CN112687108B - Detection method and detection device for man-vehicle matching, shooting device and storage medium - Google Patents
Detection method and detection device for man-vehicle matching, shooting device and storage medium Download PDFInfo
- Publication number
- CN112687108B CN112687108B CN202010600366.8A CN202010600366A CN112687108B CN 112687108 B CN112687108 B CN 112687108B CN 202010600366 A CN202010600366 A CN 202010600366A CN 112687108 B CN112687108 B CN 112687108B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- man
- target
- information
- related target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a detection method for man-vehicle matching, which comprises the following steps: acquiring a panoramic image through a shooting device, and identifying a man-vehicle related target in the panoramic image; detecting the distance between the man-vehicle related target and the shooting device; if the distance between at least one person-vehicle associated target in the panoramic image and the shooting device is smaller than a threshold value; carrying out man-vehicle matching detection on the man-vehicle associated target with the distance smaller than the threshold value; the man-vehicle matching detection comprises: acquiring the face information and the vehicle information of the man-vehicle related target; and judging whether the man-vehicle association target is man-vehicle integrated or not according to the vehicle information or the vehicle information and the face information. The detection method can optimize the man-vehicle matching process, reduce the resource loss in the processing process and improve the man-vehicle matching detection efficiency of the man-vehicle correlation target.
Description
Technical Field
The invention belongs to the technical field of image detection, and particularly relates to a man-vehicle matching detection method, a man-vehicle matching detection device, a shooting device and a storage medium.
Background
At present, a bayonet camera system is installed at urban crossroads, highways, pedestrian crossings, time-limited roads, main and auxiliary road entrances and exits, public transport special roads and the like, and bayonet detection is generally a system which is mainly used for installing monitoring equipment at crossroads and road sections and carrying out uninterrupted detection and recording on the driving behaviors of motor vehicles in specified lanes. The current bayonet equipment is generally better in the detection effect such as overspeed detection, illegal lane change violation of regulations driving, but has limitation to the effect in the aspect of human-vehicle integrated matching detection.
Disclosure of Invention
The invention provides a detection method, a detection device, a shooting device and a storage medium for man-vehicle matching, which aim to improve the detection efficiency of man-vehicle matching.
In order to solve the technical problems, the invention adopts a technical scheme that: the detection method for the man-vehicle matching comprises the following steps:
acquiring a panoramic image through a shooting device, and identifying a man-vehicle related target in the panoramic image;
detecting the distance between the man-vehicle related target and the shooting device;
if the distance between at least one person-vehicle related target in the panoramic image and the shooting device is smaller than a threshold value; carrying out man-vehicle matching detection on the man-vehicle related target with the distance smaller than the threshold value;
people's car matching detection includes:
acquiring face information and vehicle information of a person-vehicle related target;
and judging whether the man-vehicle association target is man-vehicle integrated or not according to the vehicle information or according to the comparison between the vehicle information and the face information.
The invention also comprises a second technical scheme, and the detection device for man-vehicle matching comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the detection method.
The invention also comprises a third technical scheme, wherein the shooting device comprises a panoramic camera, a detail camera and a surface acoustic wave reader, the panoramic camera is used for acquiring the panoramic image and identifying the human-vehicle associated target in the panoramic image, the detail camera is used for acquiring the face information of the human-vehicle associated target, and the combination of the panoramic camera and the detail camera can be used for measuring the speed of the human-vehicle associated target; and the surface acoustic wave reader is used for reading the surface acoustic wave label and acquiring the vehicle information corresponding to the surface acoustic wave label.
The shooting device comprises a first cloud platform and a third cloud platform, the panoramic camera is arranged on the first cloud platform, the surface acoustic wave reader is arranged on the third cloud platform, and one driving mechanism is used for driving the first cloud platform and the third cloud platform to rotate in the horizontal direction.
The present invention further includes a fourth technical means, which is a computer storage medium storing a computer program executable by a computing apparatus, and when the program runs on the computing apparatus, the method comprises the steps of the detecting method described above.
The invention has the beneficial effects that: different from the situation in the prior art, the human-vehicle matching detection method in the embodiment of the invention compares the distance of the human-vehicle related target in the obtained panoramic image with the threshold value, and performs human-vehicle matching detection on the human-vehicle related target with the distance smaller than the threshold value, while the human-vehicle related target with the distance larger than the threshold value does not enter the human-vehicle matching detection program, so that the human-vehicle matching process can be optimized, the resource loss in the processing process is reduced, and the human-vehicle matching detection efficiency of the human-vehicle related target is improved.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of a camera apparatus according to the present invention;
FIG. 2 is a schematic step diagram of an embodiment of a method for detecting people-vehicle matching according to the present invention;
FIG. 3 is a schematic diagram illustrating steps of another embodiment of a method for detecting matching between a human and a vehicle;
FIG. 4 is a schematic diagram illustrating steps of another embodiment of a method for detecting human-vehicle matching according to the present invention;
FIG. 5 is a schematic diagram illustrating steps of a method for detecting matching between a human and a vehicle according to yet another embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating steps of another embodiment of a method for detecting human-vehicle matching according to the present invention;
FIG. 7 is a schematic diagram illustrating steps of still another embodiment of a method for detecting human-vehicle matching according to the present invention;
FIG. 8 is a block diagram of an embodiment of the device for detecting matching between a human and a vehicle of the present invention;
FIG. 9 is a block diagram of a computer storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples.
