WO2018068317A1

WO2018068317A1 - Vehicle wrong-way detection apparatus and method, and electronic device

Info

Publication number: WO2018068317A1
Application number: PCT/CN2016/102168
Authority: WO
Inventors: 杨雅文; 王琪
Original assignee: 富士通株式会社; 杨雅文
Priority date: 2016-10-14
Filing date: 2016-10-14
Publication date: 2018-04-19
Also published as: JP2019532431A; CN109661667A

Abstract

A vehicle wrong-way detection apparatus (100) and method, and an electronic device. According to the apparatus and method, a vehicle trajectory set is established and a vehicle trajectory therein is detected, and it is determined whether each vehicle trajectory is oriented the wrong way according to a proportion, in each vehicle trajectory, of the number of vehicle wrong-way occurrences detected in each image frame to the total number of times of the vehicle being detected, and according to the vector direction of the vehicle trajectory. In the invention, the calculation process is relatively simple, and higher detection accuracy can be obtained.

Description

Vehicle retrograde detecting device and method, electronic device

Technical field

The present invention relates to the field of information technology, and in particular, to a vehicle retrograde detecting apparatus and method, and an electronic device.

Background technique

With the continuous advancement of urbanization, video surveillance is widely used. Compared with traditional manual monitoring, intelligent monitoring systems have many advantages, such as continuous monitoring throughout the day, low cost and protection of personal information. The detection of traffic violations by intelligent monitoring systems and notification to traffic managers or warning of vehicle drivers can reduce and avoid traffic accidents.

Vehicle retrograde is a common traffic violation, which is harmful and easily causes traffic accidents. Existing vehicle retrograde detection methods generally use a Gaussian background detection algorithm to determine which part of the image is the target vehicle, and then use the mean shift and Harris Corner features to track and determine the direction of travel of the vehicle.

It should be noted that the above description of the technical background is only for the purpose of facilitating a clear and complete description of the technical solutions of the present invention, and is convenient for understanding by those skilled in the art. The above technical solutions are not considered to be well known to those skilled in the art simply because these aspects are set forth in the background section of the present invention.

Summary of the invention

The calculation process of the above existing detection methods is complicated, and the detection accuracy is low.

Embodiments of the present invention provide a vehicle retrograde detecting apparatus and method, and an electronic device. By establishing a vehicle trajectory set and detecting a vehicle trajectory therein, the number of times the vehicle is retrograde is detected in each frame image according to each vehicle trajectory, and the detected vehicle is detected. The ratio of the total number of times and the vector direction of the vehicle trajectory determine whether each vehicle trajectory is retrograde, the calculation process is relatively simple, and high detection accuracy can be obtained.

According to a first aspect of the present invention, there is provided a vehicle retrograde detecting apparatus, wherein the apparatus is configured to detect each frame image of a surveillance video frame by frame, the apparatus comprising: a first detecting unit, configured to detect a current a traveling vehicle in the frame image; an establishing unit for establishing a vehicle track set of the current frame image based on the detected traveling vehicle in the current frame image; a second detecting unit for the vehicle for the current frame image Vehicle trajectories that are not determined to be retrograde in the trajectory set are detected one by one, and the trajectory of the vehicle that satisfies the preset condition is determined as retrograde Vehicle trajectory, wherein the preset condition includes: detecting, in the current frame image and all previous frame images, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction in the vehicle trajectory that is not determined to be retrograde and detecting the The ratio of the total number of times the traveling direction of the vehicle is greater than the first threshold, and the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction.

According to a second aspect of an embodiment of the present invention, there is provided an electronic device comprising the apparatus according to the first aspect of the embodiments of the present invention.

