresponding merging lane entrance, and vehicles in the rightmost lane and merging lane enter the corresponding merging lane entrance. Step S2: Detect the vehicles in the rightmost lane and the vehicles merging into the lane from the captured image, and calculate the vehicle density in the rightmost lane and the vehicle density in the merging lane. Step S3: Based on the vehicle density of the rightmost lane and the vehicle density of the merging lane, determine whether both the rightmost lane and the merging lane are in a congested queuing state; if both lanes are in a congested queuing state, proceed to step S4; otherwise, return to step S3. Step S4: Sort the vehicles in the rightmost lane and the vehicles in the merging lane respectively, then obtain the vehicle entry order at the entrance of the merging lane from the captured image, and finally determine whether the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rules based on the vehicle entry order at the entrance of the merging lane.
[0005] Further, step S1 includes: A high-definition camera is installed at a suitable location upstream of the intersection. The tilt and horizontal angles of the high-definition camera are adjusted on-site, and the passage areas of the rightmost lane and merging lane of the main road are calibrated to ensure that the camera's capture range only covers the rightmost lane and merging lane of the main road and the corresponding merging lane entrance.
[0006] Furthermore, the detection of vehicles in the rightmost lane and vehicles merging into the lane from the captured image includes: A pixel-level segmentation algorithm is used to identify the rightmost road area in the captured image as the merging lane, and its left adjacent area as the rightmost lane of the main road. The pixel area of the merging lane and the pixel area of the rightmost lane of the main road are recorded. A pixel-level segmentation algorithm is used to detect each motor vehicle in the captured image, and the pixel area and centroid of each motor vehicle area are recorded. Then, the lane to which each motor vehicle belongs is determined based on the lane area into which the centroid of each motor vehicle area falls. Specifically, if the center of gravity of the motor vehicle area falls within the merging lane, the motor vehicle travels in the merging lane; if the center of gravity of the motor vehicle area falls within the rightmost lane of the main road, the motor vehicle travels in the rightmost lane of the main road.
[0007] Furthermore, the calculation of the vehicle density in the rightmost lane and the vehicle density in the merging lane includes: Calculate the sum of the pixel areas of all motor vehicle areas in the rightmost lane of the main road, and calculate the sum of the pixel areas of all motor vehicle areas in the merging lane; The sum of the pixel areas is divided by the pixel area of the corresponding lane to obtain the vehicle density of the corresponding lane.
[0008] Further, determining whether both the rightmost lane and the merging lane are in a congested queuing state based on the vehicle density of the rightmost lane and the vehicle density of the merging lane includes: When the vehicle density in the rightmost lane is greater than or equal to a preset threshold, the rightmost lane is determined to be in a congested queuing state; otherwise, the rightmost lane is determined not to be in a congested queuing state. When the vehicle density in the merging lane is greater than or equal to the preset threshold, the merging lane is determined to be in a congested queuing state; otherwise, the merging lane is determined not to be in a congested queuing state.
[0009] Furthermore, the process of sorting the vehicles in the rightmost lane and the vehicles in the merging lane includes: For the vehicles in the rightmost lane, they are assigned capital letter numbers A, B, C... in order of their arrival timestamps at the merging lane entrance, with the capital letters cycling from A to Z. For the motor vehicles entering the merging lane, they are assigned numbers 1, 2, 3... in sequence according to the order of their arrival timestamps at the entrance of the merging lane, and the numbers cycle from 1 to 20.
[0010] Furthermore, the step of determining whether the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rules based on the order of vehicle entry at the merging lane entrance includes: If the order of vehicles entering the merging lane conforms to "letter-number-letter-number..." or "number-letter-number-letter...", it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rule, and the process returns to step S3; otherwise, it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane do not comply with the alternating traffic rule, and the illegally cutting-in vehicle is locked for further control measures.
[0011] Furthermore, it also includes: If the order of vehicles entering the merging lane entrance is A-1, it is determined that the alternating traffic rule is met. If the order of vehicles entering the merging lane entrance is AB, it is determined that the alternating traffic rule is not followed; among them, vehicle numbered B is an illegal vehicle that cuts in line. If the order of vehicles entering the merging lane entrance is A-1-BCD, they are divided into four groups for judgment: A-1, 1-B, BC, and CD. It is determined that BC and CD do not comply with the alternating traffic rules. Among them, vehicles numbered C and D are illegal vehicles that cut in line.
