CN113362608A

CN113362608A - Vehicle detection method and device

Info

Publication number: CN113362608A
Application number: CN202010153023.1A
Authority: CN
Inventors: 李阳
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Cloud Computing Technologies Co Ltd
Priority date: 2020-03-06
Filing date: 2020-03-06
Publication date: 2021-09-07

Abstract

A vehicle detection method and device, in order to raise the detection efficiency that the vehicle detects violating the regulations, in this method, the checkout gear can obtain the picture to be detected first, later, the checkout gear can confirm the vehicle that exists in the picture, while confirming the vehicle has violated the violation factor in the picture, send the instruction that the vehicle violates the regulations. In the whole vehicle detection process, manual participation is not needed, and efficient vehicle detection can be realized by virtue of the detection device. The detection device can send out an instruction after determining that the vehicle violates the violation element, so that the timeliness of the violation vehicle detection can be ensured.

Description

Vehicle detection method and device

Technical Field

The present application relates to the field of communications technologies, and in particular, to a vehicle detection method and apparatus.

Background

With the rapid development of social economy and the continuous improvement and perfection of road traffic construction, the number of automobiles is increased in a well-jet manner. However, the automobiles are convenient and cause various problems, such as traffic accidents, illegal parking, and the like.

At present, vehicles parking against regulations mainly depend on field workers to take pictures for evidence. And then the owner of the vehicle which parks illegally needs to pay the corresponding penalty amount by himself. When the owner of the vehicle parking against the regulations pays the penalty amount, the related staff further needs to further verify according to the pictures taken by the field staff in the past. When the field workers take photos for evidence collection, the problem that the photos are not clear often exists, the further verification of the related workers is difficult, and therefore, a lot of additional recognition and correction work is needed.

In conclusion, the current vehicle detection efficiency of illegal parking is poor.

Disclosure of Invention

The application provides a vehicle detection method and device, which are used for improving the detection efficiency of illegal vehicle detection.

In a first aspect, an embodiment of the present application provides a vehicle detection method, which may be performed by a detection device, and the method includes: the detection device may obtain the image to be detected first, for example, the detection device may actively obtain the image from other devices, or the other devices may actively send the image to the detection device. The detection means may then identify the vehicle present in the image and issue an indication of a vehicle violation upon identifying the vehicle in the image as violating the violation element.

By the method, the illegal vehicle detection does not need manual participation, and efficient vehicle detection can be realized by the detection device. In addition, the detection device can give an instruction after determining that the vehicle violates the violation element, so that the timeliness of the violation vehicle detection can be ensured, that is, the detection device can detect the image in real time and obtain a final detection result (such as vehicle violation).

In a possible implementation manner, when the detection device determines a vehicle existing in the image, the detection device may further obtain vehicle information such as a license plate, a model and the like of the vehicle from the image; in the case where the detection device determines that the vehicle in the image violates the violation element, the detection device may feed back violation information indicating that the vehicle violates to other devices, and the violation information may also carry vehicle information of the vehicle.

By the method, the detection device can timely inform other equipment of vehicle violation in an information interaction mode.

In one possible implementation, the detection device may detect the violation elements in the image, and the types of violation elements that the detection device can detect are many, including but not limited to: the device comprises a yellow solid line, a sidewalk, a zebra crossing, a no-stop line, a no-stop sign, a yellow dotted line and a diversion line.

By the method, the detection device can detect various different violation factors, so that the detection device can detect the violation conditions of various vehicles, and the accuracy of the detection result obtained by the detection device in the image detection process is higher.

In one possible implementation, when the detection means determines that the vehicle violates a violation element based on the image, the violation element in the image may be detected first, and then the vehicle violating the violation element present in the image may be determined based on the detected violation element.

By the method, the detection device can conveniently and rapidly determine that the vehicle violates the violation elements through the detected violation elements, and the detection efficiency of the violation vehicles is further ensured.

In one possible implementation manner, when the detection device determines that the vehicle violating the violation element exists in the image, whether the vehicle violating the violation element is determined according to the relative position of the violation element and the vehicle in the image or a no-parking area where the vehicle is prohibited from parking is divided in the image according to the violation element, and the vehicle in the no-parking area in the image is taken as the vehicle violating the violation element.

By the method, the detection device can detect the vehicles violating the violation factors in various different modes, and the detection mode is more flexible.

In a second aspect, embodiments of the present application provide a vehicle detection method, which may be performed by a detection device, and the method includes: the detection device may obtain the video to be detected first, for example, the detection device may actively obtain the video from other devices, or the other devices may actively send the video to the detection device. Then, determining the vehicles in the multi-frame images from the continuous multi-frame images in the video; and then when the vehicle is determined to violate the violation element based on each frame of the multi-frame images, sending out an indication of vehicle violation, wherein the multi-frame images can be part of the image frames in the video or all the image frames in the video.

By the method, the detection of the violation vehicle does not need workers, and efficient vehicle detection can be realized only by using the detection device. When the detection device detects the violation vehicle, the detection device can send an indication, so that the timeliness of the violation vehicle detection is ensured.

In a possible implementation manner, when the detection device determines that the vehicle violates the violation element based on each frame of image in the multiple frames of images, the detection device may determine that the vehicle violates the same violation element in the multiple frames of images based on the violation element and each frame of image in the multiple frames of images, and the vehicle is the vehicle violating the violation element.

By the method, under the condition that the vehicle violates the same violation element in the multi-frame image in the video, the vehicle is used as a violation vehicle, and the accuracy of violation vehicle detection can be ensured.

In a possible implementation manner, when determining a vehicle existing in a multi-frame image, the detection device may further acquire vehicle information such as a license plate, a vehicle type, and the like of the vehicle from a part of or all of the image frames in the multi-frame image; when the detection device determines that the vehicle violates the violation element, the detection device may feed back violation information indicating that the vehicle violates the violation to other devices, and the violation information may also carry vehicle information of the vehicle.