In order to carry out intelligent monitoring in the aspect of man-vehicle integrated matching detection, shooting devices can be arranged at urban crossroads, expressways, pedestrian crossings, time-limited roads, main and auxiliary road inlets and outlets, bus lanes and the like.
As shown in fig. 1, an embodiment of the present invention includes a shooting apparatus 10, where the shooting apparatus 10 includes a panoramic camera 11, a detail camera 12, and a surface acoustic wave reader 13, where the panoramic camera 11 is configured to obtain a panoramic image and identify a human-vehicle related target in the panoramic image, the detail camera 12 is configured to obtain face information of the human-vehicle related target, and the panoramic camera 11 and the detail camera 12 in combination may be used to determine a speed of the human-vehicle related target; the surface acoustic wave reader 13 is configured to read the surface acoustic wave tag 30 and acquire information of the vehicle 20 corresponding to the surface acoustic wave tag 30.
The panoramic camera 11 of the embodiment of the invention obtains the panoramic image, the image range is wider, the vehicles 20 on the road can comprise motor vehicles and non-motor vehicles, and the panoramic camera 11 can intelligently extract the human-vehicle related targets, license plates and the like in the panoramic image; the panoramic camera 11 may also be used to capture images of human faces within the vehicle 20 of human-vehicle related targets; the detail camera 12 can shoot the face image in the vehicle 20, wherein the resolution of the face image shot by the detail camera 12 is higher than that of the face image shot by the panoramic camera 11, and the face image shot by the detail camera 12 with high resolution is beneficial to face image recognition, so that the phenomenon of blurring of the shot face image caused by high-speed movement of the vehicle 20 is reduced, and the face image acquisition time is saved.
The embodiment of the invention adopts the surface acoustic wave reader 13, and the surface acoustic wave has longer identification distance and can identify objects with higher speed than the common electronic IC RFID, can be used for extracting the high-speed and long-distance man-vehicle related targets in a complex scene, improves the information matching speed, reduces the time for matching one man and vehicle at a time and leaves sufficient time for matching the next target. The surface acoustic wave tag 30 is disposed on a vehicle of a human-vehicle related object, for example, a license plate.
The shooting device 10 comprises a first cloud platform, a second cloud platform and a third cloud platform, the panoramic camera 11 is arranged on the first cloud platform, the detail camera 12 is arranged on the second cloud platform, the surface acoustic wave reader 13 is arranged on the third cloud platform, and the first cloud platform and the third cloud platform rotate in the horizontal direction to share one driving mechanism. The first holder, the second holder and the third holder can horizontally and vertically rotate, so that the panoramic camera 11 supported by the first holder, the second holder and the third holder can perform dynamic tracking snapshot and other processing on a human-vehicle related target in a scene, the detail camera 12 can also perform tracking snapshot on detail information of the human-vehicle related target in the scene, and more accurate and high-quality actual face information, such as a face photo, can be obtained in real time; wherein first cloud platform and third cloud platform are rotatory independently each other, and are not influenced each other during the motion for panoramic camera 11 and detail camera 12 can track the snapshot independently each other, and the control scene of detail camera 12 can not change when first cloud platform drives panoramic camera 11 motion. One driving mechanism is used for driving the first holder and the third holder to rotate in the horizontal direction, so that the number of the driving mechanisms can be reduced, and the arrangement space of the shooting device 10 is reduced. The difference angle between the horizontal installation positions of the panoramic camera 11 and the surface acoustic wave reader 13 is a fixed value theta, and the panoramic camera 11 and the surface acoustic wave reader 13 are independent in vertical motion.
The embodiment of the invention also comprises a second technical scheme, and provides a man-vehicle matching detection method, as shown in fig. 2, the detection method comprises the following steps:
step 100: and acquiring the panoramic image through a shooting device, and identifying a man-vehicle related target in the panoramic image.
The obtained panoramic image can obtain a panoramic image with a larger range according to the shooting range of the shooting device, and corresponding vehicles can be identified by identifying the people and vehicles associated targets in the panoramic image. The human-vehicle related target may be a vehicle target for which matching of a human with a vehicle is required. For example, the road has motor vehicles and non-motor vehicles, and the motor vehicles are identified as human-vehicle related targets.