[0012] The present invention provides a method for detecting motor vehicles failing to alternate turns as required, which has the following beneficial effects: By limiting the capture area, accurately distinguishing vehicles in the rightmost lane of the main road from those in the merging lane and dynamically numbering them, and combining intelligent judgment of congestion status and automatic verification of alternating turns rules, the present invention achieves high-accuracy automatic identification of violations of "failure to alternate turns as required" in merging sections without traffic lights, effectively avoiding interference and misjudgment, and has the advantages of low deployment cost, strong applicability, and objective law enforcement basis. Attached Figure Description
[0013] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the following detailed description to explain the invention, but do not constitute a limitation thereof.
[0014] Figure 1 A flowchart of the method for detecting motor vehicles not taking turns passing as required, provided by the present invention.
[0015] Figure 2 This is a schematic diagram of the camera capture angle provided by the present invention. Detailed Implementation
[0016] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for detecting motor vehicles failing to alternate passage as required by the present invention. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.
[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0018] This embodiment provides a method for detecting vehicles failing to alternate traffic as required, applied to intersections where the rightmost lane of the main road meets a merging lane from a ramp on an urban road. Figure 1 As shown, the method for detecting motor vehicles failing to take turns passing as required includes the following steps: Step S1: Acquire the captured image using the camera; where, for example... Figure 2 As shown, the camera's capture range only covers the rightmost lane and merging lane of the main road, as well as the corresponding merging lane entrance. Vehicles in the rightmost lane and merging lane enter the corresponding merging lane entrance. Preferably, step S1 includes: A high-definition camera is installed at a suitable location upstream of the intersection. The tilt and horizontal angles of the high-definition camera are adjusted on-site, and the passage areas of the rightmost lane and merging lane of the main road are calibrated to ensure that the camera's capture range only covers the rightmost lane and merging lane of the main road and the corresponding merging lane entrance, so as to reduce interference from other lanes and ensure that the vehicle images at the merging lane entrance are clear and non-overlapping.
[0019] Step S2: Detect the vehicles in the rightmost lane and the vehicles merging into the lane from the captured image, and calculate the vehicle density in the rightmost lane and the vehicle density in the merging lane. Preferably, the step of detecting vehicles in the rightmost lane and vehicles merging into the lane from the captured image includes: A pixel-level segmentation algorithm is used to identify the rightmost road area in the captured image as the merging lane, and its left adjacent area as the rightmost lane of the main road. The pixel area of the merging lane and the pixel area of the rightmost lane of the main road are recorded. A pixel-level segmentation algorithm is used to detect each motor vehicle in the captured image, and the pixel area and centroid of each motor vehicle area are recorded. Then, the lane to which each motor vehicle belongs is determined based on the lane area into which the centroid of each motor vehicle area falls. Specifically, if the center of gravity of the motor vehicle area falls within the merging lane, the motor vehicle travels in the merging lane; if the center of gravity of the motor vehicle area falls within the rightmost lane of the main road, the motor vehicle travels in the rightmost lane of the main road.
[0020] Preferably, the calculation of the vehicle density in the rightmost lane and the vehicle density in the merging lane includes: Calculate the sum of the pixel areas of all motor vehicle areas in the rightmost lane of the main road, and calculate the sum of the pixel areas of all motor vehicle areas in the merging lane; The sum of the pixel areas is divided by the pixel area of the corresponding lane to obtain the vehicle density of the corresponding lane.
[0021] Step S3: Based on the vehicle density of the rightmost lane and the vehicle density of the merging lane, determine whether both the rightmost lane and the merging lane are in a congested queuing state to confirm whether it is necessary to determine whether there is no alternation of traffic; if both lanes are in a congested queuing state, proceed to step S4; otherwise, the conditions for determining whether there is no alternation of traffic are not met, there is no need to determine whether there is no alternation of traffic, and return to step S3. Preferably, determining whether both the rightmost lane and the merging lane are in a congested queuing state based on the vehicle density of the rightmost lane and the vehicle density of the merging lane includes: When the vehicle density in the rightmost lane is greater than or equal to a preset threshold, the rightmost lane is determined to be in a congested queuing state; otherwise, the rightmost lane is determined not to be in a congested queuing state. When the vehicle density in the merging lane is greater than or equal to the preset threshold, the merging lane is determined to be in a congested queuing state; otherwise, the merging lane is determined not to be in a congested queuing state.
