CN116403380A - Overrun monitoring method and device based on road side binocular camera - Google Patents
Overrun monitoring method and device based on road side binocular camera Download PDFInfo
- Publication number
- CN116403380A CN116403380A CN202310671053.5A CN202310671053A CN116403380A CN 116403380 A CN116403380 A CN 116403380A CN 202310671053 A CN202310671053 A CN 202310671053A CN 116403380 A CN116403380 A CN 116403380A
- Authority
- CN
- China
- Prior art keywords
- overrun
- binocular
- target vehicle
- vehicle
- parallax
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012544 monitoring process Methods 0.000 title claims abstract description 54
- 238000012545 processing Methods 0.000 claims description 14
- 238000007619 statistical method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 10
- 230000006835 compression Effects 0.000 description 6
- 238000007906 compression Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- 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
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an overrun monitoring method and device based on a road side binocular camera, wherein the method comprises the following steps: obtaining a binocular image of a target vehicle, generating a parallax image by using a binocular stereo matching method according to the binocular image, and calculating according to parallax in the parallax image to obtain three-dimensional coordinates of the target vehicle; based on the three-dimensional coordinates, judging whether the target vehicle is out of limit, and generating an alarm instruction under the condition that the target vehicle is out of limit, wherein the alarm instruction is used for controlling an alarm to send an alarm signal. The overrun monitoring method adopts a binocular vision scheme, can accurately detect standard and nonstandard obstacles, can realize the recording and management of overrun vehicle information, and provides powerful technical support for road traffic management and safety guarantee. Therefore, the monitoring of the overrun vehicle is realized, the accuracy and the stability of the monitoring of the overrun vehicle are improved, and the monitoring cost of the overrun vehicle is reduced.
Description
Technical Field
The invention relates to the technical field of camera calibration, in particular to an overrun monitoring method and device based on a road side binocular camera.
Background
With the development of economy, the number of various vehicles has sharply increased, and the occurrence of overrun vehicles has also increased. Overrun vehicles damage traffic facilities such as road surfaces, bridges and the like, and bring great economic and safety risks to society. Therefore, in order to ensure the safety of roads and bridges, the overrun monitoring method and device based on the road-side binocular camera are provided, so that monitoring of overrun vehicles with high accuracy, high stability and low cost is realized, and the overrun monitoring method and device are the problems to be solved urgently by those skilled in the art.
Disclosure of Invention
Therefore, the embodiment of the invention provides an overrun monitoring method and device based on a road side binocular camera, so as to monitor an overrun vehicle, thereby improving the accuracy and stability of overrun vehicle monitoring and reducing the monitoring cost of the overrun vehicle.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
an overrun monitoring method based on a road side binocular camera, the method comprising:
acquiring a binocular image of a target vehicle;
generating a parallax image by using a binocular stereo matching method according to the binocular image;
calculating according to the parallax in the parallax map to obtain the three-dimensional coordinates of the target vehicle;
judging whether the target vehicle is overrun or not based on the three-dimensional coordinates;
and under the condition that the target vehicle exceeds the limit, generating an alarm instruction, wherein the alarm instruction is used for controlling an alarm to send an alarm signal.
In some embodiments, the calculating according to the parallax in the parallax map, to obtain the three-dimensional coordinates of the target vehicle specifically includes:
extracting target feature points from the binocular image;
performing feature point matching by comparing feature descriptors for each feature point in the binocular image;
for the feature point pairs successfully matched, calculating parallax of the feature point pairs in the binocular image;
and calculating the distance from the target vehicle to the camera through the relation between the parallax and the camera parameters so as to determine the three-dimensional coordinates of the target vehicle.
In some embodiments, determining whether the target vehicle is overrun based on the three-dimensional coordinates specifically includes:
counting the parallaxes exceeding a preset alarm threshold in the parallax map;
and judging that the target vehicle is out of limit when the number of parallaxes exceeding the alarm threshold reaches a number threshold.
