CN110738858B - Camera image processing method, coder-decoder and storage device - Google Patents
Camera image processing method, coder-decoder and storage device Download PDFInfo
- Publication number
- CN110738858B CN110738858B CN201911062997.2A CN201911062997A CN110738858B CN 110738858 B CN110738858 B CN 110738858B CN 201911062997 A CN201911062997 A CN 201911062997A CN 110738858 B CN110738858 B CN 110738858B
- Authority
- CN
- China
- Prior art keywords
- image
- person
- camera
- vehicle
- program
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Abstract
The invention discloses a camera image processing method, a coder-decoder and a storage device, wherein the camera image processing method comprises the following steps: acquiring a camera image; determining whether a person and a vehicle are present in the camera image at the same time; detecting the speed of the person and the vehicle when the person and the vehicle exist in the camera image at the same time; determining the faster and slower of the speed of the person and the speed of the vehicle; and calling the identification image program corresponding to the faster person to perform image identification, and calling the identification image program corresponding to the slower person to perform image identification. Through the mode, the identification function of the identification camera can be ensured, the identification efficiency is improved, and the identification effects of a plurality of scenes and objects to be identified with different reflectivities are considered.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a camera image processing method, a codec, and a storage device.
Background
With the popularization of the intelligent identification function of the cameras, more and more cameras need to have the capabilities of face identification, license plate identification and customized identification requirements in practical application. The camera can normally work at night and needs light supplement for a camera monitoring area, and the camera is normally used for infrared light or white light. The face features of the key recognition class are generally diffuse reflection surfaces, while the license plate features are generally strong reflection surfaces or reflection surfaces stronger than the face. At this time, a technical contradiction is faced: the camera can identify the face at the farthest distance at night or when the ambient brightness is dark, and meanwhile, the license plate at the near place is prevented from being overexposed. The traditional scheme adopts the same image program, and has the problems that the human face or the human body can be identified in the picture, but the license plate is overexposed, or the license plate can be identified, but the human face and the human body are blackish, and the like.
Disclosure of Invention
The application provides a camera image processing method, a coder-decoder and a storage device, which are used for all intelligent cameras, the sequence of calling an image program is selected by judging the speed of people and vehicles, and the faces and license plates in the images are accurately identified, so that the identification function of an identification camera can be ensured, the identification efficiency is improved, and the identification effects of a plurality of scenes and objects to be identified with different reflectivities are considered.
In order to solve the technical problem, the application adopts a technical scheme that: provided is a camera image processing method including:
acquiring a camera image;
determining whether a person and a vehicle are present in the camera image at the same time;
detecting the speed of the person and the vehicle when the person and the vehicle exist in the camera image at the same time;
judging whether the speed of the person is greater than the speed of the vehicle;
determining the faster and slower of the speed of the person and the speed of the vehicle;
and calling the identification image program corresponding to the faster person to perform image identification, and calling the identification image program corresponding to the slower person to perform image identification.
In order to solve the above technical problem, the present application adopts another technical solution that: providing a codec comprising a processor, a memory coupled to the processor, wherein the memory stores program instructions for implementing the camera image processing method; the processor is operable to execute the program instructions stored in the memory to process the camera image.
In order to solve the above technical problem, the present application adopts another technical solution that: a storage device is provided for storing a program file capable of implementing the camera image processing method.
The beneficial effect of this application is: through the speed of detecting people and car, select the order of transferring the image procedure, carry out accurate discernment to people's face in the image and license plate, not only can guarantee the recognition function of discernment class camera, promote recognition efficiency, compromise the recognition effect of the object of waiting to discern of a plurality of scenes and different reflectivities simultaneously.
Drawings
Fig. 1 is a schematic flow chart of a camera image processing method according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of a camera image processing method according to a second embodiment of the present invention;
fig. 3 is a schematic configuration diagram of a camera image processing apparatus according to a first embodiment of the present invention;
fig. 4 is a schematic configuration diagram of a camera image processing apparatus according to a second embodiment of the present invention;
FIG. 5 is a block diagram of a codec according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a memory device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first", "second" and "third" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any indication of the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of the feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. All directional indications (such as up, down, left, right, front, and rear … …) in the embodiments of the present application are only used to explain the relative positional relationship between the components, the movement, and the like in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indication is changed accordingly. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Fig. 1 is a flowchart illustrating a camera image processing method according to a first embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 1 if the results are substantially the same. As shown in fig. 1, the method comprises the steps of:
step S101: a camera image is acquired.
In step S101, the camera image may be a video image or a single frame image.
Step S102: it is determined whether a person and a vehicle are simultaneously present in the camera image.
In step S102, the method includes: collecting picture data in a camera image; whether a person and a vehicle are simultaneously present in the camera image is determined based on the picture data. In the present embodiment, the picture data in the camera image includes contour data of a person and contour data of a car. The determination of whether a person and a vehicle are present in the camera image simultaneously according to the picture data may be implemented in two preferable ways, and in one embodiment, the determination of whether a person and a vehicle are present in the camera image simultaneously according to the picture data and the preset profile. The preset contour comprises a preset vehicle type and a preset human type, the picture data is compared with the preset vehicle type, and when the contour consistent with the preset vehicle type exists in the picture data, the vehicle in the camera image is detected; and comparing the picture data with a preset human type, and detecting that a human exists in the camera image when a contour consistent with the preset human type exists in the picture data. In another embodiment, a deep learning algorithm is used to determine if a person and a vehicle are present in the camera image simultaneously based on the captured visual data. Collecting multiple groups of training data to establish a recognition model, wherein each group of training data comprises picture data including people and/or vehicles, inputting images of a camera into the recognition model, and outputting outlines of the people and/or vehicles. When the output result is the outline of the person, detecting that the person exists in the camera image; when the output result is the outline of the vehicle, detecting that the vehicle exists in the camera image; when the output result is the outlines of the person and the vehicle, it is detected that the person and the vehicle are simultaneously present in the camera image.
Step S103: when a person and a vehicle are simultaneously present in the camera image, the speeds of the person and the vehicle are detected.
In step S103, the step of detecting the speeds of the person and the vehicle includes: acquiring multiple frames of camera images, wherein people and vehicles exist in the camera images; selecting two frames of camera images, recording the shooting time of the two frames of camera images, and respectively calculating the displacement of a person and the displacement of a vehicle; the speed of the person and the speed of the vehicle are calculated from the photographing time, the displacement amount of the person, and the displacement amount of the vehicle, respectively. The speed of the person is the ratio of the displacement of the person to the shooting time difference of the two frames of camera images, and the speed of the vehicle is the ratio of the displacement of the vehicle to the shooting time difference of the two frames of camera images.
Step S104: the faster and slower of the speed of the person and the speed of the vehicle are determined.
In step S104, the person and the vehicle coming from the camera appear within the shooting range of the camera earlier as the speed is higher.
Step S105: and calling the identification image program corresponding to the faster person to perform image identification, and calling the identification image program corresponding to the slower person to perform image identification.
In step S105, the human-corresponding recognition image program performs face recognition, and the vehicle-corresponding recognition image program performs license plate recognition. And comparing the speed of the person with the speed of the vehicle, and calling the identification image program corresponding to the person and then calling the identification image program corresponding to the vehicle when the speed of the person is greater than the speed of the vehicle. When the speed of the vehicle is higher than that of the person, the identification image program corresponding to the vehicle is called first, and then the identification image program corresponding to the person is called. When the speed of the person is equal to that of the vehicle, the identification image program corresponding to the vehicle is called preferentially, and then the identification image program corresponding to the person is called. In this embodiment, when the speed of the person outside the vehicle is equal to the speed of the vehicle, the identification image program corresponding to the vehicle is called with priority, and the identification image program corresponding to the person is called again.
The camera image processing method of the first embodiment of the invention is suitable for all intelligent cameras, and can accurately identify the faces and license plates in the images respectively by judging the speeds of people and vehicles and selecting the sequence of calling image programs, thereby not only ensuring the identification function of the identification cameras and improving the identification efficiency, but also considering the identification effects of a plurality of scenes and objects to be identified with different reflectivities.
Fig. 2 is a flowchart illustrating a camera image processing method according to a second embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 2 if the results are substantially the same. As shown in fig. 2, the method comprises the steps of:
step S201: a camera image is acquired.
Step S201 in this embodiment is similar to step S101 in fig. 1, and is not described herein again.
Step S202: and presetting an image program, wherein the image program comprises a license plate recognition image program, a face recognition image program and a general image program.
In step S202, an image program is preset according to a scene, wherein the scene refers to a daytime scene or a nighttime scene, and a ball-grabbing linkage scheme, a single gun scheme or a single ball scheme is adopted, and the image program is preset according to the steps of: adjusting camera data according to the reflection characteristics of the human face or the human body, wherein the camera data when the human face information can be recognized is a preset human face recognition image program; adjusting camera data according to the reflection characteristic of the license plate, wherein the camera data when the license plate information can be identified is a preset license plate identification image program; and adjusting the camera data according to the environment, wherein the camera data when the camera data is adjusted to be capable of identifying the outlines of the people and the vehicle is a preset general image program.
The preset face recognition image program, the preset license plate recognition image program and the preset general image program all comprise: aperture control mode or parameter, shutter control mode or parameter, gain control mode or parameter, and fill light intensity control mode or parameter. In the same scene, (1) the preset face recognition image program is larger than the diaphragm opening of the license plate recognition image program for the size of the diaphragm opening, (2) the preset face recognition image program is longer than the shutter time of the license plate recognition image program for the shutter time, (3) the preset face recognition image program is higher than the gain of the license plate recognition image program for the gain size, and (4) the preset face recognition image program is higher than the fill light intensity of the license plate recognition image program for the fill light intensity. In the actual working process, it is only required that the preset face recognition image program and the preset license plate recognition image program simultaneously meet at least one condition of the above conditions (1), (2), (3) and (4).
Step S203: and calling a preset general image program to identify the outlines of the people and the vehicles in the camera image.
In step S203, a preset general-purpose image program is used to cause the phenomena of license plate overexposure and face blackness, so that the license plate and the face cannot be recognized at the same time, but the outlines of the person and the vehicle in the camera image can be recognized.
Step S204: it is determined whether a person and a vehicle are simultaneously present in the camera image.
Step S204 in the present embodiment is similar to step S102 in fig. 1, and executes step S205 and step S206 when a person and a vehicle are present in the camera image at the same time, executes step S207 when only a person is present in the camera image, executes step S208 when only a vehicle is present in the camera image, and executes step S209 when a person and a vehicle are not present in the camera image.
Step S205: the speed of the person and the vehicle is detected.
Step S205 in the present embodiment is similar to step S103 in fig. 1.
Step S206: it is determined whether the speed of the person is greater than the speed of the vehicle.
In the present embodiment, step S206 is executed after step S205, and when the speed of the person is greater than the speed of the vehicle, step S2061 is executed: the method comprises the steps of calling a preset face recognition image program, then calling a preset license plate recognition image program, saving a face recognition result after calling the preset face recognition image program, saving a camera image containing the face recognition result, and saving the face recognition result extracted from the camera image; the method also comprises the step of storing the license plate recognition result after calling the preset license plate recognition image program, and can store a camera image containing the license plate recognition result and also can store the license plate recognition result extracted from the camera image. After step S2061, step S203 is cyclically executed.
When the speed of the vehicle is higher than the speed of a person, the step S2062 is executed to call a preset license plate recognition image program, then call a preset face recognition image program, and save license plate recognition results after calling the preset license plate recognition image program, wherein the camera image containing the license plate recognition results can be saved, and the license plate recognition results extracted from the camera image can also be saved; the method also comprises the step of saving the face recognition result after the preset face recognition image program is called, and can save a camera image containing the face recognition result and also can save the face recognition result extracted from the camera image. After step S2062, step S203 is executed cyclically.
When the speed of a person is equal to that of a vehicle, a preset license plate recognition image program is called preferentially, and then a preset face recognition image program is called. In this embodiment, when the speed of the person outside the vehicle is equal to the speed of the vehicle, the preset license plate recognition image program is called first, and then the preset face recognition image program is called, and the person inside the vehicle and the vehicle are also suitable for calling the preset license plate recognition image program first, and then the preset face recognition image program is called.
Step S207: and calling a preset face recognition image program.
In step S207, the step of calling the preset face recognition image program further includes saving a face recognition result, which may be saving a camera image containing the face recognition result, or saving a face recognition result extracted from the camera image. After step S207, step S203 is executed cyclically.
Step S208: and calling a preset license plate recognition image program.
In step S208, the step of saving the license plate recognition result after calling the preset license plate recognition image program may be performed, and the camera image including the license plate recognition result may be saved, or the license plate recognition result extracted from the camera image may be saved. After step S208, step S203 is executed cyclically.
Step S209: and calling a preset general image program.
After step S209, step S203 is executed cyclically.
The camera image processing method of the second embodiment of the invention calls different image programs according to the detection result on the basis of the first embodiment to accurately identify the face and the license plate in the image respectively, thereby not only ensuring the identification function of the identification camera and improving the identification efficiency, but also considering the identification effects of a plurality of scenes and objects to be identified with different reflectivities.
Fig. 3 is a schematic configuration diagram of a camera image processing apparatus according to a first embodiment of the present invention. As shown in fig. 3, the apparatus 30 includes: the device comprises an image acquisition module 31, a determination module 32, a detection module 33, a judgment module 34 and an execution module 35.
The image acquisition module 31 is used for acquiring camera images.
In this embodiment, the camera image may be a video image or a single frame image.
The determination module 32 is coupled to the image acquisition module 31 for determining whether a person and a vehicle are present in the camera image at the same time.
In this embodiment, the determination module 32 includes a collecting unit for collecting picture data in the camera image and a determining unit coupled to the collecting unit for determining whether a person and a vehicle are simultaneously present in the camera image according to the picture data. The image data in the camera image includes the contour data of the person and the contour data of the vehicle, and the determining unit may have two preferred embodiments, in one embodiment, whether the person and the vehicle are present in the camera image at the same time is determined according to the image data and the preset contour. The preset contour comprises a preset vehicle type and a preset human type, the picture data is compared with the preset vehicle type, and when the contour consistent with the preset vehicle type exists in the picture data, the vehicle in the camera image is detected; and comparing the picture data with a preset human type, and detecting that a human exists in the camera image when a contour consistent with the preset human type exists in the picture data. In another embodiment, a deep learning algorithm is used to determine if a person and a vehicle are present in the camera image simultaneously based on the captured visual data. Collecting multiple groups of training data to establish a recognition model, wherein each group of training data comprises picture data including people and/or vehicles, inputting images of a camera into the recognition model, and outputting outlines of the people and/or vehicles. When the output result is the outline of the person, detecting that the person exists in the camera image; when the output result is the outline of the vehicle, detecting that the vehicle exists in the camera image; when the output result is the outlines of the person and the vehicle, it is detected that the person and the vehicle are simultaneously present in the camera image.
The detection module 33 is coupled to the determination module 32 for detecting the speed of the person and the vehicle when both are present in the camera image.
In this embodiment, the detection module 33 obtains multiple camera images, where people and vehicles are present in the camera images; selecting two frames of camera images, recording the shooting time of the two frames of camera images, and respectively calculating the displacement of a person and the displacement of a vehicle; the speed of the person and the speed of the vehicle are calculated from the photographing time, the displacement amount of the person, and the displacement amount of the vehicle, respectively. The speed of the person is the ratio of the displacement of the person to the shooting time difference of the two frames of camera images, and the speed of the vehicle is the ratio of the displacement of the vehicle to the shooting time difference of the two frames of camera images.
The decision module 34 is coupled to the detection module 33 for determining the faster and slower of the speed of the person and the speed of the vehicle.
In the present embodiment, the faster the speed is, the earlier the person and the vehicle come from the camera appears within the shooting range of the camera.
The executing module 35 is coupled to the determining module 34, and configured to, according to the determination result of the determining module 34, first call the identification image program corresponding to the faster to perform image identification, and then call the identification image program corresponding to the slower to perform image identification.
The execution module 35 calls an image recognition program corresponding to a person to perform face recognition, and an image recognition program corresponding to a vehicle to perform license plate recognition. And comparing the speed of the person with the speed of the vehicle, and calling the identification image program corresponding to the person and then calling the identification image program corresponding to the vehicle when the speed of the person is greater than the speed of the vehicle. When the speed of the vehicle is higher than that of the person, the identification image program corresponding to the vehicle is called first, and then the identification image program corresponding to the person is called. When the speed of the person is equal to that of the vehicle, the identification image program corresponding to the vehicle is called preferentially, and then the identification image program corresponding to the person is called. In this embodiment, when the speed of the person outside the vehicle is equal to the speed of the vehicle, the identification image program corresponding to the vehicle is called with priority, and the identification image program corresponding to the person is called again.
Fig. 4 is a schematic configuration diagram of a camera image processing apparatus according to a second embodiment of the present invention. As shown in fig. 4, the apparatus 40 includes: the image processing system comprises an image acquisition module 41, an image program presetting module 42, a first calling module 43, a determining module 44, a detection module 45, a judgment module 46, a first control module 461, a second control module 462, a second calling module 47, a third calling module 48 and a fourth calling module 49.
The image acquisition module 41 is used for acquiring camera images.
In this embodiment, the camera image may be a video image or a single frame image.
The image program presetting module 42 and the image acquiring module 41 are configured to preset image programs, where the image programs include a license plate recognition image program, a face recognition image program, and a general image program.
In this embodiment, the image program presetting module 42 adjusts the camera data according to the reflection characteristics of the human face or the human body, and the camera data adjusted to be capable of recognizing the human face information is a preset human face recognition image program; adjusting camera data according to the reflection characteristic of the license plate, wherein the camera data when the license plate information can be identified is a preset license plate identification image program; and adjusting the camera data according to the environment, wherein the camera data when the camera data is adjusted to be capable of identifying the outlines of the people and the vehicle is a preset general image program.
The preset face recognition image program, the preset license plate recognition image program and the preset general image program all comprise: aperture control mode or parameter, shutter control mode or parameter, gain control mode or parameter, and fill light intensity control mode or parameter. In the same scene, (1) the preset face recognition image program is larger than the diaphragm opening of the license plate recognition image program for the size of the diaphragm opening, (2) the preset face recognition image program is longer than the shutter time of the license plate recognition image program for the shutter time, (3) the preset face recognition image program is higher than the gain of the license plate recognition image program for the gain size, (4) the preset face recognition image program is higher than the light supplement intensity of the license plate recognition image program for the light supplement intensity, and in the actual working process, the preset face recognition image program and the license plate recognition image program can simultaneously meet at least one condition of the conditions (1), (2), (3) and (4).
The first calling module 43 is coupled to the image program presetting module 42, and is used for calling a preset general image program to identify the outlines of people and vehicles in the camera image.
In this embodiment, the phenomenon of license plate overexposure and face overexposure exists by adopting a preset general image program, so that the license plate and the face cannot be recognized at the same time, but the outlines of a person and a vehicle in the image of the camera can be recognized.
The determination module 44 is coupled to the first calling module 43 for determining whether a person and a vehicle are present in the camera image at the same time.
The determination module 44 of this embodiment is similar to the determination module 32 in fig. 3, and is not described herein again.
The detection module 45 is coupled to the determination module 44 for detecting the speed of the person and the vehicle when both are present in the camera image.
The determination module 46 is coupled to the detection module 45 for determining whether the speed of the person is greater than the speed of the vehicle.
The first control module 461 is coupled to the determining module 46 and the image program presetting module 42, respectively, and when the determination result indicates that the speed of the person is greater than the speed of the vehicle, the first control module 461 invokes a preset face recognition image program and then invokes a preset license plate recognition image program.
The second control module 462 is coupled to the determining module 46 and the image program presetting module 42, respectively, and when the determination result is that the speed of the vehicle is greater than the speed of the person, the second control module 462 invokes a preset license plate recognition image program and then invokes a preset face recognition image program.
The second calling module 47 is respectively coupled to the determining module 44 and the image program presetting module 42, and is used for calling the preset face recognition image program by the second calling module 47 when only a person exists in the camera image.
The third calling module 48 is coupled to the determining module 44 and the image program presetting module 42, respectively, and is configured to, when only a vehicle exists in the camera image, call the preset license plate recognition image program by the third calling module 48.
The fourth calling module 49 is coupled to the determining module 44 and the image program presetting module 42, respectively, and is used for calling the preset general image program by the fourth calling module 49 when no person or vehicle exists in the camera image.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a codec according to an embodiment of the invention. As shown in fig. 5, the codec 50 includes a processor 51 and a memory 52 coupled to the processor 51.
The memory 52 stores program instructions for implementing the camera image processing method of any of the embodiments described above.
The processor 51 is operative to execute program instructions stored in the memory 52 to process the camera images.
The processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having signal processing capabilities. The processor 51 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a memory device according to an embodiment of the invention. The storage device of the embodiment of the present invention stores a program file 61 capable of implementing all the methods described above, wherein the program file 61 may be stored in the storage device in the form of a software product, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage device includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.
Claims (10)
1. A camera image processing method, comprising:
acquiring a camera image;
determining whether a person and a vehicle are present in the camera image at the same time;
detecting the speed of the person and the vehicle when the person and the vehicle exist in the camera image at the same time;
determining the faster and slower of the speed of the person and the speed of the vehicle;
calling an identification image program corresponding to a faster person to perform image identification, and calling an identification image program corresponding to a slower person to perform image identification, wherein the identification image program corresponding to the faster person is obtained based on the reflection characteristic of the faster person, and the identification image program corresponding to the slower person is obtained based on the reflection characteristic of the slower person.
2. The camera image processing method according to claim 1,
the step of determining whether a person and a vehicle are present in the camera image at the same time includes:
acquiring picture data in the camera image;
and determining whether a person and a vehicle exist in the camera image at the same time according to the picture data.
3. The camera image processing method according to claim 2, wherein the determining whether a person and a vehicle are present in the camera image at the same time comprises:
presetting an image program, wherein the image program comprises a license plate recognition image program, a face recognition image program and a general image program;
and calling the preset general image program to identify the outlines of people and vehicles in the camera image.
4. A camera image processing method according to claim 3, characterized in that the step of presetting the image program comprises:
adjusting camera data according to the reflection characteristics of the human face or the human body, wherein the camera data when the human face information can be recognized is a preset human face recognition image program;
adjusting camera data according to the reflection characteristic of the license plate, wherein the camera data when the license plate information can be identified is a preset license plate identification image program;
adjusting camera data according to the environment, wherein the camera data when the camera data can be adjusted to identify the outlines of people and vehicles is a preset general image program;
the preset face recognition image program, the preset license plate recognition image program and the preset general image program all comprise: aperture control mode or parameter, shutter control mode or parameter, gain control mode or parameter, and fill light intensity control mode or parameter.
5. The camera image processing method according to claim 3,
determining the faster and the slower of the speed of the person and the speed of the vehicle, calling the identification image program corresponding to the faster to perform image identification, and then calling the identification image program corresponding to the slower to perform image identification comprises:
judging whether the speed of the person is greater than the speed of the vehicle;
when the speed of the person is greater than the speed of the vehicle, calling the preset face recognition image program, and then calling the preset license plate recognition image program;
and when the speed of the vehicle is higher than the speed of the person, calling the preset license plate recognition image program, and then calling the preset face recognition image program.
6. The camera image processing method according to claim 3, wherein said determining whether a person and a vehicle are simultaneously present in the camera image comprises:
when only a person exists in the camera image, calling the preset face recognition image program;
when only a vehicle exists in the camera image, calling the preset license plate recognition image program;
and when no person or vehicle exists in the camera image, calling the preset general image program.