According to a third aspect of the present invention, there is provided a vehicle retrograde detection method, the method for detecting each frame image of a surveillance video frame by frame, the method comprising: detecting a traveling vehicle in a current frame image; Detecting the traveling vehicle in the current frame image, establishing a vehicle trajectory set of the current frame image; detecting, for the vehicle trajectory of the current frame image, the vehicle trajectory not determined to be retrograde, detecting the vehicle trajectory satisfying the preset condition Determining a vehicle trajectory that is retrograde, wherein the preset condition includes: detecting, in the vehicle trajectory that is not determined to be retrograde, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction in the current frame image and all previous frame images The ratio of the total number of times of detecting the traveling direction of the vehicle is greater than the first threshold, and the vector direction of the vehicle trajectory not determined to be retrograde is opposite to the normal traveling direction.

The invention has the beneficial effects of detecting the vehicle trajectory set and detecting the vehicle trajectory therein, detecting the ratio of the number of times the vehicle is retrograde to the total number of detected vehicles and the vector direction of the vehicle trajectory in each frame image according to each vehicle trajectory. To determine whether each vehicle trajectory is retrograde, the calculation process is relatively simple, and high detection accuracy can be obtained.

Specific embodiments of the present invention are disclosed in detail with reference to the following description and the drawings, in which <RTIgt; It should be understood that the embodiments of the invention are not limited in scope. The embodiments of the present invention include many variations, modifications, and equivalents within the scope of the appended claims.

Features described and/or illustrated with respect to one embodiment may be used in one or more other embodiments in the same or similar manner, in combination with, or in place of, features in other embodiments. .

It should be emphasized that the term "comprising" or "comprises" or "comprising" or "comprising" or "comprising" or "comprising" or "comprises"

DRAWINGS

The drawings are included to provide a further understanding of the embodiments of the invention, which constitute a part of the specification The embodiments are illustrated to illustrate the principles of the invention, together with the written description. Obviously, the drawings in the following description are only some of the embodiments of the present invention, and those skilled in the art can obtain other drawings according to the drawings without any inventive labor. In the drawing:

1 is a schematic diagram of a vehicle retrograde detecting device according to Embodiment 1 of the present invention;

2 is a schematic diagram of an establishing unit 102 according to Embodiment 1 of the present invention;

Figure 3 is a schematic diagram of a vehicle trajectory according to Embodiment 1 of the present invention;

4 is a schematic diagram of an electronic device according to Embodiment 2 of the present invention;

Figure 5 is a schematic block diagram showing the system configuration of an electronic device according to Embodiment 2 of the present invention;

Fig. 6 is a schematic diagram of a vehicle retrograde detecting method according to a third embodiment of the present invention.

detailed description

The foregoing and other features of the present invention will be apparent from the The specific embodiments of the present invention are disclosed in the specification and the drawings, which are illustrated in the embodiment of the invention The invention includes all modifications, variations and equivalents falling within the scope of the appended claims.

Example 1

Embodiments of the present invention provide a vehicle retrograde detection apparatus, which is configured to detect each frame image of a surveillance video frame by frame. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a view showing a vehicle retrograde detecting device according to a first embodiment of the present invention. As shown in FIG. 1, the device 100 includes:

a first detecting unit 101, configured to detect a traveling vehicle in the current frame image;

An establishing unit 102, configured to establish a vehicle track set of the current frame image according to the detected traveling vehicle in the current frame image;

a second detecting unit 103, configured to detect the vehicle trajectory that is not determined to be retrograde for the vehicle trajectory set of the current frame image, and determine a vehicle trajectory that meets the preset condition as a retrograde vehicle trajectory, wherein the preset condition The ratio of the number of times that the traveling direction of the vehicle is opposite to the normal traveling direction and the total number of times of detecting the traveling direction of the vehicle in the current frame image and all previous frame images in the vehicle trajectory that is not determined to be retrograde is greater than the first threshold. The vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction.

It can be seen from the above embodiment that by establishing a vehicle trajectory set and detecting the vehicle trajectory therein, according to each The vehicle trajectory detects the ratio of the number of vehicle retrogrades to the total number of detected vehicles and the vector direction of the vehicle trajectory in each frame image, determines whether each vehicle trajectory is retrograde, the calculation process is relatively simple, and high detection accuracy can be obtained. .