In some embodiments, acquiring the binocular image of the target vehicle further comprises:
compressing and encrypting the binocular image;
and uploading the compressed and encrypted binocular image to a remote server.
In some embodiments, in the event that the target vehicle is determined to be overrun, the method further comprises:
acquiring statistical data of all overrun target vehicles within a preset duration;
uploading the statistical data to a remote server so that the remote server generates a statistical analysis result.
In some embodiments, the statistics include at least one of:
the basic information of the vehicle at least comprises license plate numbers, vehicle types, vehicle colors and vehicle brand information;
vehicle size information including at least a vehicle length, a height, and a width;
the violation information at least comprises violation time, place and violation behavior information;
the detection result at least comprises whether the limit is exceeded or not and the limit is exceeded;
and the statistical analysis result at least comprises the number of the overrun vehicles, the ratio of the overrun vehicles and the distribution condition of the overrun vehicles.
The invention also provides an overrun monitoring device based on the road side binocular camera, which comprises:
an image acquisition unit configured to acquire a binocular image of a target vehicle;
the parallax generation unit is used for generating a parallax image by using a binocular stereo matching method according to the binocular image;
the image processing unit is used for calculating according to the parallaxes in the parallax map to obtain the three-dimensional coordinates of the target vehicle;
an overrun judging unit configured to judge whether the target vehicle overruns based on the three-dimensional coordinates;
and the result generation unit is used for generating an alarm instruction under the condition that the target vehicle is judged to be out of limit, and the alarm instruction is used for controlling the alarm to send an alarm signal.
The invention also provides an intelligent terminal, which comprises: the device comprises a data acquisition device, a processor and a memory;
the data acquisition device is used for acquiring data; the memory is used for storing one or more program instructions; the processor is configured to execute one or more program instructions to perform the method as described above.
The present invention also provides a computer readable storage medium having embodied therein one or more program instructions for performing the method as described above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a method as described in any of the above.
According to the overrun monitoring method and device based on the road side binocular camera, the binocular image of the target vehicle is obtained, the binocular stereo matching method is utilized to generate a parallax image according to the binocular image, and the parallax image is calculated according to the parallax in the parallax image to obtain the three-dimensional coordinate of the target vehicle; based on the three-dimensional coordinates, judging whether the target vehicle is out of limit, and generating an alarm instruction under the condition that the target vehicle is out of limit, wherein the alarm instruction is used for controlling an alarm to send an alarm signal. Compared with the prior art, the overrun monitoring system provided by the invention adopts a binocular vision scheme, can accurately detect standard and nonstandard obstacles, and has the advantages of high monitoring precision, good real-time performance, convenience in operation, high reliability and the like. Meanwhile, the system can also realize the record and management of the information of the overrun vehicles, and provides powerful technical support for road traffic management and safety guarantee. Therefore, the monitoring of the overrun vehicle is realized, the accuracy and the stability of the monitoring of the overrun vehicle are improved, and the monitoring cost of the overrun vehicle is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a flowchart of an overrun monitoring method based on a road side binocular camera provided by the present invention;
FIG. 2 is a second flowchart of an overrun monitoring method based on a road side binocular camera according to the present invention;
FIG. 3 is a flow chart of a method for overrun monitoring of binocular cameras in one particular use scenario of the present invention;
FIG. 4 is a block diagram of an overrun monitoring device for binocular cameras in one particular use scenario of the present invention;
fig. 5 is a block diagram of an overrun monitoring device based on a road side binocular camera.
Description of the embodiments
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
First, terms involved in the embodiments of the present invention will be explained.
Parallax: the position of pixels imaged under the left and right cameras of the same scene deviates. For example, an X point in the scene is an X coordinate at the left camera, and an (x+d) coordinate at the right camera, then d is a value of the X coordinate point in the disparity map, and the disparity of each point on the disparity map is recorded as disp.