In one possible implementation, the detection device may detect the presence of the violation element in the plurality of frames of images, and the types of violation elements that the detection device can detect are many, including but not limited to: the device comprises a yellow solid line, a sidewalk, a zebra crossing, a no-stop line, a no-stop sign, a yellow dotted line and a diversion line.

By the method, the detection device can detect various different violation factors, so that the detection device can detect various violation conditions, and the accuracy of the detection result obtained by the detection device in the video detection process is higher.

In one possible implementation, the detection device needs to distinguish between a stationary vehicle and a moving vehicle in the video when determining the vehicle from the plurality of frames of images, for example, the detection device may determine the moving vehicle and the stationary vehicle based on the position of the vehicle in each frame of image in the plurality of frames of images; the moving vehicle is a vehicle whose vehicle position changes in each of the plurality of frame images, and the stationary vehicle is a vehicle whose vehicle position does not change in each of the plurality of frame images. After that, the detection device can reject the running vehicle from the vehicles with the multi-frame images and keep the static vehicle.

By the method, the running vehicle can only pass through or stay in the violation element for a short time and is not a real violation vehicle, and the detection device eliminates the running vehicle, so that the finally determined violation vehicle is a static vehicle, and the accuracy of the detection result is further ensured.

In a possible implementation mode, when the detection device determines that the vehicle violates the violation elements based on each frame of image in the multi-frame image, the detection device can detect the violation elements of part or all of the image frames in the multi-frame image, and the stationary vehicle violating the violation elements in the part or all of the image frames is the violation vehicle.

By the method, the detection device can determine the violation factors of the vehicle simply through the detected violation factors, and the high efficiency of vehicle detection is further ensured.

In a possible implementation manner, when the detection device detects a violation vehicle, the detection device may determine an image frame appearing for the first time and an image frame appearing for the last time of the violation vehicle, and if the violation element is violated by the vehicle in both the two image frames and the time interval of the two image frames is greater than the threshold value, the vehicle is a violation vehicle.

By the method, the detection device can determine whether the vehicle breaks rules and regulations only by detecting the two frames of images where the vehicle is located, and the detection mode is more efficient. In addition, in a scene that the violation duration of the vehicle is required (if the violation duration exceeds a certain duration, the vehicle can be judged to be a violation vehicle), whether the vehicle violates the violation element can be conveniently determined by detecting the time interval of two frames of images where the vehicle is located.

In a possible implementation mode, when the detection device determines that the vehicle violates the violation element based on each frame of image in the multi-frame image, whether the vehicle violates the violation element can be determined according to the relative position of the violation element and the vehicle in the multi-frame image; or determining a forbidden stop area in the multi-frame image according to the violation element in the multi-frame image, and then taking the static vehicle in the forbidden stop area as the vehicle violating the violation element.

In a third aspect, embodiments of the present application provide a vehicle detection method, which may be performed by a detection device, and the method includes: the detection device may obtain the video to be detected first, for example, the detection device may actively obtain the video from other devices, or the other devices may actively send the video to the detection device. The detection device can also acquire the information of a forbidden stop area in a scene shot by the video, determine vehicles in continuous multi-frame images in the video, determine the vehicles in the forbidden stop area in each frame image in the multi-frame images based on the multi-frame images, and then indicate the vehicles to violate regulations. The multi-frame image may be a part of the image frames in the video or all the image frames in the video.

By the method, the detection of the violation vehicle does not need workers, and efficient vehicle detection can be realized only by using the detection device. When the detection device detects the violation vehicle, the detection device can send out an indication, so that the timeliness of the violation vehicle detection is improved.

In a possible implementation manner, when determining a vehicle existing in a multi-frame image, the detection device may further acquire vehicle information such as a license plate, a vehicle type, and the like of the vehicle from a part of or all of the image frames in the multi-frame image; under the condition that the detection device determines that the vehicle is a violation vehicle, the detection device can feed back violation information indicating vehicle violation to other equipment, and the violation information can also carry the vehicle information of the vehicle.

In a possible implementation manner, the information of the no-parking area is that the detection apparatus may be sent to the detection apparatus by another device, or the detection apparatus is determined in advance according to an image of a scene captured by the video.

By the method, the detection device can acquire the information of the no-parking area in advance, the detection time can be effectively shortened, and the timeliness of the detection of the illegal vehicle is ensured.

In one possible implementation, the detection device needs to distinguish between a stationary vehicle and a moving vehicle in the video when determining the vehicle from the plurality of frames of images, for example, the detection device may determine the moving vehicle and the stationary vehicle based on the position of the vehicle in each frame of image in the plurality of frames of images; the moving vehicle is a vehicle whose vehicle position changes in each of the plurality of frame images, and the stationary vehicle is a vehicle whose vehicle position does not change in each of the plurality of frame images. And then, the detection device can eliminate the running vehicles in the multi-frame images and keep the static vehicles.

In a possible implementation manner, when the detection device determines the same vehicle located in the no-parking area in each frame of image in the multi-frame image based on the multi-frame image, the detection device may determine the no-parking area of a part or all of the image frames in the multi-frame image, and the stationary vehicle located in the no-parking area in the part or all of the image frames is the violation vehicle.

By the method, the detection device can determine the violation vehicle through the detected no-parking area more simply, and the high efficiency of vehicle detection is further ensured.

In a possible implementation manner, when the detection device detects a violation vehicle, it may determine an image frame that the vehicle appears for the first time and an image frame that the vehicle appears for the last time, and if the vehicle is located in the no-parking area in both the two image frames and the time interval of the two image frames is greater than the threshold value, the vehicle is a violation vehicle.

By the method, the detection device can determine whether the vehicle belongs to the position vehicle or not by detecting the two frames of images of the vehicle, and the detection efficiency of the detection mode is higher. In addition, in a scene that the vehicle violation duration is required (if the vehicle violation duration is judged to be a violation vehicle after a certain duration is exceeded), whether the vehicle is a violation vehicle or not can be conveniently determined by detecting the time interval of two frames of images of the vehicle.

In a possible implementation manner, when determining the no-parking area, the detection device determines the no-parking area according to the violation elements of the image of the scene shot by the video, which are acquired in advance, and then after determining the no-parking area, may store the information of the no-parking area locally.

By the method, the detection device can determine the forbidden zone more conveniently.

In a fourth aspect, an embodiment of the present application further provides a detection apparatus, and for beneficial effects, reference may be made to the description of the first aspect, which is not described herein again. The apparatus has the functionality to implement the actions in the method instance of the first aspect described above. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions. In a possible design, the structure of the apparatus includes a transmission unit, a determination unit, and an indication unit, and these units may perform corresponding functions in the method example of the first aspect, for which specific reference is made to the detailed description in the method example, and details are not repeated here.

In a fifth aspect, an embodiment of the present application further provides a detection apparatus, and for beneficial effects, reference may be made to the description of the second aspect, which is not described herein again. The apparatus has the functionality to implement the actions in the method instance of the second aspect described above. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions. In a possible design, the structure of the apparatus includes a transmission unit, a determination unit, and an indication unit, and these units may perform corresponding functions in the method example of the second aspect, for specific reference, detailed description in the method example is given, and details are not repeated here.

In a sixth aspect, an embodiment of the present application further provides a detection apparatus, and for beneficial effects, reference may be made to the description of the third aspect, which is not described herein again. The apparatus has the function of implementing the actions in the method instance of the third aspect described above. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions. In a possible design, the structure of the apparatus includes a transmission unit, a determination unit, and an indication unit, and these units may perform corresponding functions in the method example of the third aspect, for specific reference, detailed description in the method example is given, and details are not repeated here.

In a seventh aspect, an embodiment of the present application further provides a computing device, where the computing device includes a processor and a memory, and may further include a communication interface, where the processor executes program instructions in the memory to perform the method provided in the first aspect or any possible implementation manner of the first aspect, and the processor may also execute program instructions in the memory to perform the method provided in any possible implementation manner of the second aspect or the second aspect. The processor may also execute the program instructions in the memory to perform the method provided in any of the third aspect or the third possible implementation manner of the above third aspect, the memory being coupled to the processor and storing the program instructions and data necessary for performing the data synchronization. The communication interface is used for communicating with other devices (such as client devices), such as acquiring images or videos from other devices.

In an eighth aspect, the present application provides a computing device system comprising at least one computing device. Each computing device includes a memory and a processor. A processor of at least one computing device may be configured to access the code in the memory to perform the method provided by the first aspect or any one of the possible implementations of the first aspect. The processor of the at least one computing device may be configured to access the code in the memory to perform the method provided by the second aspect or any one of the possible implementations of the second aspect. A processor of at least one computing device may be configured to access code in the memory to perform the method provided by the third aspect or any one of the possible implementations of the third aspect.

In a ninth aspect, the present application provides a non-transitory readable storage medium, which when executed by a computing device performs the method provided in the foregoing first aspect or any possible implementation manner of the first aspect, any possible implementation manner of the second aspect or the second aspect, or any possible implementation manner of the third aspect. The storage medium stores a program therein. The storage medium includes, but is not limited to, volatile memory such as random access memory, and non-volatile memory such as flash memory, Hard Disk Drive (HDD), and Solid State Drive (SSD).

In a tenth aspect, the present application provides a computing device program product comprising computer instructions that, when executed by a computing device, may perform the method as provided in the foregoing first aspect or any possible implementation manner of the first aspect, any possible implementation manner of the second aspect or the second aspect, or any possible implementation manner of the third aspect or the third aspect. The computer program product may be a software installation package, which may be downloaded and executed on a computing device in case it is required to use the method provided in the aforementioned first aspect or any possible implementation of the first aspect, any possible implementation of the second aspect or the second aspect, or any possible implementation of the third aspect or the third aspect.

Drawings

FIG. 1 is a block diagram of a system according to the present application;

FIG. 2 is a schematic diagram of another system configuration provided herein;

FIG. 3 is a schematic diagram of another system configuration provided herein;

FIG. 4 is a schematic diagram of a vehicle detection method provided herein;

FIGS. 5A-5B are schematic diagrams of feedback information provided herein;

FIG. 6 is a schematic diagram of another vehicle detection method provided herein;

FIG. 7 is a schematic structural diagram of a synchronization apparatus provided in the present application;

FIG. 8 is a schematic diagram of a computing device provided by an embodiment of the present application;

fig. 9 is a schematic diagram of a computing device in a computing device system according to an embodiment of the present application.

Detailed Description

Fig. 1 shows a system architecture suitable for the embodiment of the present application, which includes a detection apparatus 100 and a client device 200.

The client device 200 may provide a video or an image to the detection apparatus 100, and the detection apparatus 100 performs the vehicle detection method provided by the embodiment of the application based on the video or the image provided by the client device 200 to determine the vehicle violation condition existing in the video or the image.

In the embodiment of the present application, the client device 200 may be a device with transceiving function, such as may be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water surface (such as a ship and the like); and may also be deployed in the air (e.g., airplanes, balloons, satellites, etc.). The client device 200 may be a mobile phone (mobile phone), a camera, a video camera, a monitoring apparatus, a tablet (pad), a notebook, a desktop, a kiosk, a set-top box, a Virtual Reality (VR) terminal, an Augmented Reality (AR) terminal, a wireless terminal in industrial control (industrial control), a wireless terminal in self driving (self driving), a terminal in transportation safety (transportation safety), a terminal in smart city (smart city), and the like. The client device 200 may also be a terminal dedicated to receiving images or videos, and the user may transmit the images or videos to the client device 200 in a wired or wireless manner to inquire about vehicle violations.