In this embodiment, the surveillance video can be obtained according to existing methods. For example, it can be obtained by installing a camera above the area to be monitored.

In this embodiment, each frame image of the surveillance video may include consecutive multi-frame images in the surveillance video for a period of time, and each frame image is detected frame by frame.

In the present embodiment, the first detecting unit 101 can detect the traveling vehicle in the current frame image using the classifier, and thus, by using the classifier to detect the traveling vehicle, the Gaussian background detection algorithm used in the existing retrograde detecting method is compared. The use of the classifier can effectively improve the vehicle detection rate and prevent the vehicle from being missed.

In this embodiment, the classifier may be an existing type of classifier, for example, a Support Vector Machine (SVM) classifier, a Bayesian classifier, and the like.

In this embodiment, the entire current frame image may be detected, or a predetermined region in the current frame image may be detected, for example, only a Region of Interest (ROI) in the image is detected.

For example, if the current frame image contains only one-way lanes, the entire image can be detected. If the current frame image contains two-way or multi-directional lanes, the area where the one-way lane is located can be used as the ROI area and detected.

In this embodiment, the establishing unit 102 is configured to establish a vehicle track set of the current frame image according to the detected traveling vehicle in the current frame image. The structure of the establishing unit 102 of the present embodiment and the method of establishing a vehicle track set are exemplarily described below.

FIG. 2 is a schematic diagram of the establishing unit 102 of Embodiment 1 of the present invention. As shown in FIG. 2, the establishing unit 102 includes:

a first updating unit 201, configured to add the traveling vehicle to the vehicle trajectory when the detected traveling vehicle in the current frame image matches any one of the vehicle trajectories of the previous frame image;

a new unit 202, configured to: when the detected traveling vehicle in the current frame image does not match any of the vehicle trajectories in the vehicle trajectory of the previous frame image, create a new vehicle trajectory according to the traveling vehicle;

a second updating unit 203, configured to determine a current frame image according to an average speed of the vehicle and a normal driving direction when the vehicle in the vehicle trajectory that has been established in the vehicle trajectory set of the previous frame image is not detected in the current frame image The virtual target of the vehicle is added to the vehicle trajectory.

In this embodiment, a determining unit (not shown) is further configured to determine whether the detected vehicle in the current frame image matches any one of the vehicle trajectories in the vehicle trajectory of the previous frame image, for example, The determination may be made based on whether the detected predicted position of the traveling vehicle and the vehicle trajectory in the current frame image matches. Among them, the predicted position can be obtained according to an existing method.

In this embodiment, the second updating unit 203 is configured to: when the vehicle in the vehicle trajectory that has been established in the vehicle trajectory set of the previous frame image is not detected in the current frame image, according to the average speed of the vehicle and the normal traveling direction, A virtual target of the vehicle in the current frame image is determined and added to the vehicle trajectory. In this way, when the tracked vehicle is not detected in some frames, by determining the virtual target of the vehicle and adding it to the end of the vehicle trajectory, the continuity of the vehicle trajectory can be ensured, thereby effectively improving the vehicle tracking. Great.

In the present embodiment, for example, multiplying the average speed of the vehicle by the time interval between frames, the average displacement of the vehicle is obtained, and the average displacement of the vehicle traveling in the normal direction of travel detected in the previous frame is obtained. Is the location of the virtual target.

In the present embodiment, the average speed of the vehicle can be obtained by calculating the average speed of movement of the vehicle between frames according to the vehicle trajectory, and since the normal traveling direction of the single lane in the image is known, the normality of the vehicle The direction of travel should be consistent with the normal direction of travel of the lane.

In this embodiment, the size of the virtual target of the vehicle in the current frame image may be set to be the same as the size of the vehicle detected in the image of the previous frame.