Step 200: and detecting the distance between the man-vehicle related target and the shooting device.
The distance between the panoramic image man-car related target and the shooting device can be measured to obtain the corresponding distance.
If the distance between at least one person-vehicle related target in the panoramic image and the shooting device is smaller than a threshold value; then step 300: and carrying out man-vehicle matching detection on the man-vehicle related target with the distance smaller than the threshold value.
The threshold value is the maximum identification distance of the surface acoustic wave reader in the shooting device, the identification distance of the surface acoustic wave reader is limited, when the distance between the human-vehicle related target and the shooting device is smaller than the maximum identification distance of the surface acoustic wave reader, human-vehicle matching detection can be carried out on the human-vehicle related target, and when the distance between the human-vehicle related target and the shooting device is larger than the maximum identification distance of the surface acoustic wave reader, the surface acoustic wave reader in the shooting device cannot identify the human-vehicle related target, and the distance identified by the panoramic image is larger than the maximum identification distance of the surface acoustic wave reader. And if the distance between at least one human-vehicle associated target in the panoramic image and the shooting device is less than the threshold value, starting human-vehicle matching detection, and if the distance between no human-vehicle associated target in the panoramic image and the shooting device is not more than the threshold value, entering conventional video picture monitoring, optimizing a human-vehicle matching process, and reducing resource loss in a processing process and system performance damage.
People's car matching detection includes:
step 310: and acquiring the face information and the vehicle information of the person-vehicle related target.
In the embodiment of the invention, the face information of the person-vehicle related target is a face picture shot by the shooting device, the vehicle information is obtained by setting a label on the vehicle in advance, and the label is related with vehicle owner identity information which is stored and recorded in advance, such as a driving license picture, a vehicle owner identity picture or a vehicle owner head portrait picture. And identifying the tag on the vehicle of the person-vehicle related target and acquiring vehicle information.
Step 320: and judging whether the human-vehicle related target is human-vehicle integrated or not according to the vehicle information or the vehicle information and the face information.
If the acquired vehicle information is associated with the owner identity information, comparing the vehicle information with the face information of the person-vehicle associated target, and judging whether the person-vehicle associated target is integrated with the vehicle according to a comparison result, for example, when the facial features of the photos of the face information and the owner identity information of the vehicle information are 80% or more, the person-vehicle is considered to be integrated with the vehicle; otherwise, the people and vehicles are considered to be abnormal in the association target, and the people and the vehicles are not combined. And if the acquired vehicle information is not associated with the vehicle owner identity information, directly judging that the person-vehicle associated target is abnormal and the person and the vehicle are not integrated. And for the condition that people and vehicles are not integrated, the related abnormal results are output and stored in real time, so that related departments can conveniently and quickly obtain the abnormal results.
According to the man-vehicle matching detection method, the distance of the man-vehicle related target in the panoramic image is compared with the threshold value, man-vehicle matching detection is conducted on the man-vehicle related target with the distance smaller than the threshold value, and the man-vehicle related target larger than the threshold value does not enter a man-vehicle matching detection program, so that a man-vehicle matching process can be optimized, resource loss in a processing process is reduced, and man-vehicle matching detection efficiency of the man-vehicle related target is improved.
In places where photographing devices are arranged at urban crossroads, highways, pedestrian crossings, time-limited roads, main and auxiliary road entrances and exits, bus dedicated roads and the like, vehicles of people and vehicles related targets are often not one, and are generally concentrated into a plurality of vehicles, and the detection of matching of people and vehicles is difficult and detection omission easily occurs due to the occurrence of a large number of people and vehicles related targets, so that as shown in fig. 3, the detection method of the embodiment of the invention further comprises the following steps:
step 210: and calculating the movement speed of the human-vehicle related target according to the position change of the human-vehicle related target in the front and rear frame panoramic images.
When the detection method step 200 detects the distance between the human-vehicle related target and the shooting device, step 210 may be included, and the movement speed of the human-vehicle related target may be calculated and marked beside the human-vehicle related target of the panoramic image.
The man-vehicle matching detection in step 300 further comprises:
step 301: and performing priority ranking on all the people and vehicle related targets with the distance smaller than the threshold value according to the distance between the people and vehicle related target and the shooting device and the movement speed of the people and vehicle related target.