The detection device 100 may be a hardware device, such as: a server, a terminal computing device, etc., or a software device, specifically a set of software systems running on a hardware computing device. The position where the detection apparatus 100 is deployed is not limited in the embodiments of the present application. For example, as shown in fig. 2, the detection apparatus 100 may operate on a cloud computing device system (including at least one cloud computing device, such as a server, etc.), may also operate on an edge computing device system (including at least one edge computing device, such as a server, a desktop, etc.), and may also operate on various terminal computing devices, such as: notebook computers, personal desktop computers, and the like.

The detection apparatus 100 may also be logically configured by a plurality of parts, for example, the detection apparatus 100 may include a transmission unit, a determination unit, and an indication unit, and each component in the detection apparatus 100 may be respectively deployed in different systems or servers. For example, as shown in fig. 3, each part of the apparatus may operate in three environments, namely, a cloud computing device system, an edge computing device system, or a terminal computing device, respectively, or may operate in any two of the three environments. The cloud computing device system, the edge computing device system and the terminal computing device are connected through communication paths, and can communicate with each other and transmit data. The vehicle determination step method provided by the embodiment of the application is cooperatively executed by the combined parts of the detection device 100 operating in three environments (or any two of the three environments).

In the embodiment of the present application, the detection device processes an image or a video including a plurality of frame images in different manners, and the manner in which the detection device detects an image and a video will be described below.

The detection device detects an image.

A vehicle detection method provided in an embodiment of the present application is described below with reference to fig. 4. As shown in fig. 4, the method includes:

step 401: the detection apparatus 100 acquires an image.

The image may be sent to the detection device 100 by the client device 200 when it is determined that the violation vehicle in the image needs to be detected, or may be actively acquired by the detection device 100 from the client device 200.

For example, the client device 200 may periodically transmit a captured image or a stored image to the detection apparatus 100. For another example, the client device 200 may transmit a captured image or a stored image to the detection apparatus 100 under the trigger of the user.

For example, the detection apparatus 100 may periodically retrieve an image in the client device 200 and detect the image. For example, the detection apparatus 100 may acquire an image from the client device 200 at an early peak and a late peak in a day and detect the image.

Step 402: the detection apparatus 100 determines a vehicle from the image.

Step 403: the detection device 100 indicates a vehicle violation when it determines that the vehicle violates a violation element based on the image.

After acquiring the image, the detection device 100 can detect the image and detect the vehicle and the violation element in the image.

The detection apparatus 100 may perform rough detection, for example, only detecting the position of the vehicle in the image, when detecting the vehicle in the image. More detailed detection can also be performed, and in addition to detecting the position of the vehicle in the image, vehicle information of the vehicle, such as a license plate, the color of the license plate, the model of the vehicle, the color of the vehicle, and the like, can also be detected.

When detecting a vehicle in an image, the detection apparatus 100 may detect all vehicles appearing in the image, or may detect only some vehicles. For example, the detection device 100 may detect only vehicles whose license plates appear in the image as yellow, blue, and green, and ignore vehicles whose license plates appear in the image as white and black.

The types of the violation elements are various, and the violation elements can be divided into forbidden marking lines and forbidden marks according to the shapes of the violation elements.

The stopping-prohibition marked lines are line types drawn on the road surface and the road edge (such as a road tooth), and include but are not limited to: the traffic light comprises a yellow solid line, a sidewalk, a zebra crossing, a no-stop line (such as a yellow grid line), a yellow dotted line (such as a yellow short line or a yellow and black interval line), and a diversion line (such as a white oblique line). The embodiment of the application does not limit the specific shape of the parking forbidding marked line, and all linear lines capable of indicating the parking forbidding can be used as the parking forbidding marked line.

The stop prohibition signs are signs standing on the road surface and comprise long-time stop prohibition signs and short-time stop prohibition signs. Besides the common blue bottom stop prohibition signs, in some places, other kinds of stop prohibition signs are allowed to be adopted, such as text signs, and the text content is the prohibition of parking. The specific type of the parking prohibition sign is not limited in the embodiment of the application, and all signs capable of indicating that parking is prohibited can be used as the parking prohibition signs.

The detection device 100 can determine whether a violation element is violated based on the location of the vehicle in the image. Two ways of determining whether a violation element is violated based on the position of the vehicle in the image are described below.

First, the detection apparatus 100 can determine whether the vehicle in the image has an obstruction to the no-stop marking (yellow solid line, sidewalk, zebra crossing, no-stop line, yellow dotted line, yellow grid, diversion line). If the vehicle stops beside the solid yellow line or the dashed yellow line, the vehicle in the image blocks part of the solid yellow line or the dashed yellow line. And if the vehicle is stopped on the sidewalk, the zebra crossing, the no-stop line or the diversion line, the vehicle blocks the sidewalk, the zebra crossing, the no-stop line or the diversion line in the image. If the vehicle in the image has shelter from the stopping marking, the vehicle violates the violation element.

The detection apparatus 100 may also detect whether the distance between the vehicle in the image and the parking prohibition flag (or the parking prohibition marking) is smaller than a threshold value, and if the distance between the vehicle in the image and the parking prohibition flag (or the parking prohibition marking) is smaller than a certain value, the vehicle violates the violation element. The embodiment of the present application does not limit the specific value of the threshold, and may be an empirical value. The parking prohibition sign is set at a position, so that parking is generally required to be prohibited in a certain area, and if the parking prohibition sign and the vehicle appear simultaneously in the same picture, it indicates that the vehicle is parked in the area where parking is prohibited. In order to improve the detection efficiency, the detection device 100 may determine the violation element of the vehicle in the image after detecting that the parking prohibition flag is present in the image.

In the second mode, the detection device 100 may determine whether the violation element is violated based on the position of the vehicle in the image based on the no-parking area.

The detection device 100 may determine the parking forbidding area based on the violation element after detecting the violation element in the image. For the stop-prohibiting marked lines, the stop-prohibiting area corresponding to the stop-prohibiting marked lines may be the road surface area marked by the stop-prohibiting marked lines, for example, the stop-prohibiting area corresponding to the yellow solid line (or the yellow dotted line) is the whole road surface area from the start position of the yellow solid line (or the yellow dotted line) to the end position of the yellow solid line (or the yellow dotted line). The non-stop area corresponding to the non-stop marking line such as the sidewalk, the zebra crossing, the non-stop line or the diversion line is the area covered by the non-stop marking line. For the stop-forbidden mark, the stop-forbidden area corresponding to the stop-forbidden mark may be an area which is less than a set value (e.g. 200 m) from the stop-forbidden mark, or may be a specific area to which the position of the stop-forbidden mark belongs. For example, when the parking prohibition flag is set at the entrance of a shop, the area of the entrance of the shop is the parking prohibition area.

After determining the no-parking area, the detection apparatus 100 may determine whether the vehicle in the image is located in the no-parking area, or whether a part of the vehicle is located in the no-parking area. If the vehicle is located in the no-parking area or a part of the vehicle is located in the no-parking area, the detection apparatus 100 determines that the vehicle is a vehicle violating the violation element, otherwise, the vehicle does not violate the violation element.

The detection device 100 may issue an indication of a vehicle violation upon determining that the vehicle in the image violates the violation element. The detection device 100 may display the instruction on a display screen of the detection device 100, or play the instruction in a voice manner, and the detection device 100 may also feed the instruction back to the client device 200 as violation information.

Optionally, the violation information may further include vehicle information of a vehicle violating the violation element, for example, the violation information may carry information such as a license plate of the vehicle, a model of the vehicle, and the like.

After receiving the violation message, the client device 200 may display the violation information in the form of text, voice, or picture.

Of course, the detection device 100 may also issue an indication that the vehicle does not violate the violation element after determining that the vehicle in the image does not violate the violation element, and similar to the indication that the vehicle violates, the detection device 100 may display the indication on a display screen of the detection device 100 itself, may play the indication in a voice manner, or may feed back the indication as violation information to the client device 200.

When the detection device 100 cannot determine whether the vehicle in the image violates the violation element, the detection device 100 may issue an indication that the detection is unsuccessful, and similar to the indication that the vehicle violates the violation, the detection device 100 may display the indication on a display screen of the detection device 100, may play the indication in a voice manner, or may feed the indication back to the client device 200 as feedback information, so that the user may obtain the feedback information through the client device 200 to re-photograph the image or record the image.

There are many situations where the detection device 100 cannot determine whether the vehicle in the image violates the violation element, for example, the image itself is unclear, the position of the vehicle and the violation element in the image is not easily identified, and there is a shelter in front of the vehicle in the image. The detection apparatus 100, when issuing the indication that the detection is unsuccessful, may also indicate the reason for the unsuccessful detection, such as the unsuccessful detection due to the unclear image itself.

In the embodiment of the present application, an image in which the detection apparatus 100 can successfully detect that the vehicle in the image violates the violation element or that the vehicle in the image does not violate the violation element may be referred to as a positive. The image in which the detection device 100 cannot accurately detect whether the vehicle in the image violates the violation element is called a scrap. The detection device 100 may also indicate that the image is a positive when sending the violation message to the client device 200, and may also indicate that the image is a waste when the detection device 100 sends the feedback message to the client device 200.

As shown in fig. 5A, which is a schematic diagram of violation information, the image on the left side in fig. 5A is shown as a positive, and violation elements detected in the image are displayed, and the definition of each violation element in the image is marked with different colors. And the vehicle violating the violation event is marked with a linear box in the image.

As shown in fig. 5B, which is a schematic diagram of violation information, the image on the left side in fig. 5B is shown as a waste film, and violation elements which can be detected in the image are displayed, and the definition of each violation element in the image and the content which needs to be further audited are marked with different colors. These contents requiring further review, which can be understood as the reason for unsuccessful detection, can effectively prompt the user to take or enter a clearer image again, and the client device 200 sends the image again to the detection apparatus 100 so that the detection apparatus 100 continues to perform detection.

(II), the detection device 100 detects the video.

A vehicle detection method provided in an embodiment of the present application is described below with reference to fig. 6. As shown in fig. 6, the method includes:

step 601: the detection apparatus 100 acquires a video. The manner of acquiring the video by the detection apparatus 100 is similar to the manner of acquiring the image by the detection apparatus 100 in the embodiment shown in fig. 4, and is not described herein again.

Step 602: the detection apparatus 100 determines the vehicle from the consecutive multiple frames of images in the video. The detection apparatus 100 may detect the vehicle in each of the consecutive multi-frame images, respectively. The detection apparatus 100 may also detect a vehicle in a part of the frames of the images (e.g., detect only one frame of the image) of the frames of the images, and then determine the position of the vehicle in the remaining frames of the images of the frames of the images. The manner of detecting the vehicle in one frame of image by the detection apparatus 100 is similar to the manner of detecting the vehicle in the image by the detection apparatus 100 in the embodiment shown in fig. 4, and reference may be made to the foregoing specifically, and details are not repeated here.

Step 603: the detection device 100 indicates a vehicle violation upon determining that the vehicle violates a violation element based on each of the plurality of images. The description of the violation elements can be found in the foregoing and will not be repeated here.

And if each frame of image in the plurality of frames of images determines that the same vehicle violates the same violation element, the vehicle violates the rule. The detection device 100 may detect the multiple frames of images, determine the same vehicle in each frame of image, then determine whether the vehicle violates the same violation element in each frame of image based on the violation element, and if so, the vehicle violates the violation. The detection device 100 may detect the multi-frame image, identify the stationary vehicle in the multi-frame image, identify the stationary vehicle violating the violation element based on the violation element, and if the violation element is violated, violate the vehicle.

It should be noted that the multi-frame image detected by the detection apparatus 100 may be a part of consecutive image frames in the video, or may be all image frames included in the video.

If each frame of the plurality of frames of images determines that the same vehicle violates a different violation element, the detection device 100 may further determine whether the vehicle actually violates the violation element. The detection device 100 may first determine whether the vehicle is a stationary vehicle, and after determining that the vehicle is a stationary vehicle, determine whether the vehicle violates the violation element, and the manner in which the detection device 100 determines the stationary vehicle and determines whether the stationary vehicle violates the violation element may be referred to as described later.

In the process of shooting the video, the running vehicle and the stationary vehicle are shot, and the running vehicle usually passes through the violation element or the violation area soon and does not violate the rule, so that the detection apparatus 100 needs to distinguish the running vehicle and the stationary vehicle in the multi-frame image in the video when executing step 602, and then determine whether the stationary vehicle violates the violation element.

There are many ways in which the detection device 100 determines a stationary vehicle and a traveling vehicle, and the embodiment of the present application does not limit the way in which the detection device 100 determines a stationary vehicle or a traveling vehicle.

For example, the detection device 100 may track the position of the vehicle in each frame image by using a tracking algorithm, and distinguish between a traveling vehicle and a stationary vehicle according to the position of the vehicle. The running vehicle is a vehicle whose vehicle position is constantly changed in the multi-frame images in the video, and the stationary vehicle is a vehicle whose vehicle position is not changed in the multi-frame images in the video.

It should be noted that, for some vehicles, there may be a case where the position in a part of image frames (two or more image frames) in a plurality of image frames is not changed, and the position in the part of image frames is changed, and the vehicle may be regarded as a stationary vehicle.

For another example, the detection apparatus 100 may determine the traveling vehicle and the stationary vehicle according to a time interval between the image frame in which the vehicle first appears and the image frame in which the vehicle last appears, where the vehicle with the time interval greater than the preset value is the stationary vehicle, and the vehicle with the time interval less than the preset value is the traveling vehicle.

The detection device 100 determines the stationary vehicles and the traveling vehicles, and can eliminate the traveling vehicles from the vehicles and keep the stationary vehicles. Thereafter, it is determined whether the stationary vehicle violates a violation element.

There are various ways in which the detection device 100 can determine whether a stationary vehicle violates a violation element, as described below:

in the first mode, the detection device 100 may determine whether the stationary vehicle blocks the parking prohibition marking, may determine whether the distance between the stationary vehicle and the parking prohibition marking is less than a certain value, and the detection device 100 may determine that the stationary vehicle violates the violation element after detecting that one of the plurality of images includes the stationary vehicle and the parking prohibition marking. This method is similar to the second method in the embodiment shown in fig. 4, and reference may be made to the foregoing specifically, and details are not repeated here.

In the second mode, the detection device 100 determines whether or not a violation element is violated based on the no-parking area and the position of the stationary vehicle. This method is similar to the second method in the embodiment shown in fig. 4, and reference may be made to the foregoing specifically, and details are not repeated here.

When the detection device 100 determines whether or not the violation element is violated from the position of the stationary vehicle based on the no-parking area, the no-parking area may be determined by the detection device 100 from the violation element in one image of the plurality of images, or may be predetermined by the detection device 100, and for example, the detection device 100 may acquire an image of a scene photographed by the video in advance, detect the violation element in the image, determine the no-parking area, and store information in the no-parking area. After receiving the video, the detection apparatus 100 may determine the no-stop area in each frame of image in the video according to the information of the no-stop area stored in advance.

And thirdly, the detection device 100 determines that the vehicle violates the violation element according to the violation element and the time interval between the first image frame and the last image frame of the static vehicle in the video.

For some violation elements, there are limits on the parking time of the vehicle, some violation elements allow the vehicle to park for a short time, and some violation elements do not allow the vehicle to park for a long time (e.g. yellow dotted line), and some violation elements do not allow the vehicle to park for a short time, and some violation elements do not allow the vehicle to park for a long time (e.g. no-parking line). That is, the detection device 100 needs to further confirm the time at which the vehicle violates the violation element, that is, the stationary time period of the stationary vehicle.

In practical applications, the third mode may be combined with the first mode or the second mode, that is, the detection apparatus 100 may determine the candidate vehicle violating the violation element by means of the first mode or the second mode, then determine whether the time interval between the first image frame and the last image frame of the vehicle in the video is greater than a threshold value, and determine that the vehicle violates the violation element after determining that the time interval is greater than the threshold value.

Based on the same inventive concept as the method embodiment, the embodiment of the present application further provides a detection apparatus, which is configured to perform the method performed by the detection apparatus 100 in the method embodiment shown in fig. 4. As shown in fig. 7, the detection apparatus 700 includes a transmission unit 701, a determination unit 702, and an indication unit 703, and the foregoing modules may be software modules. Specifically, in the detection apparatus 700, the units are connected to each other through a communication path.

A transmission unit 701 for acquiring an image; the transmitting unit 701 may perform step 401 as shown in fig. 4.

A determination unit 702 for determining a vehicle from the image; and determining a violation element for the vehicle based on the image; the determination unit 702 may perform the method of determining a violation element for a vehicle as shown in step 402 and step 403 of fig. 4.

An indicating unit 703 for indicating a violation of the vehicle when the determining unit 702 determines that the vehicle violates the violation element based on the image, and the indicating unit 703 may perform the method of indicating a violation of the vehicle in step 403 as shown in fig. 4.

As a possible embodiment, the determining unit 702 is further configured to obtain vehicle information of the vehicle from the image when the vehicle is determined from the image, and the transmission unit 701 may feed back violation information when the determining unit 702 is determining that the vehicle violates the violation element, the violation information including the vehicle information of the vehicle, the violation information indicating the vehicle violation.

As a possible embodiment, the violation elements include some or all of the following:

the device comprises a yellow solid line, a sidewalk, a zebra crossing, a no-stop line, a no-stop sign, a yellow dotted line and a diversion line.

As a possible embodiment, the determination unit 702 may detect the violation element in the image first when determining that the vehicle violates the violation element based on the image; and then determining the vehicle in the image that violates the violation element.

As a possible embodiment, when determining that there is a vehicle violating the violation element in the image, the determining unit 702 may also determine the violation vehicle according to the no-parking area, for example, the determining unit 702 may determine the no-parking area according to the violation element; and then, taking the vehicles in the forbidden stop area as the vehicles violating the violation elements.

Based on the same inventive concept as the method embodiment, the embodiment of the present application further provides a detection apparatus, which is configured to perform the method performed by the detection apparatus 100 in the method embodiment shown in fig. 6. The detection apparatus is similar to the detection apparatus of fig. 7, and referring to fig. 7, the detection apparatus 700 includes a transmission unit 701, a determination unit 702, and an indication unit 703, which may be software modules. Specifically, in the detection apparatus 700, the units are connected to each other through a communication path.

A transmission unit 701 for acquiring a video; the transmitting unit 701 may perform step 601 as shown in fig. 6.

A determination unit 702 configured to determine a vehicle from consecutive multi-frame images in the video; determining that the vehicle violates the violation elements based on each frame of image in the plurality of frames of images; the determination unit 702 may perform the method of determining a violation element for a vehicle as shown in step 602 and step 603 of fig. 6.

And an indicating unit 703 for indicating the violation of the vehicle when the determining unit 702 determines that the vehicle violates the violation element based on each of the frames of images. The indication unit 703 may perform the method of indicating a vehicle violation as in step 603 shown in fig. 6.

As a possible embodiment, the determination unit 702 may determine that the vehicle violates the same violation element based on the violation element and each of the images of the plurality of images when determining that the vehicle violates the violation element based on the violation element and each of the images of the plurality of images.

As a possible embodiment, when determining a vehicle from the multiple images, the determining unit 702 may further obtain vehicle information of the vehicle from the images; when the determination unit 702 determines that the vehicle violates the violation element, the transmission unit 701 may feed back violation information including vehicle information of the vehicle, the violation information indicating the vehicle violation.

As one possible embodiment, the determination unit 702, when determining the vehicle from the plurality of images, may determine the traveling vehicle and the stationary vehicle based on the position of the vehicle in the plurality of images; and (5) removing the running vehicles in the vehicles and keeping the static vehicles.

As a possible embodiment, the determining unit 702 may detect the violation element of the multi-frame image when it is determined that the vehicle violates the violation element based on each frame image of the multi-frame images; thereafter, a stationary vehicle is determined that violates the violation element.

As a possible embodiment, when it is determined that the vehicle violates the violation element based on each of the plurality of frames of images, the determination unit 702 may determine that the vehicle violates the violation element based on each of the plurality of frames of images in both of a first-appearing frame of images and a last-appearing frame of images of the plurality of frames of images, where a time interval between the first-appearing frame of images and the last-appearing frame of images is greater than a threshold value.

As a possible embodiment, when determining that the vehicle violates the violation element based on each frame of image in the multiple frames of images, the determining unit 702 may determine the forbidden area in the multiple frames of images according to the violation element in the multiple frames of images; the stationary vehicles in the no-go zone are treated as vehicles violating the violation elements.

The division of the modules in the embodiments of the present application is schematic, and only one logic function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, may also exist alone physically, or may also be integrated in one module by two or more modules. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a terminal device (which may be a personal computer, a mobile phone, or a network device) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Such as computing device 800 shown in fig. 8. The computing device 800 includes a bus 801, a processor 802, a communication interface 803, and a memory 804. The processor 802, memory 804, and communication interface 803 communicate over a bus 801.

The processor 802 may be a Central Processing Unit (CPU). The memory 804 may include volatile memory (volatile memory), such as Random Access Memory (RAM). The memory 804 may also include a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, an HDD, or an SSD. The memory has stored therein executable code that the processor 802 executes to perform the aforementioned vehicle detection method (e.g., the method shown in fig. 4 or 6). The memory 804 may also include other software modules required to run processes, such as an operating system. The operating system may be LINUX^TM,UNIX^TM,WINDOWS^TMAnd the like.

Specifically, the memory 804 stores the modules of the detection apparatus 700. The memory 804 may include, in addition to the aforementioned modules, other software modules required for running processes, such as an operating system. The operating system may be LINUX^TM,UNIX^TM,WINDOWS^TMAnd the like.

The present application also provides a computing device system that includes at least one computing device 900 as shown in fig. 9. The computing device 900 includes a bus 901, a processor 902, a communication interface 903, and a memory 904. The processor 902, memory 904, and communication interface 903 communicate over a bus 901. At least one computing device 900 in the system of computing devices communicates with each other via a communication path.

The processor 902 may be a CPU. The memory 904 may include volatile memory, such as random access memory. The memory 904 may also include a non-volatile memory, such as a read-only memory, a flash memory, an HDD, or an SSD. The memory 904 has stored therein executable code that the processor 902 executes to perform any or all of the aforementioned methods of data synchronization. The memory may also include other software modules required to run processes, such as an operating system. The operating system may be LINUX, UNIX, WINDOWS^TMAnd the like.

Specifically, the memory 904 stores any one or a plurality of modules of the detection apparatus 700. The memory 904 may include, in addition to any one or more of the elements described above, other software modules required to run a process, such as an operating system. The operating system may be LINUX, UNIX, WINDOWS^TMAnd the like.

At least one computing device 900 in the computing device system, on each of which any one or any plurality of elements of the detection apparatus 700 are running, establishes communication with each other via a communication network. The at least one computing device 900 collectively performs the aforementioned vehicle detection operations.

The descriptions of the flows corresponding to the above-mentioned figures have respective emphasis, and for parts not described in detail in a certain flow, reference may be made to the related descriptions of other flows.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product for data synchronization comprises one or more computer program instructions for data synchronization which, when loaded and executed on a computer, cause, in whole or in part, the flow or function of data synchronization according to embodiments of the invention.