In this embodiment, after the establishing unit 102 establishes the vehicle trajectory set of the current frame image, the second detecting unit 103 is configured to detect the vehicle trajectory that is not determined to be retrograde for the vehicle trajectory set of the current frame image, and the pre-preparation is satisfied. The conditional vehicle trajectory is determined as a retrograde vehicle trajectory.

In this embodiment, the preset condition includes: detecting, in the vehicle frame that is not retrograde, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction in the current frame image and all previous frame images, and detecting the driving of the vehicle. The ratio of the total number of directions is greater than the first threshold, and the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction.

In the present embodiment, the vector of the vehicle trajectory that is not determined to be retrograde is the displacement vector of the first vehicle to the last vehicle in the vehicle trajectory. Among them, the first vehicle is the first detected vehicle, and the last vehicle is the last detected vehicle.

In the present embodiment, the second detecting unit 103 arrives at the previous vehicle in the vehicle trajectory that is not determined to be retrograde When the vector direction of the adjacent next vehicle is opposite to the normal traveling direction, the number of times the traveling direction of the vehicle is detected to be opposite to the normal traveling direction is incremented by one.

For example, when the angle between the vector direction of the current vehicle and the adjacent one of the vehicles and the normal traveling direction is less than or equal to 90 degrees, the vector direction is considered to be the same as the normal traveling direction, and when the angle is greater than 90 degrees, the vector is considered as the vector. The direction is opposite to the normal driving direction. In the present embodiment, the same method can be used to determine whether the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction, and details are not described herein again.

In this embodiment, the first threshold may be set according to actual needs, for example, the first threshold is a value between 0.3 and 0.8.

The following is a specific description of the method for determining whether the preset condition is satisfied in the embodiment.

Figure 3 is a schematic illustration of a vehicle trajectory in accordance with a first embodiment of the present invention. As shown in FIG. 3, the vehicle trajectory 301 is a vehicle trajectory in which the vehicle trajectory set of the current frame image is not determined to be retrograde, and the target vehicle 302-1 of the head of the vehicle trajectory 301 is the first time in the current frame and all previous frame images. The detected vehicle, and so on, the target vehicles 302-2 to 302-7 are the same vehicle detected from the 2nd to the 7th, respectively, and the direction D is the normal traveling direction, and the vector of the vehicle trajectory 301 is FIG. The vector A in the middle is the displacement vector of the vehicle from the first vehicle to the last (last detected), and the vector of the previous vehicle to the next vehicle is, for example, the vector B in Fig. 3, which is the target The vector of the vehicle 302-1 to the target vehicle 302-2.

As shown in FIG. 3, the direction of the vector A is opposite to the normal traveling direction D, and the vector in which the vector direction of the preceding vehicle to the adjacent next vehicle is opposite to the normal traveling direction D includes: the target vehicle 302-1 to the target vehicle 302- Vector of 2, vector of target vehicle 302-2 to target vehicle 302-3, vector of target vehicle 302-4 to target vehicle 302-5, vector of target vehicle 302-6 to target vehicle 302-7, a total of 4 vectors The vector in which the vector direction of the previous vehicle to the adjacent next vehicle is the same as the normal traveling direction D includes: a vector of the target vehicle 302-3 to the target vehicle 302-4 and a target vehicle 302-5 to the target vehicle 302-6. Vector, a total of 2 vectors. Therefore, in the vehicle trajectory 301, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction is detected 4 times in the current frame image and all previous frame images, and the total number of times of detecting the traveling direction of the vehicle is 4+2=6 times. Then, the ratio of the number of times the traveling direction of the vehicle is opposite to the normal traveling direction and the total number of times of detecting the traveling direction of the vehicle in the current frame image and all previous frame images in the vehicle trajectory 301 is 4/6=0.67. For example, if the first threshold is set to 0.6, then, since the ratio is greater than the first threshold, and the direction of the vector A is opposite to the normal traveling direction D, the vehicle trajectory 301 satisfies the preset condition, thereby being determined as a retrograde vehicle trajectory. .

In this embodiment, the preset condition may further include: a vector of the vehicle trajectory that is not determined to be retrograde is in the The ratio of the projected length in the normal driving direction to the height of the last vehicle in the vehicle trajectory not determined to be retrograde is greater than the second threshold. That is, the preset condition includes: detecting, in the current frame image and all previous frame images, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction in the vehicle trajectory that is not determined to be retrograde, and detecting the traveling direction of the vehicle. The ratio of the total number of times is greater than the first threshold, and the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction, and the vector of the vehicle trajectory that is not determined to be retrograde in the normal traveling direction is not The ratio of the height of the last vehicle in the vehicle trajectory determined to be retrograde is greater than a second threshold.

Thus, by setting the condition of the length ratio, the accuracy of the detection can be further improved.

In this embodiment, the second threshold may be set according to actual needs. For example, the second threshold is a value between 1.8 and 2.8.

For example, in FIG. 3, the projection length of the vector A in the direction D, that is, the ratio of the projection length in the vertical direction to the height of the last vehicle 302-7 in the vehicle trajectory 301, is determined to determine whether the ratio is greater than the second. Threshold.

It can be seen from the above embodiment that by establishing the vehicle trajectory set and detecting the vehicle trajectory therein, the ratio of the number of times of vehicle retrograde to the total number of detected vehicles and the vector direction of the vehicle trajectory are detected in each frame image according to each vehicle trajectory. It is determined whether the trajectory of each vehicle is retrograde, the calculation process is relatively simple, and high detection accuracy can be obtained.

Example 2

An embodiment of the present invention further provides an electronic device, and FIG. 4 is a schematic diagram of the electronic device according to Embodiment 2 of the present invention. As shown in FIG. 4, the electronic device 400 includes a vehicle retrograde detecting device 401. The structure and function of the vehicle retrograde detecting device 401 are the same as those in the first embodiment, and are not described herein again.

Fig. 5 is a schematic block diagram showing the system configuration of an electronic apparatus according to a second embodiment of the present invention. As shown in FIG. 5, electronic device 500 can include central processor 501 and memory 502; memory 502 is coupled to central processor 501. The figure is exemplary; other types of structures may be used in addition to or in place of the structure to implement telecommunications functions or other functions.

As shown in FIG. 5, the electronic device 500 may further include an input unit 503, a display 504, and a power source 505.

In one embodiment, the functions of the vehicle retrograde detecting apparatus described in Embodiment 1 may be integrated into the central processing unit 501. For example, the central processing unit 501 can be configured to: detect a traveling vehicle in the current frame image; establish a vehicle trajectory set of the current frame image according to the detected traveling vehicle in the current frame image; The vehicle trajectory of the previous frame image in which the vehicle trajectory is not determined to be retrograde is detected one by one, and the vehicle trajectory that satisfies the preset condition is determined as a retrograde vehicle trajectory, wherein the preset condition includes: the predetermined condition is not determined as retrograde In the vehicle trajectory, the ratio of the number of times the traveling direction of the vehicle is opposite to the normal traveling direction and the total number of times the traveling direction of the vehicle is detected in the current frame image and all previous frame images is greater than a first threshold, and the said is not determined. The vector direction of the retrograde vehicle trajectory is opposite to the normal driving direction.

For example, the preset condition includes: detecting, in the vehicle trajectory that is not determined to be retrograde, the number of times the traveling direction of the vehicle is opposite to the normal traveling direction in the current frame image and all previous frame images, and detecting the traveling direction of the vehicle. The ratio of the total number of times is greater than the first threshold, the vector direction of the vehicle trajectory not determined to be retrograde is opposite to the normal traveling direction, and the vector of the vehicle trajectory not determined to be retrograde is in the normal traveling direction The ratio of the projected length to the height of the last vehicle in the vehicle trajectory that is not determined to be retrograde is greater than a second threshold.

For example, the vector of the vehicle trajectory that is not determined to be retrograde is the displacement vector of the first vehicle to the last vehicle in the vehicle trajectory.

For example, the vehicle trajectory of the vehicle trajectory set that is not determined to be retrograde for the current frame image is detected one by one, including: when the vehicle trajectory that is not determined to be retrograde, the previous vehicle to the adjacent one of the vehicles When the vector direction is opposite to the normal traveling direction, the number of times the traveling direction of the vehicle is detected to be opposite to the normal traveling direction is incremented by one.

For example, the establishing a vehicle trajectory set of the current frame image according to the detected traveling vehicle in the current frame image includes: when detecting the vehicle in the current frame image and the vehicle trajectory of the previous frame image is concentrated in any one of the vehicles When the trajectory is matched, the traveling vehicle is added to the vehicle trajectory; when the detected traveling vehicle in the current frame image does not match any of the vehicle trajectories in the vehicle trajectory of the previous frame image, a new one is created according to the traveling vehicle. Vehicle trajectory.

For example, the establishing a vehicle trajectory set of the current frame image according to the detected traveling vehicle in the current frame image further includes: in the vehicle trajectory that has been established in the vehicle trajectory set in which the previous frame image is not detected in the current frame image. The vehicle is determined based on the average speed of the vehicle and the normal traveling direction, and the virtual target of the vehicle in the current frame image is determined and added to the vehicle trajectory.

For example, the size of the virtual target of the vehicle in the current frame image is the same as the size of the vehicle detected in the previous frame image.

For example, the detecting the traveling vehicle in the current frame image includes: using a classifier to detect the current frame image Driving vehicle in the middle.

In another embodiment, the vehicle retrograde detecting device described in Embodiment 1 may be configured separately from the central processing unit 501. For example, the vehicle retrograde detecting device may be configured as a chip connected to the central processing unit 501 through the central processing unit 501. Control to realize the function of the vehicle retrograde detecting device.

It is also not necessary for the electronic device 500 to include all of the components shown in FIG. 5 in this embodiment.

As shown in FIG. 5, central processor 501, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device that receives input and controls various components of electronic device 500. Operation.

Memory 502, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable device. And the central processing unit 501 can execute the program stored in the memory 502 to implement information storage or processing and the like. The functions of other components are similar to those of the existing ones and will not be described here. The various components of electronic device 500 may be implemented by special purpose hardware, firmware, software, or a combination thereof without departing from the scope of the invention.

Example 3

The embodiment of the present invention further provides a vehicle retrograde detection method, which is used for detecting each frame image of a surveillance video frame by frame, which corresponds to the vehicle retrograde detection apparatus of Embodiment 1. Fig. 6 is a schematic diagram of a vehicle retrograde detecting method according to a third embodiment of the present invention. As shown in FIG. 6, the method includes:

Step 601: detecting a traveling vehicle in the current frame image;

Step 602: Establish a vehicle track set of the current frame image according to the detected traveling vehicle in the current frame image.

Step 603: The vehicle trajectory of the vehicle trajectory set that is not determined to be retrograde is detected one by one for the current frame image, and the vehicle trajectory that meets the preset condition is determined as a retrograde vehicle trajectory, wherein the preset condition includes: not determined as: The ratio of the number of times the traveling direction of the vehicle is opposite to the normal traveling direction and the total number of times the traveling direction of the vehicle is detected in the current frame image and all previous frame images in the retrograde vehicle trajectory is greater than the first threshold, and the determination is not determined. The vector direction of the retrograde vehicle trajectory is opposite to the normal driving direction.

In this embodiment, the specific implementation method of each step in steps 601-603 is the same as that in Embodiment 1, and details are not described herein again.

Embodiments of the present invention also provide a computer readable program, wherein the program causes a computer to perform an implementation in the vehicle retrograde detecting device or an electronic device when the program is executed in a vehicle retrograde detecting device or an electronic device The vehicle retrograde detection method described in Example 3.

The embodiment of the present invention further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to execute the vehicle retrograde detection method described in Embodiment 3 in a vehicle retrograde detecting device or an electronic device.

The method for performing vehicle retrograde detection in a vehicle retrograde detecting apparatus described in connection with the embodiments of the present invention may be directly embodied as hardware, a software module executed by a processor, or a combination of both. For example, one or more of the functional block diagrams shown in FIG. 1 and/or one or more combinations of functional block diagrams may correspond to various software modules of a computer program flow, or to individual hardware modules. These software modules may correspond to the respective steps shown in FIG. 6, respectively. These hardware modules can be implemented, for example, by curing these software modules using a Field Programmable Gate Array (FPGA).

The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor to enable the processor to read information from, and write information to, the storage medium; or the storage medium can be an integral part of the processor. The processor and the storage medium can be located in an ASIC. The software module can be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if a device (such as a mobile terminal) uses a larger capacity MEGA-SIM card or a large-capacity flash memory device, the software module can be stored in the MEGA-SIM card or a large-capacity flash memory device.

One or more of the functional blocks described with respect to FIG. 1 and/or one or more combinations of functional blocks may be implemented as a general purpose processor, digital signal processor (DSP), dedicated for performing the functions described herein. Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates or Transistor logic device, discrete hardware component, or any suitable combination thereof. One or more of the functional block diagrams described with respect to FIG. 1 and/or one or more combinations of functional block diagrams may also be implemented as a combination of computing devices, eg, a combination of a DSP and a microprocessor, a plurality of microprocessors, One or more microprocessors or any other such configuration in conjunction with DSP communication.

The present invention has been described in connection with the specific embodiments thereof, and it should be understood by those skilled in the art that A person skilled in the art can make various modifications and changes to the present invention within the scope of the present invention.

Claims

A vehicle retrograde detecting device, wherein the device is configured to detect each frame image of a surveillance video frame by frame, the device comprising:

a first detecting unit, configured to detect a traveling vehicle in the current frame image;

Establishing a unit for establishing a vehicle track set of the current frame image according to the detected traveling vehicle in the current frame image;

a second detecting unit, configured to detect, for the vehicle trajectory of the current frame image, a vehicle trajectory that is not determined to be retrograde, and determine a vehicle trajectory that meets a preset condition as a retrograde vehicle trajectory, wherein the pre-predetermined The condition includes: a ratio of the number of times the traveling direction of the vehicle is opposite to the normal traveling direction and the total number of times of detecting the traveling direction of the vehicle in the current frame image and all previous frame images in the vehicle trajectory that is not determined to be retrograde A vector direction that is greater than the first threshold and that is not determined to be retrograde is opposite to the normal direction of travel.
The device according to claim 1, wherein

The preset condition includes: a total number of times that the traveling direction of the vehicle is opposite to the normal traveling direction and the total traveling direction of the vehicle are detected in the current frame image and all previous frame images in the vehicle trajectory that is not determined to be retrograde The ratio of the number of times is greater than the first threshold, the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction, and the projection length of the vector of the vehicle trajectory that is not determined to be retrograde in the normal traveling direction The ratio of the height of the last vehicle in the vehicle trajectory that is not determined to be retrograde is greater than a second threshold.
The device according to claim 1, wherein

The vector of the vehicle trajectory that is not determined to be retrograde is the displacement vector of the first vehicle to the last vehicle in the vehicle trajectory.
The device according to claim 1, wherein

The second detecting unit is configured to detect the traveling direction of the vehicle and the normal driving when the vector direction of the previous vehicle to the adjacent one of the vehicle trajectories not determined to be retrograde is opposite to the normal traveling direction Add 1 to the opposite direction.
The apparatus of claim 1 wherein said establishing unit comprises:

a first updating unit for detecting a vehicle in a current frame image and a vehicle in a previous frame image Adding the traveling vehicle to the vehicle trajectory when any one of the trajectories in the trajectory is matched;