In order to solve the technical problems, the invention relates to a plurality of fields including the fields of binocular machine vision technology, road side monitoring technology, big data analysis and the like. The binocular machine vision technology is a technology for obtaining scene image information by adopting a binocular camera, and processing and analyzing the image to obtain depth information and three-dimensional structure information. The road side monitoring technology is a technology for setting monitoring equipment on the road side and carrying out real-time monitoring and detection on vehicles running on the road. Whereas big data analysis refers to techniques that process and analyze large-scale data to discover rules, associations, and value information hidden therein. By comprehensively applying the technologies, the overrun monitoring system can realize high-precision detection and identification of overrun vehicles, process and analyze related data, and improve traffic safety level and management efficiency.
Referring to fig. 1, fig. 1 is a flowchart of an overrun monitoring method based on a road side binocular camera according to the present invention.
In a specific embodiment, the overrun monitoring method based on the road side binocular camera provided by the invention comprises the following steps:
s110: acquiring a binocular image of a target vehicle;
s120: generating a parallax image by using a binocular stereo matching method according to the binocular image;
s130: calculating according to the parallax in the parallax map to obtain the three-dimensional coordinates of the target vehicle;
s140: judging whether the target vehicle is overrun or not based on the three-dimensional coordinates;
s150: and under the condition that the target vehicle exceeds the limit, generating an alarm instruction, wherein the alarm instruction is used for controlling an alarm to send an alarm signal.
In a specific use scene, the overrun monitoring method based on the road side binocular camera is used for monitoring the overrun condition of vehicles in traffic facilities such as roads, bridges and the like. The hardware system based on the overrun monitoring method comprises a road side binocular camera, an image processing device, an audible and visual alarm system and an illegal vehicle information recording device. The road side binocular camera is used for acquiring binocular image information of the vehicle, the image processing device is used for processing and analyzing the image, a stereoscopic vision technology is adopted, the depth and three-dimensional information of the vehicle with high precision and high accuracy are measured, further the overrun condition of the vehicle is analyzed and identified, an audible and visual alarm is sent out to warn a driver if the danger is judged, the result is transmitted to the illegal vehicle information recording device, and the information of the overrun vehicle is recorded.
In some embodiments, as shown in fig. 2, the three-dimensional coordinates of the target vehicle are obtained by calculating according to the parallaxes in the parallaxes map, which specifically includes the following steps:
s210: extracting target feature points from the binocular image;
s220: performing feature point matching by comparing feature descriptors for each feature point in the binocular image;
s230: for the feature point pairs successfully matched, calculating parallax of the feature point pairs in the binocular image;
s240: and calculating the distance from the target vehicle to the camera through the relation between the parallax and the camera parameters so as to determine the three-dimensional coordinates of the target vehicle.
In image processing, the stereoscopic technique refers to determining the positional relationship of the same object in two images by comparing the two images at different angles of view. In the invention, the road side binocular camera can acquire binocular image information of the vehicle, and the two images are subjected to stereo matching. The principle of stereo matching is based on the measurement of parallax. Parallax refers to the amount of shift of the same object in the viewing plane in two images due to the difference in viewing angle of the human eye or binocular camera. In the image processing device, the distance between the object and the camera can be obtained by calculating the parallax of the same object in the two images, and then the three-dimensional coordinates of the object can be determined.
In particular, stereo matching can be generally divided into the following steps:
1) Feature extraction: representative feature points such as corner points, edges and the like are extracted from the binocular image.
2) Feature matching: for each feature point in the two images, it is determined whether they represent the same object by comparing their feature descriptors.
3) Parallax calculation: for pairs of feature points that match successfully, their disparities in the two images, i.e. their pixel differences in the horizontal direction, are calculated.
4) Depth estimation: and calculating the distance from the object to the camera through the relation between the parallax and the camera parameters, and further determining the three-dimensional coordinates of the object.
Wherein, the calculation formula of parallax to three-dimensional coordinates is as follows:
where f is the focal length, b is the baseline length, d is the parallax, u and v are the pixel coordinates on the left eye image,
and->
Is the principal point coordinate on the left eye image.