The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, from one website, computer, server, or data center over a wired (e.g., coaxial, fiber, digital subscriber line, or wireless (e.g., infrared, wireless, microwave, etc.) link to another website, computer, server, or data center. (e.g., floppy disk, hard disk, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., SSD).

Claims

1. A vehicle detection method, characterized in that the method comprises:

acquiring an image;

determining a vehicle from the image;

upon determining that the vehicle violates a violation element based on the image, indicating the vehicle violation.

2. The method of claim 1, wherein the method comprises:

acquiring vehicle information of a vehicle from the image;

and feeding back violation information, wherein the violation information comprises vehicle information of the vehicle, and the violation information indicates that the vehicle violates.

3. The method of claim 1 or 2 wherein the violation elements include some or all of the following:

4. The method of any of claims 1 to 3, wherein said determining the vehicle violation event based on the image comprises:

detecting violation elements in the image;

a vehicle in the image violating the violation elements is determined.

5. The method of claim 4 wherein said determining that a vehicle violating said violation element is present in said image comprises:

determining the no-parking area according to the violation elements;

and using the vehicle in the no-parking area as the vehicle violating the violation element.

6. A vehicle detection method, characterized in that the method comprises:

acquiring a video;

determining a vehicle from a plurality of continuous frames of images in the video;

indicating the vehicle violation upon determining that the vehicle violates a violation element based on each of the plurality of images.

7. The method of claim 6 wherein said determining said vehicle violation element based on said violation element and each of said plurality of images comprises:

determining that the vehicle violates the same violation element in the plurality of images based on the violation element and each of the plurality of images.

8. The method of claim 6 or 7, wherein the method comprises:

acquiring vehicle information of a vehicle from the image;

9. The method of any one of claims 6 to 8 wherein the violation elements include some or all of the following:

10. The method of any one of claims 6 to 9, wherein said determining a vehicle from said plurality of frames of images comprises:

determining a running vehicle and a static vehicle shot by the multi-frame images based on the positions of the vehicles in the multi-frame images;

and removing the running vehicles in the vehicles and keeping the static vehicles.

11. The method of claim 10 wherein said determining that the vehicle violates a violation element based on each of the plurality of images comprises:

detecting violation elements of at least one frame of image in the multiple frames of images;

a stationary vehicle is determined that violates the violation element.

12. The method of any of claims 6-10, wherein the determining that the vehicle violates a violation element based on each of the plurality of images comprises:

and determining that the vehicle violates the violation element in both the first-appearing frame image and the last-appearing frame image of the plurality of frame images based on each frame image of the plurality of frame images, wherein the time interval between the first-appearing frame image and the last-appearing frame image is greater than a threshold value.

13. The method of any of claims 6-10, wherein determining the vehicle violation element based on each of the plurality of images comprises:

determining a forbidden stop area in the multi-frame image according to the violation elements in the multi-frame image;

and using the stationary vehicle in the no-parking area as the vehicle violating the violation element.

14. A detection device is characterized by comprising a transmission unit, a determination unit and an indication unit;

the transmission unit is used for acquiring an image;

the determining unit is used for determining a vehicle from the image; and determining the vehicle violation element based on the image;

the indicating unit is used for indicating the vehicle violation when the determining unit determines that the vehicle violates the violation element based on the image.

15. The apparatus of claim 14,

the determining unit is further used for acquiring vehicle information of the vehicle from the image;

the transmission unit is used for feeding back violation information, the violation information comprises vehicle information of the vehicle, and the violation information indicates that the vehicle violates rules.

16. The apparatus of claim 14 or 15 wherein the violation elements include some or all of the following:

17. The apparatus of any of claims 14 to 16, wherein the determining unit, when determining the vehicle violation element based on the image, is specifically configured to:

detecting violation elements in the image;

a vehicle in the image violating the violation elements is determined.

18. The apparatus of claim 17, wherein the determination unit, upon determining that a vehicle violating the violation element is present in the image, is specifically configured to:

determining the no-parking area according to the violation elements;

and taking the vehicle in the no-parking area as the vehicle violating the violation element.

19. A detection device is characterized by comprising a transmission unit, a determination unit and an indication unit:

the transmission unit is used for acquiring a video;

the determining unit is used for determining a vehicle from continuous multi-frame images in the video; and determining that the vehicle violates a violation element based on each of the plurality of images;

the indicating unit is used for indicating the vehicle violation when the determining unit determines that the vehicle violates the violation element based on each frame image in the plurality of frame images.

20. The apparatus of claim 19, wherein said determining unit, when determining the vehicle violation element based on the violation element and each of the plurality of images, is specifically configured to:

determining, based on the violation element and each of the plurality of images, that the vehicle violates the same violation element in the plurality of images.

21. The apparatus of claim 19 or 20,

the transmission unit is further used for feeding back violation information, the violation information comprises vehicle information of the vehicle, and the violation information indicates that the vehicle violates rules.

22. The apparatus of any one of claims 19 to 21 wherein the violation elements include some or all of:

23. The apparatus according to any one of claims 19 to 22, wherein the determining unit, when determining the vehicle from the plurality of frame images, is specifically configured to:

24. The apparatus as recited in claim 23, wherein said determining unit, when determining that the vehicle violates a violation element based on each of said plurality of images, is specifically configured to:

a stationary vehicle is determined that violates the violation element.

25. The apparatus of any of claims 19 to 23, wherein the determining unit, when determining that the vehicle violates a violation element based on each of the plurality of images, is specifically configured to:

26. The apparatus of any of claims 19 to 23, wherein the determining unit, when determining the violation element for the vehicle based on each of the plurality of images, is specifically configured to:

and taking the static vehicle in the no-parking area as the vehicle violating the violation element.

27. A computing device, wherein the computing device comprises a processor and a memory;

the memory to store computer program instructions;

the processor invokes computer program instructions in the memory to perform the method of any of claims 1-13.