A new unit is configured to newly create a vehicle trajectory according to the traveling vehicle when the detected traveling vehicle in the current frame image does not match any of the vehicle trajectories in the vehicle trajectory of the previous frame image.
The apparatus of claim 5, wherein the establishing unit further comprises:

a second updating unit, configured to determine, in the current frame image, according to an average speed of the vehicle and a normal driving direction, when the vehicle in the vehicle trajectory that has been established in the vehicle trajectory set of the previous frame image is not detected in the current frame image The virtual target of the vehicle adds the virtual target to the vehicle trajectory.
The apparatus of claim 6, wherein the size of the virtual target of the vehicle in the current frame image is the same as the size of the vehicle detected in the previous frame image.
The apparatus according to claim 1, wherein the first detecting unit uses the classifier to detect the traveling vehicle in the current frame image.
An electronic device comprising the apparatus of claim 1.
A vehicle retrograde detection method is used for detecting each frame of a surveillance video frame by frame, the method comprising:

Detecting a traveling vehicle in the current frame image;

Establishing a vehicle track set of the current frame image according to the detected traveling vehicle in the current frame image;

Determining, for the vehicle trajectory of the current frame image, the vehicle trajectory that is not determined to be retrograde, detecting the vehicle trajectory that meets the preset condition as a retrograde vehicle trajectory, wherein the preset condition includes: The ratio of the number of times the traveling direction of the vehicle is detected to be opposite to the normal traveling direction and the total number of times of detecting the traveling direction of the vehicle in the current frame image and all previous frame images in the vehicle track determined to be retrograde is greater than a first threshold, and The vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction.
The method of claim 10, wherein

The preset condition includes: a total number of times that the traveling direction of the vehicle is opposite to the normal traveling direction and the total traveling direction of the vehicle are detected in the current frame image and all previous frame images in the vehicle trajectory that is not determined to be retrograde The ratio of the number of times is greater than the first threshold, the vector direction of the vehicle trajectory that is not determined to be retrograde is opposite to the normal traveling direction, and the projection length of the vector of the vehicle trajectory that is not determined to be retrograde in the normal traveling direction The ratio of the height of the last vehicle in the vehicle trajectory that is not determined to be retrograde is greater than a second threshold.
The method of claim 10, wherein

The vector of the vehicle trajectory that is not determined to be retrograde is the displacement vector of the first vehicle to the last vehicle in the vehicle trajectory.
The method according to claim 10, wherein the vehicle trajectory of the vehicle trajectory set that is not determined to be retrograde for the current frame image is detected one by one, including:

When the vector direction of the previous vehicle to the adjacent one of the vehicle trajectories not determined to be retrograde is opposite to the normal traveling direction, the number of times the traveling direction of the vehicle is detected to be opposite to the normal traveling direction is incremented by one.
The method of claim 10, wherein the establishing a vehicle trajectory set of the current frame image based on the detected traveling vehicle in the current frame image comprises:

Adding the traveling vehicle to the vehicle trajectory when the detected traveling vehicle in the current frame image matches any one of the vehicle trajectories in the vehicle trajectory of the previous frame image;

When the detected traveling vehicle in the current frame image does not match any of the vehicle trajectories in the vehicle trajectory of the previous frame image, a new vehicle trajectory is created according to the traveling vehicle.
The method of claim 14, wherein the establishing a vehicle trajectory set of the current frame image based on the detected traveling vehicle in the current frame image further comprises:

When the vehicle in the vehicle trajectory that has been established in the vehicle trajectory set of the previous frame image is not detected in the current frame image, the virtual target of the vehicle in the current frame image is determined according to the average speed of the vehicle and the normal traveling direction, and the A virtual target is added to the vehicle trajectory.
The method of claim 15, wherein the size of the virtual target of the vehicle in the current frame image is the same as the size of the vehicle detected in the previous frame image.
The method of claim 10 wherein said detecting a traveling vehicle in the current frame image comprises:

A classifier is used to detect the traveling vehicle in the current frame image.