Specifically, all the people-vehicle associated targets with the distance between the shooting device and the threshold value smaller than the distance between the shooting device and the vehicle-human associated targets are subjected to priority ranking, the current distance between the people-vehicle associated targets and the shooting device is S, the current movement speed of the people-vehicle associated targets is V, and the people-vehicle associated Target priority ranking decision function is Target (N) t ) Wherein:
Target(N t )＝f priority level (S,V)
The priority ranking decision function is mainly related to the current distance and the current speed of the man-vehicle related target in the current panoramic picture according to f Priority level And (S, V) calculating and recording the time t (namely the time when the man-vehicle related target disappears in the panoramic image) when each effective man-vehicle related target moves to the shooting device, sequencing the time, wherein the man-vehicle related target with the shortest time firstly runs out of the monitoring scene of the current shooting device, and when the people-vehicle related target leaves the shooting device, people-vehicle matching detection cannot be carried out on the people-vehicle related target. Marking the people and vehicle associated target with the shortest time as a first priority, and performing priority people and vehicle matching; the second short time is marked as a second priority, and the time t corresponding to the arrival of the people and the vehicles at the second priority to the shooting device is stored and recorded 2 And after all the priorities are sorted, marking time t. The position S and the speed V of the people-vehicle related target are dynamically changed, so the priority ranking and the speed V of the people-vehicle related target in the panoramic image are periodically calculated and updated according to the methodTime t when the motion reaches the camera.
Further, the step 310 of the detection method of the present invention obtains the face information and the vehicle information of the person-vehicle related target, and the step 320 determines whether the person-vehicle related target is integrated with the vehicle according to the vehicle information or the vehicle information and the face information, and as shown in fig. 3, the method includes:
step 311: and acquiring the face information and the vehicle information of the person-vehicle related target with the first priority.
Step 320': and judging whether the people and vehicles associated with the first priority are integrated according to the vehicle information or the vehicle information and the face information.
People and vehicles matching detection can be performed on the people and vehicles related targets with the first priority, so that the phenomenon that the people and vehicles related targets with the first priority are missed to be detected is avoided.
Further included after step 320' is:
step 330: and recording the detection time for carrying out human-vehicle matching detection on the human-vehicle related target with the first priority.
The detection time for detecting the people-vehicle matching of the people-vehicle related target with the first priority mainly comprises the time consumed by comparing the vehicle information and the face information of the people-vehicle related target with the first priority.
Step 340: and calculating the predicted time for the man-vehicle related target with the second priority to move to the shooting device.
And determining the people-vehicle related target with the second priority before or after the people-vehicle matching detection of the people-vehicle related target with the first priority is completed through real-time monitoring, and calculating the expected time for the people-vehicle related target with the second priority to move to the shooting device.
If the difference between the estimated time and the detected time is less than the time threshold, step 350: and carrying out rapid man-vehicle matching detection on the man-vehicle related target which is the fastest away from the shooting device.
The detection time comprises face information acquisition time t of a human-vehicle associated target 1 ', acquirerTime t of vehicle information of vehicle-related object 2 ', judgment time t for comparing face information with vehicle information 3 '. For example, if the face information acquisition and the vehicle information acquisition are performed simultaneously, the time t taken when the face information acquisition is performed 1 ' greater than vehicle information acquisition time t 2 ', the detection time T equals T 1 ’+t 3 '. If the face information acquisition, the vehicle information acquisition and the information comparison are carried out in sequence, the detection time is T ═ T 1 ’+t 2 ’+t 3 '. When the difference value between the estimated time and the detection time is smaller than the time threshold, it is indicated that the time consumption for the people-vehicle matching detection of the people-vehicle related target with the first priority is too long or abnormal, and the people-vehicle related target with the second priority may be missed to be detected.
In the embodiment of the invention, the detection time can be shortened and the difference value between the predicted time and the detection time can be increased by fast man-vehicle matching detection, so that the man-vehicle related target with the second priority can be ensured not to be missed for detection, and the missing probability of the man-vehicle related target can be reduced.
Specifically, the shooting device in the embodiment of the invention comprises a panoramic camera and a detail camera; on the basis of fig. 3, as shown in fig. 4,
the obtaining of the face information of the person-vehicle related target with the first priority in step 311 includes: step 311': and acquiring the face information of the person-vehicle related target with the first priority through the detail camera. The vehicle information of the person-vehicle related target of the first priority is acquired in step 311 ', and the vehicle information is still acquired in step 311'.
When the face information of the human-vehicle related target is acquired through the detail camera, for example, a picture is taken through the detail camera to acquire a face image of the human-vehicle related target, the resolution of the acquired face image is higher and is obviously higher than that of the picture taken through the panoramic camera, and meanwhile, the time of the face image acquired through the detail camera is longer than that of the picture taken through the panoramic camera. By acquiring the high-resolution face image, the accuracy of comparison between the face information and the vehicle information is improved.
The fast people-vehicle matching detection of the people-vehicle related target which is the fastest away from the shooting device in the step 350 comprises the following steps: step 350': and carrying out man-vehicle matching detection on the man-vehicle associated target which is farthest away from the shooting device through the panoramic camera.