7. The camera image processing method according to claim 5 or 6,
after the preset face recognition image program is called, a face recognition result is stored;
and after the preset license plate recognition image program is called, storing a license plate recognition result.
8. The camera image processing method according to claim 1, wherein the step of detecting the speeds of the person and the vehicle when the person and the vehicle are simultaneously present in the camera image comprises:
acquiring multiple frames of camera images, wherein the people and the vehicle exist in the camera images;
selecting two frames of the camera images, recording shooting time of the two frames of the camera images, and respectively calculating the displacement of the person and the displacement of the vehicle;
and respectively calculating the speed of the person and the speed of the vehicle according to the shooting time, the displacement of the person and the displacement of the vehicle.
9. A codec comprising a processor, a memory coupled to the processor, wherein,
the memory stores program instructions for implementing the camera image processing method of any of claims 1-8;
the processor is to execute the program instructions stored by the memory to process a camera image.
10. A storage device characterized by storing a program file capable of implementing the camera image processing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911062997.2A CN110738858B (en) | 2019-10-31 | 2019-10-31 | Camera image processing method, coder-decoder and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911062997.2A CN110738858B (en) | 2019-10-31 | 2019-10-31 | Camera image processing method, coder-decoder and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110738858A CN110738858A (en) | 2020-01-31 |
| CN110738858B true CN110738858B (en) | 2020-11-10 |
Family
ID=69272107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911062997.2A Active CN110738858B (en) | 2019-10-31 | 2019-10-31 | Camera image processing method, coder-decoder and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110738858B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2819395B1 (en) * | 2013-06-27 | 2015-08-12 | Axis AB | Method and apparatus for setting a camera exposure time |
| CN103559498A (en) * | 2013-09-24 | 2014-02-05 | 北京环境特性研究所 | Rapid man and vehicle target classification method based on multi-feature fusion |
| CN104144325A (en) * | 2014-07-08 | 2014-11-12 | 北京汉王智通科技有限公司 | Monitoring method and monitoring device |
| CN104282150B (en) * | 2014-09-29 | 2017-01-11 | 北京数字智通科技有限公司 | Recognition device and system of moving target |
| US10043078B2 (en) * | 2015-04-21 | 2018-08-07 | Placemeter LLC | Virtual turnstile system and method |
-
2019
- 2019-10-31 CN CN201911062997.2A patent/CN110738858B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110738858A (en) | 2020-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108322646B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN114424253A (en) | Model training method and device, storage medium and electronic equipment | |
| KR102263537B1 (en) | Electronic device and control method of the same | |
| CN116582741B (en) | Shooting method and equipment | |
| CN105872399B (en) | Backlighting detecting and backlight detection system | |
| CN104182721A (en) | Image processing system and image processing method capable of improving face identification rate | |
| CN108513069B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN112689221B (en) | Recording method, recording device, electronic equipment and computer readable storage medium | |
| CN113409296B (en) | Core-pulling detection method of winding battery cell, electronic equipment and storage medium | |
| US20150138076A1 (en) | Communication device and method of processing incoming call by facial image | |
| CN111553302B (en) | Key frame selection method, device, equipment and computer readable storage medium | |
| CN111654637B (en) | Focusing method, focusing device and terminal equipment | |
| JP2019020956A (en) | Vehicle surroundings recognition device | |
| CN108259769B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN108805838B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN114267041A (en) | Method and device for identifying object in scene | |
| CN108154090B (en) | Face recognition method and device | |
| WO2019196240A1 (en) | Photographing method, apparatus, computer device, and storage medium | |
| CN113747008A (en) | Camera and light supplementing method | |
| CN110738858B (en) | Camera image processing method, coder-decoder and storage device | |
| CN110933314B (en) | Focus-following shooting method and related product | |
| CN108810407B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN113591526A (en) | Face living body detection method, device, equipment and computer readable storage medium | |
| US9092661B2 (en) | Facial features detection | |
| CN112153300A (en) | Multi-view camera exposure method, device, equipment and medium |
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 |