In some embodiments, determining whether the target vehicle is overrun based on the three-dimensional coordinates specifically includes:
counting the parallaxes exceeding a preset alarm threshold in the parallax map;
and judging that the target vehicle is out of limit when the number of parallaxes exceeding the alarm threshold reaches a number threshold.
It should be understood that the alarm threshold is designed according to a specific height-limiting scenario, for example, a 2.5 m height-limiting rod may be set to a parallax value corresponding to 2.2 m-2.5 m height, and a 4.5 m height-limiting bridge may be set to a parallax value corresponding to 4.2 m-4.5 m height, and the calculated value of the specific parallax value may be different according to different cameras.
Specifically, according to an alarm threshold value set in advance in the system, counting out the overrun parallax in the parallax map, and if the overrun parallax meets a specified threshold value, determining that the ultrahigh obstacle passes, and carrying out alarm and data uploading by the system.
Further, acquiring a binocular image of the target vehicle, and then further comprising:
compressing and encrypting the binocular image;
and uploading the compressed and encrypted binocular image to a remote server.
There are various methods for image compression, and compression parameters can be adjusted according to specific requirements, which specifically may include:
1. coding format selection: the selection of a suitable video coding format, commonly referred to as h.264, h.265 (also known as HEVC), VP9, etc. These encoding formats use different compression algorithms, which can effectively reduce the video file size.
2. Resolution adjustment: reducing the resolution of the video may reduce the file size. The proper resolution can be selected according to the actual requirement, for example, the high-definition video is compressed into standard-definition video.
3. Bit rate setting: adjusting the bit rate of the video may control the quality and file size of the video. Lower bit rates result in smaller file sizes, but may sacrifice video quality.
4. Frame rate control: reducing the frame rate of the video may reduce the file size. Common frame rates include 30 frames/second and 24 frames/second, which can be adjusted according to actual requirements.
5. And (3) compression parameter tuning: video compression software typically provides some additional parameter settings such as GOP size, quantization parameters, etc. By adjusting these parameters, the compression effect can be further optimized.
The image encryption method can also be various, and one of the following methods can be specifically selected according to specific requirements:
1. symmetric encryption: the same key is used for encryption and decryption. Common symmetric encryption algorithms include AES (advanced encryption standard) and the like. When the video is encrypted symmetrically, a key is selected first, then the video is encrypted by using the key, and the same key is used for decryption when the video is decrypted.
2. Asymmetric encryption: encryption and decryption are performed using public and private keys. Asymmetric encryption algorithms include RSA, etc. In video encryption, the public key of the receiver may be used to encrypt the video, which may only be decrypted if the receiver has the corresponding private key.
3. Digital watermarking: the hidden information is embedded in the video and can be used to verify the authenticity and integrity of the video. The digital watermark may be visible or invisible and an appropriate watermarking algorithm may be selected according to the requirements.
Drm (digital rights management): for protecting the legal use and distribution of video content. DRM technologies may encrypt video while providing license management and access control to ensure that only authorized users can access and play the video.
That is, the method provided by the invention also relates to a data uploading function, and the vehicle image acquired by the binocular camera and the processing result thereof are uploaded to the central database through the network. And when uploading data, the system also uploads information such as the running speed of the vehicle, the time stamp, the vehicle license plate, binocular images of the original vehicle and the like to a central database, so that the subsequent data management and analysis are convenient. Meanwhile, in order to facilitate the processing and the use of the subsequent data, the invention also comprises the processing of compressing and encrypting the image to upload the dual-purpose original image, thereby ensuring the speed and the safety of data transmission. In a word, the overrun monitoring system and the data uploading mode have the advantages of high efficiency, accuracy, safety, reliability and the like, and have important practicability and innovation in the aspects of road traffic management and safety guarantee.
In some embodiments, in the event that the target vehicle is determined to be overrun, the method further comprises:
acquiring statistical data of all overrun target vehicles within a preset duration;
uploading the statistical data to a remote server so that the remote server generates a statistical analysis result.
Wherein the statistics include at least one of:
the basic information of the vehicle at least comprises license plate numbers, vehicle types, vehicle colors and vehicle brand information;
vehicle size information including at least a vehicle length, a height, and a width;
the violation information at least comprises violation time, place and violation behavior information;
the detection result at least comprises whether the limit is exceeded or not and the limit is exceeded;
and the statistical analysis result at least comprises the number of the overrun vehicles, the ratio of the overrun vehicles and the distribution condition of the overrun vehicles.
This information may be saved by the storage device and transmitted to a remote server for statistical analysis via the communication device. Through analysis of the information, traffic management departments can know the behavior rules and distribution conditions of overrun vehicles, and further formulate more scientific and reasonable management measures to improve the safety and efficiency of road traffic. Meanwhile, for the car owners, the car owners can know whether the car owners overrun or not through the information, danger possibly occurring is avoided in time, and safety awareness and operation efficiency are improved.
As shown in fig. 3 and fig. 4, taking a specific usage scenario as an example, the implementation process of the overrun monitoring method provided by the present invention is briefly described:
1. the road side binocular camera acquires binocular image information of the vehicle;
2. the image processing device performs binocular stereo matching technology to generate a parallax image;
3. obtaining depth and three-dimensional information of the vehicle according to parallax calculation of the parallax map;
4. judging whether the vehicle is overrun or not according to the depth and the three-dimensional information of the vehicle;
5. if the vehicle overrun is detected, starting an audible and visual alarm;
6. uploading overrun data to a remote server;
7. and after a period of time, carrying out centralized statistical analysis according to the overrun vehicle information.
In the specific embodiment, the overrun monitoring method based on the road side binocular camera provided by the invention is characterized in that a binocular image of a target vehicle is obtained, a parallax image is generated by using a binocular stereo matching method according to the binocular image, and the three-dimensional coordinate of the target vehicle is obtained by calculating according to the parallax in the parallax image; based on the three-dimensional coordinates, judging whether the target vehicle is out of limit, and generating an alarm instruction under the condition that the target vehicle is out of limit, wherein the alarm instruction is used for controlling an alarm to send an alarm signal. Compared with the prior art, the overrun monitoring method adopts a binocular vision scheme, can accurately detect standard and nonstandard obstacles, and has the advantages of high monitoring precision, good real-time performance, convenience in operation, high reliability and the like. Meanwhile, the system can also realize the record and management of the information of the overrun vehicles, and provides powerful technical support for road traffic management and safety guarantee. Therefore, the monitoring of the overrun vehicle is realized, the accuracy and the stability of the monitoring of the overrun vehicle are improved, and the monitoring cost of the overrun vehicle is reduced.
In addition to the above method, the present invention also provides an overrun monitoring device based on a road side binocular camera, as shown in fig. 5, the device includes:
an image acquisition unit 510 for acquiring a binocular image of a target vehicle;
a parallax generating unit 520, configured to generate a parallax map according to the binocular image by using a binocular stereo matching method;
an image processing unit 530, configured to calculate according to the parallaxes in the parallax map, and obtain three-dimensional coordinates of the target vehicle;
an overrun judging unit 540 for judging whether the target vehicle overruns or not based on the three-dimensional coordinates;
and the result generating unit 550 is used for generating an alarm instruction when the target vehicle is judged to exceed the limit, wherein the alarm instruction is used for controlling the alarm to send an alarm signal.
In some embodiments, the calculating according to the parallax in the parallax map, to obtain the three-dimensional coordinates of the target vehicle specifically includes:
extracting target feature points from the binocular image;
performing feature point matching by comparing feature descriptors for each feature point in the binocular image;
for the feature point pairs successfully matched, calculating parallax of the feature point pairs in the binocular image;
and calculating the distance from the target vehicle to the camera through the relation between the parallax and the camera parameters so as to determine the three-dimensional coordinates of the target vehicle.
In some embodiments, determining whether the target vehicle is overrun based on the three-dimensional coordinates specifically includes:
counting the parallaxes exceeding a preset alarm threshold in the parallax map;
and judging that the target vehicle is out of limit when the number of parallaxes exceeding the alarm threshold reaches a number threshold.
In some embodiments, acquiring the binocular image of the target vehicle further comprises:
compressing and encrypting the binocular image;
and uploading the compressed and encrypted binocular image to a remote server.
In some embodiments, in the event that the target vehicle is determined to be overrun, the method further comprises:
acquiring statistical data of all overrun target vehicles within a preset duration;
uploading the statistical data to a remote server so that the remote server generates a statistical analysis result.
In some embodiments, the statistics include at least one of:
the basic information of the vehicle at least comprises license plate numbers, vehicle types, vehicle colors and vehicle brand information;
vehicle size information including at least a vehicle length, a height, and a width;
the violation information at least comprises violation time, place and violation behavior information;
the detection result at least comprises whether the limit is exceeded or not and the limit is exceeded;
and the statistical analysis result at least comprises the number of the overrun vehicles, the ratio of the overrun vehicles and the distribution condition of the overrun vehicles.
In the specific embodiment, the overrun monitoring system based on the road side binocular camera provided by the invention is characterized in that a binocular image of a target vehicle is obtained, a parallax image is generated by using a binocular stereo matching method according to the binocular image, and the three-dimensional coordinate of the target vehicle is obtained by calculating according to the parallax in the parallax image; based on the three-dimensional coordinates, judging whether the target vehicle is out of limit, and generating an alarm instruction under the condition that the target vehicle is out of limit, wherein the alarm instruction is used for controlling an alarm to send an alarm signal. Compared with the prior art, the overrun monitoring system provided by the invention adopts a binocular vision scheme, can accurately detect standard and nonstandard obstacles, and has the advantages of high monitoring precision, good real-time performance, convenience in operation, high reliability and the like. Meanwhile, the system can also realize the record and management of the information of the overrun vehicles, and provides powerful technical support for road traffic management and safety guarantee. Therefore, the monitoring of the overrun vehicle is realized, the accuracy and the stability of the monitoring of the overrun vehicle are improved, and the monitoring cost of the overrun vehicle is reduced.
The present invention also provides a computer program product comprising a computer program storable on a non-transitory computer readable storage medium, the computer program being capable of performing the methods as described above when executed by a processor.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP for short), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), a field programmable gate array (Field Programmable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (Electrically EPROM, EEPROM), or a flash Memory.
The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (Direct Rambus RAM, DRRAM).
The storage media described in embodiments of the present invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in a combination of hardware and software. When the software is applied, the corresponding functions may be stored in a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer-readable media includes both computer-readable storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the foregoing is by way of illustration and description only, and is not intended to limit the scope of the invention.
Claims (10)
1. An overrun monitoring method based on a road side binocular camera, which is characterized by comprising the following steps:
acquiring a binocular image of a target vehicle;
generating a parallax image by using a binocular stereo matching method according to the binocular image;
calculating according to the parallax in the parallax map to obtain the three-dimensional coordinates of the target vehicle;
judging whether the target vehicle is overrun or not based on the three-dimensional coordinates;
and under the condition that the target vehicle exceeds the limit, generating an alarm instruction, wherein the alarm instruction is used for controlling an alarm to send an alarm signal.
2. The overrun monitoring method based on the roadside binocular camera according to claim 1, wherein the calculating is performed according to the parallaxes in the parallaxes map to obtain the three-dimensional coordinates of the target vehicle, specifically comprising:
extracting target feature points from the binocular image;
performing feature point matching by comparing feature descriptors for each feature point in the binocular image;
for the feature point pairs successfully matched, calculating parallax of the feature point pairs in the binocular image;
and calculating the distance from the target vehicle to the camera through the relation between the parallax and the camera parameters so as to determine the three-dimensional coordinates of the target vehicle.
3. The overrun monitoring method based on a roadside binocular camera according to claim 1, wherein the determining whether the target vehicle is overrun based on the three-dimensional coordinates specifically comprises:
counting parallax values exceeding a preset alarm threshold in the parallax map;
and judging that the target vehicle is out of limit under the condition that the parallax value exceeds the alarm threshold value.
4. The road side binocular camera-based overrun monitoring method of claim 1, wherein acquiring binocular images of the target vehicles, further comprising:
compressing and encrypting the binocular image;
and uploading the compressed and encrypted binocular image to a remote server.
5. The overrun monitoring method based on roadside binocular camera according to claim 1, wherein in case of determining that the target vehicle is overrun, the method further comprises:
acquiring statistical data of all overrun target vehicles within a preset duration;
uploading the statistical data to a remote server so that the remote server generates a statistical analysis result.
6. The roadside binocular camera-based overrun monitoring method of claim 5, wherein the statistical data includes at least one of:
the basic information of the vehicle at least comprises license plate numbers, vehicle types, vehicle colors and vehicle brand information;
vehicle size information including at least a vehicle length, a height, and a width;
the violation information at least comprises violation time, place and violation behavior information;
the detection result at least comprises whether the limit is exceeded or not and the limit is exceeded;
and the statistical analysis result at least comprises the number of the overrun vehicles, the ratio of the overrun vehicles and the distribution condition of the overrun vehicles.
7. Overrun monitoring device based on road side binocular camera, characterized in that the device comprises:
an image acquisition unit configured to acquire a binocular image of a target vehicle;
the parallax generation unit is used for generating a parallax image by using a binocular stereo matching method according to the binocular image;
the image processing unit is used for calculating according to the parallaxes in the parallax map to obtain the three-dimensional coordinates of the target vehicle;
an overrun judging unit configured to judge whether the target vehicle overruns based on the three-dimensional coordinates;
and the result generation unit is used for generating an alarm instruction under the condition that the target vehicle is judged to be out of limit, and the alarm instruction is used for controlling the alarm to send an alarm signal.
8. An intelligent terminal, characterized in that, the intelligent terminal includes: the device comprises a data acquisition device, a processor and a memory;
the data acquisition device is used for acquiring data; the memory is used for storing one or more program instructions; the processor being configured to execute one or more program instructions for performing the method of any of claims 1-6.
9. A computer readable storage medium having one or more program instructions embodied therein for performing the method of any of claims 1-6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310671053.5A CN116403380A (en) | 2023-06-08 | 2023-06-08 | Overrun monitoring method and device based on road side binocular camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310671053.5A CN116403380A (en) | 2023-06-08 | 2023-06-08 | Overrun monitoring method and device based on road side binocular camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116403380A true CN116403380A (en) | 2023-07-07 |
Family
ID=87016503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310671053.5A Pending CN116403380A (en) | 2023-06-08 | 2023-06-08 | Overrun monitoring method and device based on road side binocular camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116403380A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313536A (en) * | 2011-07-21 | 2012-01-11 | 清华大学 | Method for barrier perception based on airborne binocular vision |
| CN104236478A (en) * | 2014-09-19 | 2014-12-24 | 山东交通学院 | Automatic vehicle overall size measuring system and method based on vision |
| CN105157608A (en) * | 2015-08-31 | 2015-12-16 | 浙江大华技术股份有限公司 | Detection method, apparatus, and system of oversized vehicle |
| CN106650708A (en) * | 2017-01-19 | 2017-05-10 | 南京航空航天大学 | Visual detection method and system for automatic driving obstacles |
| CN109191504A (en) * | 2018-08-01 | 2019-01-11 | 南京航空航天大学 | A kind of unmanned plane target tracking |
| CN109813334A (en) * | 2019-03-14 | 2019-05-28 | 西安工业大学 | Real-time high-precision vehicle mileage calculation method based on binocular vision |
| CN110675442A (en) * | 2019-09-23 | 2020-01-10 | 的卢技术有限公司 | Local stereo matching method and system combined with target identification technology |
| CN111951339A (en) * | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for performing parallax calculation by using heterogeneous binocular cameras |
| WO2021057742A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Positioning method and apparatus, device, and storage medium |
-
2023
- 2023-06-08 CN CN202310671053.5A patent/CN116403380A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313536A (en) * | 2011-07-21 | 2012-01-11 | 清华大学 | Method for barrier perception based on airborne binocular vision |
| CN104236478A (en) * | 2014-09-19 | 2014-12-24 | 山东交通学院 | Automatic vehicle overall size measuring system and method based on vision |
| CN105157608A (en) * | 2015-08-31 | 2015-12-16 | 浙江大华技术股份有限公司 | Detection method, apparatus, and system of oversized vehicle |
| CN106650708A (en) * | 2017-01-19 | 2017-05-10 | 南京航空航天大学 | Visual detection method and system for automatic driving obstacles |
| CN109191504A (en) * | 2018-08-01 | 2019-01-11 | 南京航空航天大学 | A kind of unmanned plane target tracking |
| CN109813334A (en) * | 2019-03-14 | 2019-05-28 | 西安工业大学 | Real-time high-precision vehicle mileage calculation method based on binocular vision |
| CN110675442A (en) * | 2019-09-23 | 2020-01-10 | 的卢技术有限公司 | Local stereo matching method and system combined with target identification technology |
| WO2021057742A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Positioning method and apparatus, device, and storage medium |
| CN111951339A (en) * | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for performing parallax calculation by using heterogeneous binocular cameras |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9288451B2 (en) | Image processing apparatus and image processing method | |
| KR100878579B1 (en) | Watermarking Method, Watermark Validation Method, Watermarking Device and Watermark Validation Device | |
| CN111179345B (en) | Front vehicle line-crossing violation behavior automatic detection method and system based on vehicle-mounted machine vision | |
| CN106341664B (en) | data processing method and device | |
| JP6273725B2 (en) | Continuous road segment detection method and detection apparatus | |
| TWI582724B (en) | Event reconstruction system and method | |
| US20150029308A1 (en) | Apparatus and method for reconstructing scene of traffic accident | |
| CN113240632B (en) | Pavement detection method and system based on semantic segmentation network and intelligent terminal | |
| EP2084651A2 (en) | Electronic traffic monitor | |
| KR20140130213A (en) | Method and apparatus for authenticating video content | |
| US10848642B2 (en) | Apparatus for generating trusted image data, an apparatus for authentication of an image and a method for generating trusted image data | |
| CN107959885B (en) | Motion detection method of encrypted video | |
| DE102018120655A1 (en) | AUTHENTICATION OF VEHICLE TO VEHICLE COMMUNICATIONS | |
| CN115053225A (en) | Privacy-preserving video analytics | |
| CN108650491A (en) | A kind of video watermark detection method towards monitoring system | |
| CN105959696A (en) | Video content safety monitoring method based on SIFT characteristic algorithm | |
| CN105022946A (en) | Face decryption method and device | |
| CN108038488B (en) | Robustness image hashing method based on SIFT and LBP mixing | |
| CN113240631B (en) | Road surface detection method and system based on RGB-D fusion information and intelligent terminal | |
| CN116403380A (en) | Overrun monitoring method and device based on road side binocular camera | |
| CN111383255B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| US20210150745A1 (en) | Image processing method, device, electronic apparatus, and computer readable storage medium | |
| Joshi et al. | Tampering detection in digital video-a review of temporal fingerprints based techniques | |
| CN114938503B (en) | Remote alarm method of security chip and security chip device | |
| KR102032828B1 (en) | System and method of blackbox video sequence analysis for gathering information of crime scene or car accident |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230707 |