Specifically, the face information of the people and vehicle related target which is the fastest away from the shooting device is obtained through the panoramic camera, the vehicle information of the people and vehicle related target is obtained, the face information and the vehicle information are compared, and whether the people and vehicle related target which is the fastest away from the shooting device is integrated with the vehicle is judged. In the embodiment of the invention, the face information of the people and vehicle associated target which is farthest away from the shooting device is obtained through the panoramic camera, namely, the face image is obtained, the time for shooting the face image by the panoramic camera is shorter than the time for shooting the face image by the detail camera, the resolution for shooting the face image by the panoramic camera is relatively lower, the people and vehicle matching detection time can be shortened by shooting the face image of the people and vehicle associated target through the panoramic camera, and therefore, the probability of missing detection of the people and vehicle associated target of the second priority caused by overlong time or abnormal detection of the people and vehicle associated target of the first priority can be reduced.
As shown in fig. 5, as a preferred embodiment of the present invention: step 320 determines whether the human-vehicle association target is human-vehicle integrated according to the vehicle information or the vehicle information and the face information, including:
step 321: and detecting whether the vehicle information is related to the owner identity information.
Specifically, the vehicle information is not associated with the owner photograph information of the person-vehicle associated target.
If not, step 322: and judging that the people and the vehicles are not integrated with the target people and the vehicles.
If yes, step 323: and judging whether the face information is matched with the vehicle information.
If so, step 324: determining the combination of the man and the vehicle and the target man and the vehicle;
if not, step 322: and judging that the people and the vehicles are not integrated with the target people and the vehicles.
In the embodiment of the invention, the shooting device comprises an acoustic surface wave reader, and an acoustic surface wave tag is arranged on a man-car related target; further, as shown in fig. 6, step 310: the method for acquiring the face information and the vehicle information of the man-vehicle related target comprises the following steps:
step 3101: and reading the surface acoustic wave tag through a surface acoustic wave reader to acquire the vehicle information of the people-vehicle related target.
The surface acoustic wave reader can identify objects which are far away from each other and move at a high speed, can be used for identifying surface acoustic wave labels of high-speed and long-distance human-vehicle related targets in a complex scene, and therefore can extract vehicle information of the human-vehicle related targets. The problem that the vehicle information is difficult to acquire or the time consumed for acquiring is long due to the fact that the vehicle moves at an excessively high speed is solved. The embodiment of the invention adopts the surface acoustic wave reader to identify the surface acoustic wave label, can improve the information matching speed, reduce the time of single man-vehicle matching and reserve sufficient time for the matching of the next target; meanwhile, the identification distance is long, so that the time required for the people and vehicles to reach the shooting device is long, sufficient time is provided for identifying multiple vehicles in a complex scene, and the probability of missed detection is reduced.
In the embodiment of the invention, the shooting device comprises a panoramic camera and a detail camera; the step 200 of detecting the distance between the man-vehicle related target and the shooting device comprises the following steps:
200' binocular range finding is performed on the human-vehicle associated target through a panoramic camera and a detail camera to detect the distance between the human-vehicle associated target and a photographing device.
In particular, the measured distance may be marked next to the corresponding human-vehicle associated target in the panoramic image.
Further, step 3101: reading the surface acoustic wave tag through a surface acoustic wave reader to acquire vehicle information of a person-vehicle related target, wherein the method comprises the following steps:
step 3102': and acquiring the target position of the man-vehicle related target in the panoramic image.
In the embodiment of the invention, the panoramic camera is arranged on the first cloud deck, the detail camera is arranged on the second cloud deck, the surface acoustic wave reader is arranged on the third cloud deck, and the first cloud deck and the third cloud deck rotate horizontallyAnd the second holder is respectively independent from the first holder and the third holder. Recording the initial position P of the first head Initial Controlling the first holder to move at the maximum speed, enabling the human-vehicle related target to be located at the center of the panoramic image (three-dimensional positioning) as soon as possible, and acquiring the position coordinate information of the vehicle of the human-vehicle related target and the license plate in the panoramic image, wherein the license plate position coordinate is recorded as P Panoramic view (p Number plate horizontal ，p License plate is perpendicular )。
Step 3103': and controlling the surface acoustic wave reader to move to a corresponding position according to the target position, and reading the surface acoustic wave tag to acquire the vehicle information of the people-vehicle related target.
Specifically, the third holder rotates, because the horizontal motion of the surface acoustic wave reader and the sharing of the panoramic camera are realized, and the horizontal installation position deviation angle between the surface acoustic wave reader and the panoramic camera is theta, the first holder is controlled to rotate to theta degrees horizontally again on the basis, and the surface acoustic wave reader rotates to p in the vertical direction License plate is perpendicular The position of the acoustic surface wave reader can ensure that the acoustic surface wave reader can basically face the license plate with the acoustic surface wave label, thereby ensuring that the vehicle information of the stored vehicle owner photo in the license plate can be extracted most effectively and most quickly, and reducing the vehicle information reading time. After the surface acoustic wave reader reads the effective vehicle information, the first holder is controlled to return to the P position Initial Position in order to continue the aforementioned operations such as recognition of the object in the panoramic image.