[0022] It should be noted that a reasonable congestion judgment threshold should be set, for example, a threshold of 70%.
[0023] Step S4: Sort the vehicles in the rightmost lane and the vehicles in the merging lane respectively, then obtain the vehicle entry order at the entrance of the merging lane from the captured image, and finally determine whether the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rules based on the vehicle entry order at the entrance of the merging lane.
[0024] Preferably, the process of sorting the vehicles in the rightmost lane and the vehicles in the merging lane includes: For the vehicles in the rightmost lane, they are assigned capital letter numbers A, B, C... in order of their arrival timestamps at the merging lane entrance (the earlier arrival is assigned a smaller capital letter), and the capital letters cycle from A to Z. For the motor vehicles entering the merging lane, they are assigned numbers 1, 2, 3... in order of their arrival timestamps at the entrance of the merging lane (those that arrive first are assigned smaller numbers), and the numbers cycle from 1 to 20.
[0025] Preferably, the step of determining whether the vehicles in the rightmost lane and the vehicles in the merging lane conform to the alternating traffic rule based on the order of vehicle entry at the merging lane entrance includes: If the order of vehicles entering the merging lane conforms to "letter-number-letter-number..." or "number-letter-number-letter...", it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rule, and the process returns to step S3; otherwise, it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane do not comply with the alternating traffic rule, and the illegally cutting-in vehicle is locked for further control measures.
[0026] Preferably, it further includes: If the order of vehicles entering the merging lane entrance is A-1, it is determined that the alternating traffic rule is met. If the order of vehicles entering the merging lane entrance is AB, it is determined that the alternating traffic rule is not followed; among them, vehicle numbered B is an illegal vehicle that cuts in line. If the order of vehicles entering the merging lane entrance is A-1-BCD, they are divided into four groups for judgment: A-1, 1-B, BC, and CD. It is determined that BC and CD do not comply with the alternating traffic rules. Among them, vehicles numbered C and D are illegal vehicles that cut in line.
[0027] This invention proposes a method for detecting motor vehicles failing to alternate lanes as required. First, the camera's capture angle is adjusted so that it only captures the rightmost lane and merging lane of the main road, along with their corresponding merging lane entrances, to reduce interference from other lanes. Then, vehicle density is used to determine if the rightmost lane and merging lane are congested and queuing, thus confirming whether non-traffic is warranted. Next, the lane of each vehicle in the captured image is detected; vehicles in the rightmost lane of the main road are sorted alphabetically, and vehicles in the merging lane are sorted numerically. Finally, based on the vehicles at the merging lane entrance, it is determined whether the vehicle sorting follows a "letter-number-letter" or "number-letter-number" order to identify any instances of non-alternating lanes, confirm the violating vehicles, and implement further control measures.
[0028] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. A method for detecting motor vehicles failing to take turns passing as required, characterized in that, The method for detecting motor vehicles failing to take turns passing as required includes the following steps: Step S1: Acquire a captured image through a camera; wherein, the camera's capture range only covers the rightmost lane and merging lane of the main road and the corresponding merging lane entrance, and vehicles in the rightmost lane and merging lane enter the corresponding merging lane entrance. Step S2: Detect the vehicles in the rightmost lane and the vehicles merging into the lane from the captured image, and calculate the vehicle density in the rightmost lane and the vehicle density in the merging lane. Step S3: Based on the vehicle density of the rightmost lane and the vehicle density of the merging lane, determine whether both the rightmost lane and the merging lane are in a congested queuing state; if both lanes are in a congested queuing state, proceed to step S4; otherwise, return to step S3. Step S4: Sort the vehicles in the rightmost lane and the vehicles in the merging lane respectively, then obtain the vehicle entry order at the entrance of the merging lane from the captured image, and finally determine whether the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rules based on the vehicle entry order at the entrance of the merging lane.
2. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 1, is characterized in that, Step S1 includes: A high-definition camera is installed at a suitable location upstream of the intersection. The tilt and horizontal angles of the high-definition camera are adjusted on-site, and the passage areas of the rightmost lane and merging lane of the main road are calibrated to ensure that the camera's capture range only covers the rightmost lane and merging lane of the main road and the corresponding merging lane entrance.
3. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 1, is characterized in that... The process of detecting vehicles in the rightmost lane and vehicles merging into the lane from the captured image includes: A pixel-level segmentation algorithm is used to identify the rightmost road area in the captured image as the merging lane, and its left adjacent area as the rightmost lane of the main road. The pixel area of the merging lane and the pixel area of the rightmost lane of the main road are recorded. A pixel-level segmentation algorithm is used to detect each motor vehicle in the captured image, and the pixel area and centroid of each motor vehicle area are recorded. Then, the lane to which each motor vehicle belongs is determined based on the lane area into which the centroid of each motor vehicle area falls. Specifically, if the center of gravity of the motor vehicle area falls within the merging lane, the motor vehicle travels in the merging lane; if the center of gravity of the motor vehicle area falls within the rightmost lane of the main road, the motor vehicle travels in the rightmost lane of the main road.
4. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 3, is characterized in that... The calculation of the vehicle density in the rightmost lane and the vehicle density in the merging lane includes: Calculate the sum of the pixel areas of all motor vehicle areas in the rightmost lane of the main road, and calculate the sum of the pixel areas of all motor vehicle areas in the merging lane; The sum of the pixel areas is divided by the pixel area of the corresponding lane to obtain the vehicle density of the corresponding lane.
5. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 1, is characterized in that, The determination of whether both the rightmost lane and the merging lane are in a congested queuing state based on the vehicle density of the rightmost lane and the vehicle density of the merging lane includes: When the vehicle density in the rightmost lane is greater than or equal to a preset threshold, the rightmost lane is determined to be in a congested queuing state; otherwise, the rightmost lane is determined not to be in a congested queuing state. When the vehicle density in the merging lane is greater than or equal to the preset threshold, the merging lane is determined to be in a congested queuing state; otherwise, the merging lane is determined not to be in a congested queuing state.
6. The method for detecting motor vehicles failing to take turns passing as required according to claim 1, characterized in that, The process of sorting the vehicles in the rightmost lane and the vehicles in the merging lane includes: For the vehicles in the rightmost lane, they are assigned capital letter numbers A, B, C... in order of their arrival timestamps at the merging lane entrance, with the capital letters cycling from A to Z. For the motor vehicles entering the merging lane, they are assigned numbers 1, 2, 3... in sequence according to the order of their arrival timestamps at the entrance of the merging lane, and the numbers cycle from 1 to 20.
7. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 6, is characterized in that, The step of determining whether the vehicles in the rightmost lane and the vehicles in the merging lane comply with the alternating traffic rules based on the order of vehicle entry at the merging lane entrance includes: If the order of vehicles entering the merging lane conforms to "letter-number-letter-number..." or "number-letter-number-letter...", it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane conform to the alternating traffic rule, and the process returns to step S3; otherwise, it is determined that the vehicles in the rightmost lane and the vehicles in the merging lane do not conform to the alternating traffic rule, and the illegally cutting-in vehicle is locked for further control measures.
8. The method for detecting motor vehicles failing to take turns passing as required, as described in claim 7, is characterized in that, Also includes: If the order of vehicles entering the merging lane entrance is A-1, it is determined that the alternating traffic rule is met. If the order of vehicles entering the merging lane entrance is AB, it is determined that the alternating traffic rule is not followed; among them, vehicle numbered B is an illegal vehicle that cuts in line. If the order of vehicles entering the merging lane entrance is A-1-BCD, they are divided into four groups for judgment: A-1, 1-B, BC, and CD. It is determined that BC and CD do not comply with the alternating traffic rules. Among them, vehicles numbered C and D are illegal vehicles that cut in line.