Through the dynamic movement of the surface acoustic wave reader, the surface acoustic wave reader dynamically follows the man-car associated target, and the probability and the speed of the surface acoustic wave reader for identifying the acoustic wave label of the mobile man-car associated target can be improved. Meanwhile, the acoustic surface wave reader can be dynamically associated with the panoramic camera.
The obtaining of the face information of the person-vehicle related target in step 310 includes:
step 3104': and controlling the detail camera to move to a corresponding position according to the target position, and acquiring the face information of the man-car associated target.
In the processing process of step 3103', the linkage tracking of the detail camera is synchronously triggered, the position in the detail camera is obtained after the coordinate position of the human-vehicle related target in the panoramic camera is converted through a calibration algorithm according to the recorded coordinate position, the second holder is controlled to move to the corresponding position at the maximum speed to complete the zooming tracking snapshot of the actual human face of the human-vehicle related target, so that the detail camera can quickly capture the human face of a vehicle owner with high quality and obtain the human face information, and the process is ended as soon as a clear picture is captured.
As shown in fig. 7, before step 100, the embodiment of the present invention further includes step 001: and acquiring the maximum identification distance of the surface acoustic wave reader as a threshold value.
The present invention further includes a second technical solution, as shown in fig. 8, a human-vehicle matching detection apparatus 80, where the detection apparatus 80 includes a memory 81 and a processor 82, and the memory 81 stores a computer program, so that the processor 82 executes the computer program to implement the detection method.
The Processor 82 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general processor 82 may be a microprocessor or the processor 82 may be any conventional processor or the like, and the processor 82 is the control center of the face matching device and connects the various device parts of the entire camera using various interfaces and lines.
The memory 81 may be used to store the computer programs and/or modules, and the processor 82 implements various functions of the face matching apparatus by running or executing the computer programs and/or modules stored in the memory 81 and calling data stored in the memory 81. The memory 81 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory 81 may include a high speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The present invention also includes a fourth technical solution, as shown in fig. 9, a computer storage medium 90, where the computer storage medium 90 stores a computer program 91 executable by a computing device, and when the program runs on the computing device, the computer storage medium causes the computing device to perform the steps of the above detection method.
Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by a computer program 91 to instruct related hardware, where the computer program 91 may be stored in a computer readable storage medium, and when being executed by a processor, the computer program 91 may implement the steps of the above methods according to the embodiments. Wherein the computer program 91 comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A detection method for human-vehicle matching is characterized by comprising the following steps:
acquiring a panoramic image through a shooting device, and identifying a man-vehicle related target in the panoramic image;
detecting the distance between the man-vehicle related target and the shooting device;
if the distance between at least one person-vehicle associated target in the panoramic image and the shooting device is smaller than a threshold value; carrying out man-vehicle matching detection on the man-vehicle associated target with the distance smaller than the threshold value;
the man-vehicle matching detection comprises: according to the distance between the people and vehicle related target and the shooting device and the movement speed of the people and vehicle related target, carrying out priority ranking on all people and vehicle related targets with the distance smaller than a threshold value; acquiring face information and vehicle information of a person-vehicle associated target with a first priority; judging whether the man-vehicle association target is man-vehicle integrated or not according to the vehicle information or according to the comparison between the vehicle information and the face information; recording the detection time for carrying out human-vehicle matching detection on the human-vehicle related target with the first priority; calculating the predicted time of the man-vehicle related target with the second priority moving to the shooting device; if the difference between the estimated time and the detection time is less than a time threshold; and performing rapid man-vehicle matching detection on the man-vehicle associated target which is farthest away from the shooting device.
2. The detection method according to claim 1, further comprising:
and calculating the movement speed of the human-vehicle related target according to the position change of the human-vehicle related target in the front and rear frames of the panoramic image.
3. The detection method according to claim 1, wherein the photographing apparatus includes a panoramic camera and a detail camera;
the acquiring of the face information of the person-vehicle related target with the first priority comprises: acquiring the face information of the person-vehicle associated target with the first priority through the detail camera;
the fast people and vehicle matching detection of the people and vehicle associated target which is the fastest away from the shooting device comprises the following steps: and carrying out man-vehicle matching detection on the man-vehicle associated target which is farthest away from the shooting device through the panoramic camera.
4. The detection method according to claim 1, wherein the determining whether the human-vehicle related target is human-vehicle integrated according to the vehicle information or the vehicle information and the face information comprises:
detecting whether the vehicle information is related to owner identity information or not;
if not, judging that the people and the vehicles are not integrated with the target people and the vehicles;
if yes, judging whether the face information is matched with the vehicle information;
if so, judging that the man-vehicle association target man-vehicle combination is integrated;
if not, judging that the people and the vehicles are not integrated with the target people and the vehicles.
5. The detection method according to claim 1, wherein the shooting device comprises a surface acoustic wave reader, and a surface acoustic wave tag is arranged on the human-vehicle related target; the acquiring of the face information and the vehicle information of the person-vehicle related target comprises:
and reading the surface acoustic wave tag through the surface acoustic wave reader to acquire the vehicle information of the people-vehicle related target.
6. The detection method according to claim 5, wherein the photographing apparatus includes a panoramic camera and a detail camera; the detecting the distance between the man-vehicle related target and the shooting device comprises:
and carrying out binocular ranging on the man-vehicle related target through the panoramic camera and the detail camera so as to detect the distance between the man-vehicle related target and the shooting device.
7. The method of detecting as claimed in claim 6, wherein said reading said saw tag by said saw reader comprises:
acquiring a target position of the man-vehicle related target in the panoramic image;
controlling the surface acoustic wave reader to move to a corresponding position according to the target position, and reading the surface acoustic wave tag;
the acquiring of the face information of the people-vehicle related target comprises:
and controlling the detail camera to move to a corresponding position according to the target position, and acquiring the face information of the man-car related target.
8. A human-vehicle matching detection device, characterized in that the detection device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the detection method of any one of claims 1 to 7.
9. A computer storage medium, characterized in that it stores a computer program executable by a computing device, which program, when run on the computing device, causes the computing device to perform the steps of the detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600366.8A CN112687108B (en) | 2020-06-28 | 2020-06-28 | Detection method and detection device for man-vehicle matching, shooting device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600366.8A CN112687108B (en) | 2020-06-28 | 2020-06-28 | Detection method and detection device for man-vehicle matching, shooting device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112687108A CN112687108A (en) | 2021-04-20 |
| CN112687108B true CN112687108B (en) | 2022-08-09 |
Family
ID=75445365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010600366.8A Active CN112687108B (en) | 2020-06-28 | 2020-06-28 | Detection method and detection device for man-vehicle matching, shooting device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112687108B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103702029A (en) * | 2013-12-20 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Method and device for prompting focusing during shooting |
| CN105046246A (en) * | 2015-08-31 | 2015-11-11 | 广州市幸福网络技术有限公司 | Identification photo camera capable of performing human image posture photography prompting and human image posture detection method |
| CN107798510A (en) * | 2017-09-27 | 2018-03-13 | 北京市振隆科技股份有限公司 | Electric bicycle, motorcycle, motor tricycle monitoring management system and its method |
| CN107948538A (en) * | 2017-11-14 | 2018-04-20 | 广东欧珀移动通信有限公司 | Imaging method, device, mobile terminal and storage medium |
| CN108563985A (en) * | 2018-03-02 | 2018-09-21 | 海尔优家智能科技（北京）有限公司 | Identify method, monitoring center, public transport equipment and the storage medium stolen |
| CN108846938A (en) * | 2018-09-06 | 2018-11-20 | 星络科技有限公司 | The antitheft management method and device in intelligent Community parking lot |
| CN109214315A (en) * | 2018-08-21 | 2019-01-15 | 北京深瞐科技有限公司 | Across the camera tracking method and device of people's vehicle |
| CN109448143A (en) * | 2018-10-24 | 2019-03-08 | 西安艾润物联网技术服务有限责任公司 | Anti-stealing method for vehicles, system and storage medium |
| CN110228366A (en) * | 2019-06-24 | 2019-09-13 | 上海擎感智能科技有限公司 | It is a kind of for the control method of vehicle safety, device and computer-readable medium |
| CN110298278A (en) * | 2019-06-19 | 2019-10-01 | 中国计量大学 | A kind of underground parking garage Pedestrians and vehicles monitoring method based on artificial intelligence |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100924784B1 (en) * | 2007-12-27 | 2009-11-03 | 주식회사 인스프리트 | Apparatus and method for counting vehicle using CCTV camera, and parking system using the same |
| CN105448131A (en) * | 2015-12-14 | 2016-03-30 | 谭焕玲 | Intelligent parking lot management system having infrared monitoring function |
| CN105809797B (en) * | 2016-04-28 | 2018-04-20 | 西安艾润物联网技术服务有限责任公司 | Video camera and parking ground control system for parking ground control system |
| CN106599774A (en) * | 2016-10-31 | 2017-04-26 | 深圳市元征科技股份有限公司 | Vehicle alarm method and device |
| CN106710294A (en) * | 2016-11-07 | 2017-05-24 | 中山大学南方学院 | Vehicle anti-theft system and method of parking lot |
| CN106803933A (en) * | 2017-02-22 | 2017-06-06 | 成都华安视讯科技有限公司 | Can be used for the camera system and image capture method of the unification monitoring of people's car |
| WO2018208815A1 (en) * | 2017-05-08 | 2018-11-15 | Chase Arnold | Mobile device for autonomous vehicle enhancement system |
| JP2019008519A (en) * | 2017-06-23 | 2019-01-17 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ | Mobile body detection method, mobile body learning method, mobile body detector, mobile body learning device, mobile body detection system, and program |
| CN107677316B (en) * | 2017-09-30 | 2023-12-12 | 深圳市知赢科技有限公司 | Bicycle and user gesture, user use state identification and man-vehicle matching method |
| CN108805008A (en) * | 2018-04-19 | 2018-11-13 | 江苏理工学院 | A kind of community's vehicle security system based on deep learning |
| CN110874921A (en) * | 2018-08-31 | 2020-03-10 | 百度在线网络技术（北京）有限公司 | Intelligent road side unit and information processing method thereof |
| CN110321804A (en) * | 2019-06-11 | 2019-10-11 | 福建亿安智能技术有限公司 | One kind is combined based on face and electronic Car license recognition and carries out identity authentication method |
| CN111078927A (en) * | 2019-12-19 | 2020-04-28 | 罗普特科技集团股份有限公司 | Method, device and storage medium for identifying driver identity based on family tree data |
-
2020
- 2020-06-28 CN CN202010600366.8A patent/CN112687108B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103702029A (en) * | 2013-12-20 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Method and device for prompting focusing during shooting |
| CN105046246A (en) * | 2015-08-31 | 2015-11-11 | 广州市幸福网络技术有限公司 | Identification photo camera capable of performing human image posture photography prompting and human image posture detection method |
| CN107798510A (en) * | 2017-09-27 | 2018-03-13 | 北京市振隆科技股份有限公司 | Electric bicycle, motorcycle, motor tricycle monitoring management system and its method |
| CN107948538A (en) * | 2017-11-14 | 2018-04-20 | 广东欧珀移动通信有限公司 | Imaging method, device, mobile terminal and storage medium |
| CN108563985A (en) * | 2018-03-02 | 2018-09-21 | 海尔优家智能科技（北京）有限公司 | Identify method, monitoring center, public transport equipment and the storage medium stolen |
| CN109214315A (en) * | 2018-08-21 | 2019-01-15 | 北京深瞐科技有限公司 | Across the camera tracking method and device of people's vehicle |
| CN108846938A (en) * | 2018-09-06 | 2018-11-20 | 星络科技有限公司 | The antitheft management method and device in intelligent Community parking lot |
| CN109448143A (en) * | 2018-10-24 | 2019-03-08 | 西安艾润物联网技术服务有限责任公司 | Anti-stealing method for vehicles, system and storage medium |
| CN110298278A (en) * | 2019-06-19 | 2019-10-01 | 中国计量大学 | A kind of underground parking garage Pedestrians and vehicles monitoring method based on artificial intelligence |
| CN110228366A (en) * | 2019-06-24 | 2019-09-13 | 上海擎感智能科技有限公司 | It is a kind of for the control method of vehicle safety, device and computer-readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112687108A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101756849B1 (en) | Parking control and management system for on-street parking lot | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| EP3026651B1 (en) | Vehicle monitoring device and vehicle monitoring method | |
| US20100172543A1 (en) | Multiple object speed tracking system | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| Lin et al. | Lane departure and front collision warning using a single camera | |
| CN113055823B (en) | Method and device for managing shared bicycle based on road side parking | |
| CN111976601B (en) | Automatic parking method, device, equipment and storage medium | |
| CN115331191B (en) | Vehicle type recognition method, device, system and storage medium | |
| CN112172797B (en) | Parking control method, device, equipment and storage medium | |
| CN110880205B (en) | Parking charging method and device | |
| CN114219829A (en) | Vehicle tracking method, computer equipment and storage device | |
| JP5306124B2 (en) | Number plate reading apparatus and number plate reading method | |
| CN112687108B (en) | Detection method and detection device for man-vehicle matching, shooting device and storage medium | |
| Ćosić et al. | Time to collision estimation for vehicles coming from behind using in-vehicle camera | |
| CN115965636A (en) | Vehicle side view generating method and device and terminal equipment | |
| JP5957182B2 (en) | Road surface pattern recognition method and vehicle information recording apparatus | |
| CN112016514B (en) | Traffic sign recognition method, device, equipment and storage medium | |
| CN116152691A (en) | Image detection method, device, equipment and storage medium | |
| KR102369824B1 (en) | License Plate Recognition Method and Apparatus for roads | |
| CN104077566B (en) | Bayonet socket picture method for detecting human face based on color difference | |
| JP4333683B2 (en) | Windshield range detection device, method and program | |
| KR20080049472A (en) | Information detecting system using photographing apparatus load in vehicle and artificial neural network | |
| JP2015097038A (en) | Vehicle counter, vehicle counting program, and vehicle counting system | |
| KR102416066B1 (en) | System and method for matching video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |