CN116129316A - Image processing method, device, computer equipment and storage medium - Google Patents

Image processing method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN116129316A
CN116129316A CN202310090033.9A CN202310090033A CN116129316A CN 116129316 A CN116129316 A CN 116129316A CN 202310090033 A CN202310090033 A CN 202310090033A CN 116129316 A CN116129316 A CN 116129316A
Authority
CN
China
Prior art keywords
video frame
resource
resolution
frame group
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.)
Pending
Application number
CN202310090033.9A
Other languages
Chinese (zh)
Inventor
曹小刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Dahua Technology Co Ltd
Original Assignee
Zhejiang Dahua Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Dahua Technology Co Ltd filed Critical Zhejiang Dahua Technology Co Ltd
Priority to CN202310090033.9A priority Critical patent/CN116129316A/en
Publication of CN116129316A publication Critical patent/CN116129316A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/60—Memory management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Editing Of Facsimile Originals (AREA)
  • Television Signal Processing For Recording (AREA)
  • Television Systems (AREA)

Abstract

The present application relates to an image processing method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: acquiring an original video frame group; determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment; determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the residual device resource; the original video frame group is processed based on the resource level and the zoom resolution, and image data of the detection object is acquired from the video frame corresponding to the zoom resolution. The method can improve the quality of the grabbed images and the utilization rate of resources.

Description

Image processing method, device, computer equipment and storage medium
Technical Field
The present disclosure relates to the field of security monitoring technologies, and in particular, to an image processing method, an image processing apparatus, a computer device, a storage medium, and a computer program product.
Background
With the development of security monitoring technology, people have increasingly high requirements on the quality of image capturing. After the network camera shoots the monitoring area to obtain the monitoring video, the network camera generally needs to capture images from the monitoring video according to the requirements of actual application scenes, and views target objects in the video.
The existing capture processing is to intelligently analyze that each video channel is subjected to frame extraction to a fixed frame rate and scaled to a fixed resolution, and the detection target captures images based on the scaled size, so that capture images are low in quality and low in resource utilization rate.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an image processing method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the quality of a grip image and the utilization of resources.
In a first aspect, the present application provides an image processing method. The method comprises the following steps:
acquiring an original video frame group;
determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the scaling resolution.
In one embodiment, the device resources include a target demand memory resource and a target demand power resource, the remaining device resources include a remaining memory resource and a target remaining power resource, and determining the scaling resolution of the original video frame group according to the target device resources and the remaining device resources includes:
Determining a resource level of the image processing device according to a size relationship between the target required memory resource and the remaining memory resource and a size relationship between the target required computing power resource and the target remaining computing power resource; the target remaining computing power resource is an average value of the target remaining computing power resource in the continuous appointed time;
and determining the zoom resolution of the video frame corresponding to the resource level according to the resource level.
In one embodiment, if the target remaining computing power resource is greater than the target demand computing power resource and the remaining memory resource is greater than the target demand memory resource, determining that the resource level of the image processing device is a first resource level; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
if the resource level is a first resource level and the scaling resolution is the original resolution of the original video frame group, processing each video frame in the original video frame group, and outputting coordinate information of a target detection object;
And acquiring corresponding image data from the corresponding video frames of the original video frame group according to the coordinate information.
In one embodiment, if the target remaining computing power resource is greater than a set computing power resource and less than the target required computing power resource, and the remaining memory resource is greater than the set memory resource, determining that the resource level of the image processing device is a second resource level; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
if the resource level is the second resource level and the scaling resolution is the first specified resolution, scaling each video frame in the original video frame group to the first specified resolution to obtain a scaled first video frame group;
processing each video frame in the first video frame group and outputting coordinate information of a target detection object;
and acquiring corresponding image data from the corresponding video frames of the first video frame group according to the coordinate information.
In one embodiment, if the target remaining power resource is equal to the set power resource, determining that the resource level of the image processing device is a third resource level if the remaining memory resource is greater than or equal to the target required memory resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
If the resource level is a third resource level and the zoom resolution is a second specified resolution, caching the original video frame group to a first cache queue;
scaling the resolution of each video frame in the original video frame group to the second designated resolution to obtain a scaled second video frame group; the frame following information of each video frame in the second video frame group comprises a matching mark and a frame identifier;
processing each video frame in the second video frame group and outputting coordinate information of a target detection object;
and acquiring image data of a target detection object from the video frames corresponding to the first cache queue according to the frame identification and the coordinate information based on the matching mark.
In one embodiment, if the target remaining power resource is equal to the set power resource, determining that the resource level of the image processing device is a fourth resource level if the remaining memory resource is greater than the set memory resource and less than the target required memory resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
If the resource level is a fourth resource level and the scaling resolution is a second specified resolution, scaling the resolution of each video frame in the original video frame group to a third specified resolution, and caching the video frames to a second cache queue;
scaling the video frame group scaled to the third specified resolution to the second specified resolution again to obtain a scaled third video frame group; the frame following information of each video frame in the third video frame group comprises a matching mark and a frame identifier; the third specified resolution is greater than the second specified resolution;
processing each video frame in the third video frame group and outputting coordinate information of a target detection object;
and acquiring image data of the target detection object from the video frames corresponding to the second buffer queue according to the frame identification and the coordinate information based on the matching mark.
In one embodiment, if the target remaining computing power resource is equal to the set computing power resource, determining that the resource level of the image processing device is a fifth resource level if the remaining memory resource is equal to the set computing power resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
If the resource level is a fifth resource level and the scaling resolution is a second specified resolution, scaling the resolution of each original video frame in the original video frame group to the second specified resolution to obtain a scaled fourth video frame group;
processing each video frame in the fourth video frame group and outputting coordinate information of a target detection object;
and acquiring corresponding image data from the corresponding video frames in the fourth video frame group according to the coordinate information.
In a second aspect, the present application also provides an image processing apparatus. The device comprises:
the acquisition module is used for acquiring an original video frame group;
a determining module, configured to determine a target device resource required for processing the original video frame group and a remaining device resource of the image processing device;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and the image processing module is used for processing the original video frame group based on the resource level and the scaling resolution and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring an original video frame group;
determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the scaling resolution.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an original video frame group;
determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment;
Determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the scaling resolution.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
acquiring an original video frame group;
determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the scaling resolution.
The image processing method, the image processing device, the computer equipment, the storage medium and the computer program product, when the original video frame group is subjected to image capture, the resource grade of the image processing equipment and the scaling resolution corresponding to the resource grade are determined according to the target equipment resources required by the original video frame group and the residual equipment resources of the image processing equipment; processing the original video frame group based on the resource level and the zoom resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the zoom resolution instead of capturing images of all images according to the designated resolution; and determining the corresponding resolution according to the actual equipment resources of the equipment, and under the condition of maximally utilizing the equipment resources, determining the corresponding resolution to capture the images, so that the definition of the captured images can be improved.
Drawings
FIG. 1 is a diagram of an application environment for an image processing method in one embodiment;
FIG. 2 is a flow chart of an image processing method in one embodiment;
FIG. 3 is a flow diagram of a method of determining a resource level of an image processing device in one embodiment;
FIG. 4 is a flow chart of an image processing method according to another embodiment;
FIG. 5 is a flow chart of an image processing method according to another embodiment;
FIG. 6 is a flow chart of an image processing method according to another embodiment;
FIG. 7 is a flow chart of an image processing method according to another embodiment;
FIG. 8 is a flow chart of an image processing method according to another embodiment;
FIG. 9 is a block diagram showing the structure of an image processing apparatus in one embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The image processing method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the image acquisition device 102 communicates with the image processing device 104 via a network. The data storage system may store data that the image processing device 104 needs to process. The data storage system may be integrated on the image processing device 104 or may be located on a cloud server or other network server. The image processing equipment acquires an original video frame group; determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment; determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the residual device resource; the original video frame group is processed based on the resource level and the scaling resolution, and image data of the detection object is acquired from the video frame of the resolution corresponding to the scaling resolution. Wherein the image capture device 102 may be, but is not limited to, various types of image capture devices, for example, the image capture device may be a different type of camera. The image processing apparatus 104 may be a server, which may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, an image processing method is provided, taking an example that the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
step S202, an original video frame set is acquired.
The original video frame group is obtained by decoding the obtained original video code stream. In the application scene, the acquired video images are encoded and compressed by the image acquisition equipment and then uploaded to the image processing equipment in the form of a code stream. The image acquisition equipment acquires an original video code stream in real time, and decodes the original video code stream to obtain an original video frame group.
In step S204, the target device resources required for processing the original video frame group and the remaining device resources of the image processing device are determined.
It can be appreciated that in an actual application scenario, for example, a security application scenario, a capture view of a target object in a video frame is required. Because the image processing equipment supports certain decoding capability and computing capability, the resolution of the image acquisition equipment exceeds the decoding capability of the image processing equipment, and the quality of the grabs is low, so that the corresponding scaling resolution is required to be determined according to the decoding capability and computing capability of the equipment, the quality of the grabs is ensured, and the definition of the grabs is improved.
The target equipment resources comprise target required memory resources and target required computing power resources, wherein the target required memory resources are memories required for storing original video frames, and the target required computing power resources are computing power resources required for analyzing the original video frame groups. The remaining device resources include remaining memory resources and target remaining computing power resources. The target remaining computing power resource may be a remaining computing power resource at a certain moment, or may be an average value of remaining computing power resources within a continuously specified duration, for example, the target remaining computing power resource is an average value of remaining computing power resources within 10 seconds continuously. The determination of the target remaining computing power resources may be determined according to actual requirements, and is not limited herein.
Step S206, determining the resource level of the image processing device and the zoom resolution corresponding to the resource level according to the target device resource and the residual device resource.
The image processing device can analyze the device resource use condition of the original video frame group according to the target device resource and the residual device resource, namely the resource grade of the image processing device can be determined. In order to ensure the image capturing quality and fully utilize the residual device resources of the image processing device, the scaling resolution corresponding to the resource level needs to be determined. And when the video frames with corresponding zoom resolutions are subjected to image capturing, the quality of the captured images is improved while equipment resources are fully utilized. It is understood that the correspondence between the resource level and the zoom resolution may be preconfigured according to the actual application.
The resource levels include a first resource level, a second resource level, a third resource level, a fourth resource level, a fifth resource level, and so on. The first resource level can be understood as that the image processing device can perform capture processing on the original video frame group, so that capture quality can be ensured, device resources are fully utilized, computing power resources are sufficient, and memory resources are sufficient. The second resource level may be understood as that when the image processing apparatus performs the capture processing on the original video frame set, the target remaining computing power resource can meet the set computing power resource, but cannot meet the actual requirement, and the remaining memory resource meets the actual requirement, that is, the computing power resource is tense and the memory resource is sufficient. The third resource level may be understood as that when the image processing apparatus performs the capture processing on the original video frame set, the remaining computing power resources of the image processing apparatus only can meet the set computing power requirement, and the remaining memory resources of the image processing apparatus meet the actual analysis requirement, that is, the computing power resources are insufficient and the memory resources are sufficient. The fourth resource level may be understood as being computationally inefficient and memory intensive, and the fifth resource level may be understood as being computationally efficient and memory inefficient.
The correspondence between the resource level and the scaling resolution includes: the scaled resolution corresponding to the first resource level may be an original resolution of the original video frame, the scaled resolution of the second resource level may be a first specified resolution, the scaled resolution of the third resource level may be a second specified resolution, the scaled resolution of the fourth resource level may be a third specified resolution, and the scaled resolution of the fifth resource level may be a second specified resolution.
Specifically, according to the size relation between the target device resource and the rest device resource, determining the resource level of the image processing device and obtaining the corresponding zoom resolution of the resource level. It is further understood that in the case of determining the resource level of the image processing apparatus and the scaling resolution corresponding to the resource level, the policy data of the original video frame capture processing in the case of different resource levels is different.
Step S208, the original video frame group is processed based on the resource level and the scaling resolution, and the image data of the detection object is acquired from the video frame of the resolution corresponding to the scaling resolution.
Where there is processing policy data for the respective original video frames based on the different resource levels and the respective scaling resolutions, and the respective resolution video frames for extracting the detection objects, which may be the scaling resolution video frames.
Specifically, the resource level and the scaling resolution of the image processing device are determined, and the original video frame set is processed according to the corresponding processing strategy data to obtain a processed video frame set, wherein the processed video frame set comprises the original video frame set. Analyzing the processed video frame group to obtain coordinate information of the detection object; corresponding image data is acquired from the video frames of the corresponding resolutions for extracting the detection objects according to the coordinate information. It can be understood that when determining the detection object, the target video frame can be determined first according to the frame identification, and the target video frame is processed; each frame of video in the processed video frame group can be analyzed, the detection object is determined, the frame identifier corresponding to the detection object is obtained, and the determination mode of the detection object is not limited.
In the image processing method, when the original video frame group is subjected to image capture, determining the resource level of the image processing equipment and the scaling resolution corresponding to the resource level according to the target equipment resource required by the original video frame group and the residual equipment resource of the image processing equipment; processing the original video frame group based on the resource level and the zoom resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the zoom resolution instead of capturing images of all images according to the designated resolution; and determining the corresponding resolution according to the actual equipment resources of the equipment, and under the condition of maximally utilizing the equipment resources, determining the corresponding resolution to capture the images, so that the definition of the captured images can be improved.
Before processing the original video frame group, it is necessary to determine a resource level of the image processing apparatus, and determine processing policy data of the original video frame according to the resource level. In one embodiment, determining a resource level of the image processing device according to a size relationship between the target demand memory resource and the remaining memory resource, and a size relationship between the target demand computing power resource and the target remaining computing power resource; the target remaining computing power resource is an average value of the target remaining computing power resource in the continuous appointed time length; according to the resource level, a scaling resolution of the video frame corresponding to the resource level is determined.
The method for determining the resource level of the image processing device, as shown in fig. 3, comprises the following steps:
step S302, obtaining target equipment resources required by an original video frame group and residual equipment resources of image processing equipment; the target device resources comprise target demand computing power resources and target demand memory resources, and the residual device resources comprise target residual computing power resources and residual memory resources.
The target required memory resource is determined according to the resolution of the video frame and the number of images to be cached in each frame in the actual application scene. For example, in one scenario, a 1080P image occupies about 3M of memory, and the number of required buffered images is 8, and the memory resources required to be occupied are 24M. The target required power resource is equal-scaled according to the power resource required for the image of the preset resolution, for example, equal-scaled according to the power of 6.25% required for the resolution of 1080P. The target remaining power resource is an average of remaining power resources within a continuously specified duration, e.g., the target remaining power resource may be an average of remaining power resources within 10 seconds of the continuously.
Step S304, judging the resource grade according to the target demand computing power resource, the target demand memory resource, the target residual computing power resource and the residual memory resource.
In step S306, if the target remaining computing power resource is greater than the target demand computing power resource and the remaining memory resource is greater than the target demand memory resource, determining the resource level of the image processing apparatus as the first resource level.
Wherein, in the case that the resource level of the image processing device is determined to be the first resource level, further, processing policy data of the original video frame group is determined, and the original video frame group is processed. The corresponding processing strategy data comprises the steps of directly processing the original video frame group, and adding a matching-free mark which does not need to be matched with the frame into the frame following information of each frame of video in the original video frame group. Further, the follow-up frame information includes a frame identification of each frame.
In step S308, if the target remaining computing power resource is greater than the set computing power resource and less than the target required computing power resource, and the remaining memory resource is greater than the set memory resource, determining that the resource level of the image processing apparatus is the second resource level.
The setting power resource may be, but not limited to, 6.25% of the power resource required by 1080P, and the setting power resource may be determined according to the actual requirement. The set memory resource may be set according to actual requirements, for example, may be a memory resource with 1080P resolution, which is not limited herein.
Further, after determining the resource level of the image processing device, determining processing policy data of the original video frame group, and processing the original video frame group. Under the condition that the resource level of the image processing equipment is determined to be the second resource level, the corresponding processing strategy data comprises the steps of scaling each video frame in the original video frame group to a first appointed resolution to obtain a scaled first video frame group; and processing the first video frame group, and adding a matching-free mark which does not need to be matched with the frame into the frame following information of each frame of video in the first video frame. It will be appreciated that the first specified resolution is determined in accordance with the resource level of the image processing apparatus.
In step S310, if the remaining memory resources are greater than or equal to the target required memory resources, the resource level of the image processing device is determined to be the third resource level.
Further, after determining the resource level of the image processing device, determining processing policy data of the original video frame group, and processing the original video frame group. The corresponding processing strategy data comprises the steps of caching an original video frame group into a first cache queue; scaling the resolution of each video frame in the original video frame group to a second designated resolution to obtain a scaled second video frame group; and adding a matching mark in the frame following information of each video frame in the second video frame group. It will be appreciated that the second specified resolution is determined based on the resource level of the image processing device. The second specified resolution is less than the first specified resolution, the first specified resolution being less than the original resolution of the original video frame. The second specified resolution may be, but is not limited to, 1080P resolution.
In step S312, if the target remaining computing power resource is equal to the set computing power resource, if the remaining memory resource is greater than the set memory resource and less than the target required memory resource, the resource level of the image processing apparatus is determined to be the fourth resource level.
Further, in the case where it is determined that the resource level of the image processing apparatus is the fourth resource level, processing policy data of the original video frame group is determined, and the original video frame group is processed. Scaling the resolution of each video frame in the original video frame group to a third designated resolution and caching the resolution to a second cache queue; and scaling the video frame group scaled to the third specified resolution to the second specified resolution again to obtain a scaled third video frame group, adding a matching mark in the frame following information of each video frame in the third video frame group, and using the video frame group in the second buffer queue for capture processing, wherein the third specified resolution is larger than the second specified resolution and smaller than the first specified resolution. The set memory resource is a memory resource required for analyzing an image of a set resolution, for example, the set memory resource may be an analysis requirement of 1080P resolution.
In step S314, if the target remaining computing power resource is equal to the set computing power resource, the resource level of the image processing apparatus is determined to be the fifth resource level if the remaining memory resource is equal to the set computing power resource.
And determining processing strategy data of the original video frame group and processing the original video frame group under the condition that the resource level of the image processing equipment is determined to be the fifth resource level. The corresponding processing strategy data comprises the steps of scaling the resolution ratio of each original video frame in the original video frame group to a second designated resolution ratio to obtain a fourth video frame group after scaling, adding a matching-free mark which does not need to be matched with frames in the frame following information of each frame of video in the fourth video frame group, and using the fourth video frame group for capture processing.
In the above embodiment, by determining the resource level of the image processing apparatus according to the target apparatus resource required by the original video frame group and the remaining apparatus resource of the image processing apparatus, processing the original video frame group based on the resource level of the image processing apparatus, determining the optimal video frame group for image capturing, the same scaling processing is avoided being performed on the original video frame group in the case that the resource levels of the image processing apparatuses are different, resulting in waste of apparatus resources of the image processing apparatus and affecting the quality of the captured image.
In the case of determining the resource level of the image processing apparatus and the scaling resolution corresponding to the resource level, in order to ensure the quality of the grabber, the original video frame group is processed based on the resource level and the scaling resolution, and a processed video frame group is obtained. The frame following information of each frame of video in the processed video frame group comprises a frame identification and a mark whether to be matched or not. If the video frames of the processed video frame group do not have the matching mark, when the original video frame group is processed, the image data of the detection object is obtained from the processed video frame group corresponding to the zoom resolution. If the processed video frames of the video frame group have the matching marks, the matching is needed to be removed from the buffer queue according to the frame identification of the frames, and the image data of the detection object is obtained from the video frames in the buffer queue. Wherein the resolution of the video frames in the buffer queue is determined according to the resource level of the image processing device.
In another embodiment, as shown in fig. 4, an image processing method is provided, taking an example that the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
step S402, an original video frame set is acquired.
In step S404, the target device resources required for processing the original video frame group and the remaining device resources of the image processing device are determined.
Step S406, determining a resource level of the image processing apparatus and a zoom resolution corresponding to the resource level according to the target apparatus resource and the remaining apparatus resources.
In step S408, if the resource level is the first resource level and the scaling resolution is the original resolution of the original video frame set, each video frame in the original video frame set is processed, and the coordinate information of the target detection object is output.
The first resource level can be understood as sufficient computing power resources, and can directly process the original video frame image and ensure the definition of the capture instruction.
Step S410, corresponding image data is obtained from the corresponding video frames of the original video frame group according to the coordinate information.
Specifically, under the condition that the resource level is the first resource level and the scaling resolution is the original resolution of the original video frame group, the original video frame group is used for capture processing, a matching-free mark which does not need to be matched with a frame is added into the frame following information of each frame of video in the original video frame group, each frame of video in the original video frame group is analyzed, coordinate information of a detection object is determined, and corresponding image data is obtained from corresponding video frames of the original video frame group according to the coordinate information. It can be understood that when the original video frame is analyzed, the corresponding target video frame can be identified and analyzed according to the frame identification of the video frame to be analyzed, the detection object in the target video frame is identified, the coordinate information of the detection object is output, the corresponding image data is obtained from the corresponding video frame of the original video frame group according to the coordinate information, and the image data is encoded.
In the above embodiment, under the condition that the resource level of the image processing device is determined to be the first resource level, the original video frame is directly processed, the captured image data of the detection object is obtained from the original video frame group, scaling of the original video frame group is not needed, full utilization of the device resource of the image processing device is ensured, and the detection accuracy and the definition of the capture quality are improved.
In another embodiment, as shown in fig. 5, an image processing method is provided, taking an example that the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
step S502, an original video frame set is acquired.
In step S504, the target device resources required for processing the original video frame group and the remaining device resources of the image processing device are determined.
Step S506, determining a resource level of the image processing apparatus and a zoom resolution corresponding to the resource level according to the target apparatus resource and the remaining apparatus resources.
In step S508, if the resource level is the second resource level and the scaling resolution is the first specified resolution, scaling each video frame in the original video frame set to the first specified resolution to obtain a scaled first video frame set.
Step S510, processing each video frame in the first video frame group, and outputting the coordinate information of the target detection object.
Step S512, corresponding image data is obtained from the corresponding video frames of the first video frame group according to the coordinate information.
Specifically, under the condition that the resource level is the second resource level and the scaling resolution is the first specified resolution, scaling the resolution of each video frame in the original video frame group to the first specified resolution to obtain a scaled first video frame group, and adding a matching-free mark which does not need to be matched with frames into frame following information of each video frame in the first video frame group. If the matching mark does not exist in the frame following information of the video frames of the first video frame group, each video frame in the first video frame group is directly processed, the coordinate information of the target detection object is output, and corresponding image data is obtained from the corresponding video frames of the first video frame group according to the coordinate information.
In the above embodiment, when the resource level of the image processing apparatus is determined to be the second resource level, the resolution of the video frames in the original video frame set is scaled to the first specified resolution, the respective video frames in the scaled first video frame set are processed, the corresponding image data is obtained from the corresponding video frames in the first video frame set, the original video frame set is properly scaled, so that the full utilization of the apparatus resources of the image processing apparatus is ensured, the accuracy of detection and the definition of the quality of the capture image are improved, that is, the apparatus calculation capability and the memory are reasonably used by obtaining the apparatus calculation capability and the memory use condition, and the resolution of the capture image is improved under the condition that the apparatus capability is fixed, so as to achieve the effect of improving the definition.
In another embodiment, as shown in fig. 6, an image processing method is provided, taking an example that the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
in step S602, if the resource level is the third resource level and the zoom resolution is the second specified resolution, the original video frame set is buffered to the first buffer queue.
Step 604, scaling the resolution of each video frame in the original video frame set to a second specified resolution, resulting in a scaled second video frame set.
Wherein the frame following information of each video frame in the second video frame group comprises a matching mark and a frame identification.
In step S606, each video frame in the second video frame set is processed, and the coordinate information of the target detection object is output.
Specifically, when the resource level of the image processing device is determined to be a third resource level, caching the original video frame group to a first cache queue; scaling the resolution of each video frame in the original video frame group to a second designated resolution to obtain a scaled second video frame group; and adding a matching mark in the frame following information of each video frame in the second video frame group. And processing each video frame in the scaled second video frame group, and outputting the coordinate information of the target detection object.
Step S608, based on the matching flag, the image data of the target detection object is obtained from the video frames corresponding to the first buffer queue according to the frame identification and the coordinate information.
Specifically, in order to ensure the quality of the captured image, a matched target video frame is determined from the original video frames in the first buffer queue according to the frame identification and the coordinate information based on the matching flag, the coordinate information is converted according to the resolution of the target video frame and the resolution of the video frames in the second video frame group, the target coordinate information in the target video frame is obtained, corresponding image data is acquired from the target video frame according to the target coordinate information, and the acquired image data is encoded. It can be understood that, according to the proportional relation of the resolutions between the video frames, the coordinate conversion can be implemented in the existing manner, which is not described herein.
In the above embodiment, in the case where it is determined that the resource level of the image processing apparatus is the third resource level, the coordinate information is obtained by scaling the resolution of the video frames in the original video frame group to the second specified resolution and by processing each video frame in the scaled second video frame group. The corresponding image data is determined from the original video frame group in the buffer queue through coordinate conversion, the original video frame group is properly scaled, the full utilization of equipment resources of the image processing equipment is ensured, the detection accuracy and the definition of the quality of the grabs are improved, namely, the equipment calculation force and the memory are reasonably used by acquiring the equipment calculation force and the memory service condition, and the resolution of the grabs is improved under the condition of certain equipment capacity so as to achieve the effect of improving the definition.
In another embodiment, as shown in fig. 7, an image processing method is provided, taking an example that the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
in step S702, if the resource level is the fourth resource level and the scaling resolution is the third specified resolution, scaling the resolution of each video frame in the original video frame set to the third specified resolution, and buffering the scaled resolution in the second buffer queue.
Step S704, the video frame group scaled to the third designated resolution is scaled to the second designated resolution again, so as to obtain a scaled third video frame group; the frame following information of each video frame in the third video frame group comprises a matching mark and a frame identification.
Wherein the third specified resolution is greater than the second specified resolution.
In step S706, each video frame in the third video frame group is processed, and the coordinate information of the target detection object is output.
Specifically, when the resource level of the image processing device is determined to be the fourth resource level, scaling the resolution of each video frame in the original video frame group to a third specified resolution, and buffering the video frames in the second buffer queue. Further, in order to avoid that the insufficient equipment resources cannot meet the image processing, the video frame group scaled to the third designated resolution is scaled to the second designated resolution again, a scaled third video frame group is obtained, and a matching mark is added in the frame following information of each video frame in the third video frame group. And processing each video frame in the third video frame group and outputting the coordinate information of the target detection object.
Step S708, based on the matching mark, the image data of the target detection object is obtained from the video frames corresponding to the second buffer queue according to the frame identification and the coordinate information.
Specifically, based on the matching flag, a matched target video frame is determined from the second buffer queue according to the frame identification and the coordinate information, the coordinate information is converted according to the resolution of the target video frame and the resolution of the video frame in the third video frame group, the target coordinate information in the target video frame is obtained, corresponding image data is obtained from the target video frame according to the target coordinate information, and the obtained image data is encoded.
In the above embodiment, in the case where it is determined that the resource level of the image processing apparatus is the fourth resource level, the second buffer queue is obtained by scaling the resolution of the video frames in the original video frame group to the third specified resolution. Further scaling to the second specified resolution on the basis of the third specified resolution, and processing each video frame in the scaled third video frame group to obtain coordinate information. The corresponding image data is determined from the original video frame group in the buffer queue through coordinate conversion, the original video frame group is properly scaled, the full utilization of equipment resources of the image processing equipment is ensured, the detection accuracy and the definition of the quality of the grabs are improved, namely, the equipment calculation force and the memory are reasonably used by acquiring the equipment calculation force and the memory service condition, and the resolution of the grabs is improved under the condition of certain equipment capacity so as to achieve the effect of improving the definition.
In another embodiment, as shown in fig. 8, an image processing method is provided, taking an example in which the method is applied to the image processing apparatus in fig. 1 as an illustration, comprising the steps of:
in step S802, if the resource level is the fifth resource level and the scaling resolution is the second specified resolution, scaling the resolution of each original video frame in the original video frame set to the second specified resolution to obtain a scaled fourth video frame set.
In step S804, each video frame in the fourth video frame group is processed, and the coordinate information of the target detection object is output.
Step S806, corresponding image data is obtained from the corresponding video frames in the fourth video frame group according to the coordinate information.
Specifically, when the resource level of the image processing device is determined to be the fifth resource level, scaling the resolution of each original video frame in the original video frame group to a second designated resolution to obtain a scaled fourth video frame group, and adding a matching-free mark which does not need to be matched with the frame in the frame following information of each frame of video in the fourth video frame group. And processing the video frames in the fourth video frame group after scaling, outputting coordinate information of the target detection object, and acquiring corresponding image data from the corresponding video frames in the fourth video frame group according to the coordinate information.
In the above embodiment, when it is determined that the resource level of the image processing apparatus is the fifth resource level, the resolution of the video frames in the original video frame group is scaled to the second specified resolution, so as to obtain the scaled fourth video frame group, and the video frames of the fourth video frame group are directly processed, and corresponding image data is obtained from the corresponding video frames of the fourth video frame group according to the coordinate information. Based on the resource grade of the image processing equipment, by properly scaling the original video frame group, the full utilization of equipment resources of the image processing equipment is ensured, and the accuracy of detection and the definition of the quality of the grabs are improved, namely, the equipment calculation force and the memory are reasonably used by acquiring the equipment calculation force and the memory service condition, and the resolution of the grabs is improved under the condition of certain equipment capability so as to achieve the effect of improving the definition.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiments of the present application also provide an image processing apparatus for implementing the above-mentioned image processing method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the image processing apparatus provided below may refer to the limitation of the image processing method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 9, there is provided an image processing apparatus including: a decoding module 902, a determining module 904, and an image processing module 906, wherein:
a decoding module 902, configured to obtain an original video frame set.
A determining module 904, configured to determine a target device resource required for processing the original video frame set and a remaining device resource of the image processing device.
And determining the resource level of the image processing equipment and the scaling resolution corresponding to the resource level according to the target equipment resource and the residual equipment resource.
An image processing module 906, configured to process the original video frame set based on the resource level and the scaling resolution, and acquire image data of the detection object from the video frame of the resolution corresponding to the scaling resolution.
When the original video frame group is grabbed, the image processing device determines the resource grade of the image processing device and the zoom resolution corresponding to the resource grade according to the target device resource required by the original video frame group and the residual device resource of the image processing device; processing the original video frame group based on the resource level and the zoom resolution, and acquiring image data of a detection object from the video frames with the resolution corresponding to the zoom resolution instead of capturing images of all images according to the designated resolution; and determining the corresponding resolution according to the actual equipment resources of the equipment, and under the condition of maximally utilizing the equipment resources, determining the corresponding resolution to capture the images, so that the definition of the captured images can be improved.
In another embodiment, an image processing apparatus is provided, which includes, in addition to the decoding module 902, the determining module 904, and the image processing module 906: an image data acquisition module and a scaling module, wherein:
the determining module 904 is further configured to determine a resource level of the image processing device according to a size relationship between the target required memory resource and the remaining memory resource and a size relationship between the target required computing power resource and the target remaining computing power resource; the target remaining computing power resources are average values of the remaining computing power resources corresponding to each time node in the continuous appointed time length; according to the resource level, a scaling resolution of the video frame corresponding to the resource level is determined.
The image processing module 906 is further configured to process each video frame in the original video frame set if the resource level is the first resource level and the scaling resolution is the original resolution of the original video frame set, and output coordinate information of the target detection object.
And the image data acquisition module is used for acquiring corresponding image data from the corresponding video frames of the original video frame group according to the coordinate information.
And the scaling module is used for scaling each video frame in the original video frame group to the first appointed resolution if the resource level is the second resource level and the scaling resolution is the first appointed resolution, so as to obtain a scaled first video frame group.
The image processing module 906 is further configured to process each video frame in the first video frame group, and output coordinate information of the target detection object.
The image data acquisition module is further used for acquiring corresponding image data from the corresponding video frames of the first video frame group according to the coordinate information.
The scaling module is further configured to buffer the original video frame group to the first buffer queue if the resource level is the third resource level and the scaling resolution is the second specified resolution;
scaling the resolution of each video frame in the original video frame group to a second designated resolution to obtain a scaled second video frame group; the frame following information of each video frame in the second video frame group comprises a matching mark and a frame identification.
The image processing module 906 is further configured to process each video frame in the second video frame set, and output coordinate information of the target detection object.
The image data acquisition module is further used for acquiring image data of the target detection object from the video frames corresponding to the first cache queue according to the frame identification and the coordinate information based on the matching mark.
And the scaling module is further configured to scale the resolution of each video frame in the original video frame group to the third specified resolution and buffer the scaled resolution to the second buffer queue if the resource level is the fourth resource level and the scaled resolution is the third specified resolution.
Scaling the video frame group scaled to the third specified resolution to the second specified resolution again to obtain a scaled third video frame group; the frame following information of each video frame in the third video frame group comprises a matching mark and a frame identifier; the third specified resolution is greater than the second specified resolution.
The image processing module 906 is further configured to process each video frame in the third video frame group, and output coordinate information of the target detection object.
The image data acquisition module is further used for acquiring image data of the target detection object from the video frames corresponding to the second cache queue according to the frame identification and the coordinate information based on the matching mark.
And the scaling module is further configured to scale the resolution of each original video frame in the original video frame set to the second specified resolution if the resource level is the fifth resource level and the scaling resolution is the second specified resolution, so as to obtain a scaled fourth video frame set.
The image processing module 906 is further configured to process each video frame in the fourth video frame group, and output coordinate information of the target detection object.
The image data acquisition module is further used for acquiring corresponding image data from the corresponding video frames in the fourth video frame group according to the coordinate information.
The respective modules in the above-described image processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store raw video frame set data required for the image processing method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image processing method.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims (10)

1. An image processing method, the method comprising:
acquiring an original video frame group;
determining target equipment resources required for processing the original video frame group and remaining equipment resources of the image processing equipment;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
And processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame corresponding to the scaling resolution.
2. The method of claim 1, wherein the target device resources comprise target demand memory resources and target demand computing power resources, the remaining device resources comprise remaining memory resources and target remaining computing power resources, and wherein determining the scaling resolution of the original video frame set based on the target device resources and the remaining device resources comprises:
determining a resource level of the image processing device according to a size relationship between the target required memory resource and the remaining memory resource and a size relationship between the target required computing power resource and the target remaining computing power resource; the target residual computing power resource is an average value of the residual computing power resources corresponding to each time point in the continuous appointed time length;
and determining the zoom resolution of the video frame corresponding to the resource level according to the resource level.
3. The method of claim 2, wherein if the target remaining power resource is greater than the target demand power resource and the remaining memory resource is greater than the target demand memory resource, determining that the resource class of the image processing device is a first resource class; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
If the resource level is a first resource level and the scaling resolution is the original resolution of the original video frame group, processing each video frame in the original video frame group, and outputting coordinate information of a target detection object;
and acquiring corresponding image data from the corresponding video frames of the original video frame group according to the coordinate information.
4. The method of claim 2, wherein if the target remaining power resource is greater than a set power resource, less than the target demand power resource, and the remaining memory resource is greater than a set memory resource, determining that the resource class of the image processing device is a second resource class; the image processing of the original video frame group based on the resource level and the scaling resolution, obtaining image data of a detection object from a video frame with a resolution corresponding to the scaling resolution, includes:
if the resource level is the second resource level and the scaling resolution is the first specified resolution, scaling each video frame in the original video frame group to the first specified resolution to obtain a scaled first video frame group;
processing each video frame in the first video frame group and outputting coordinate information of a target detection object;
And acquiring corresponding image data from the corresponding video frames of the first video frame group according to the coordinate information.
5. The method according to claim 2, wherein in case the target remaining power resource is equal to a set power resource, determining that the resource level of the image processing device is a third resource level if the remaining memory resource is greater than or equal to the target demand memory resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
if the resource level is a third resource level and the zoom resolution is a second specified resolution, caching the original video frame group to a first cache queue;
scaling the resolution of each video frame in the original video frame group to the second designated resolution to obtain a scaled second video frame group; the frame following information of each video frame in the second video frame group comprises a matching mark and a frame identifier;
performing image processing on each video frame in the second video frame group, and outputting coordinate information of a target detection object;
And acquiring image data of a target detection object from the video frames corresponding to the first cache queue according to the frame identification and the coordinate information based on the matching mark.
6. The method according to claim 2, wherein in case the target remaining power resource is equal to a set power resource, determining that the resource class of the image processing device is a fourth resource class if the remaining memory resource is larger than the set memory resource and smaller than the target required memory resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
if the resource level is a fourth resource level and the scaling resolution is a third specified resolution, scaling the resolution of each video frame in the original video frame group to the third specified resolution, and caching the video frame to a second cache queue;
scaling the video frame group scaled to the third specified resolution to the second specified resolution again to obtain a scaled third video frame group; the frame following information of each video frame in the third video frame group comprises a matching mark and a frame identifier; the third specified resolution is greater than the second specified resolution;
Performing image processing on each video frame in the third video frame group, and outputting coordinate information of a target detection object;
and acquiring image data of the target detection object from the video frames corresponding to the second buffer queue according to the frame identification and the coordinate information based on the matching mark.
7. The method according to claim 2, wherein in case the target remaining power resource is equal to a set power resource, determining that the resource level of the image processing device is a fifth resource level if the remaining memory resource is equal to the set power resource; the processing the original video frame group based on the resource level and the scaling resolution, and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution, including:
if the resource level is a fifth resource level and the scaling resolution is a second specified resolution, scaling the resolution of each original video frame in the original video frame group to the second specified resolution to obtain a scaled fourth video frame group;
performing image processing on each video frame in the fourth video frame group, and outputting coordinate information of a target detection object;
And acquiring corresponding image data from the corresponding video frames in the fourth video frame group according to the coordinate information.
8. An image processing apparatus, characterized in that the apparatus comprises:
the decoding module is used for acquiring an original video frame group;
a determining module, configured to determine a target device resource required for processing the original video frame group and a remaining device resource of the image processing device;
determining a resource level of the image processing device and a scaling resolution corresponding to the resource level according to the target device resource and the remaining device resources;
and the image processing module is used for processing the original video frame group based on the resource level and the scaling resolution and acquiring image data of a detection object from the video frame with the resolution corresponding to the scaling resolution.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
CN202310090033.9A 2023-01-17 2023-01-17 Image processing method, device, computer equipment and storage medium Pending CN116129316A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310090033.9A CN116129316A (en) 2023-01-17 2023-01-17 Image processing method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310090033.9A CN116129316A (en) 2023-01-17 2023-01-17 Image processing method, device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116129316A true CN116129316A (en) 2023-05-16

Family

ID=86302563

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310090033.9A Pending CN116129316A (en) 2023-01-17 2023-01-17 Image processing method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116129316A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116886880A (en) * 2023-09-08 2023-10-13 中移（杭州）信息技术有限公司 Method, device, equipment and computer program product for adjusting surveillance video

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116886880A (en) * 2023-09-08 2023-10-13 中移（杭州）信息技术有限公司 Method, device, equipment and computer program product for adjusting surveillance video
CN116886880B (en) * 2023-09-08 2023-12-26 中移（杭州）信息技术有限公司 Method, device, equipment and computer program product for adjusting surveillance video

Similar Documents

Publication Publication Date Title
JP7026878B2 (en) Quantization parameter prediction with maintained visual quality using deep neural network
CN108154518B (en) Image processing method and device, storage medium and electronic equipment
CN108399052B (en) Picture compression method and device, computer equipment and storage medium
JP6016332B2 (en) Image processing apparatus and image processing method
CN111898416A (en) Video stream processing method and device, computer equipment and storage medium
Zhang et al. A joint compression scheme of video feature descriptors and visual content
EP2255533A2 (en) Capturing event information using a digital video camera
CN109740589B (en) Asynchronous object ROI detection method and system in video mode
US9305603B2 (en) Method and apparatus for indexing a video stream
CN111241938A (en) Face recognition method and device based on image verification and computer equipment
US9256789B2 (en) Estimating motion of an event captured using a digital video camera
CN116129316A (en) Image processing method, device, computer equipment and storage medium
US20110069146A1 (en) System and method for processing images
JP7255841B2 (en) Information processing device, information processing system, control method, and program
CN115115968A (en) Video quality evaluation method and device and computer readable storage medium
CN114356243A (en) Data processing method and device and server
CN111080683A (en) Image processing method, image processing device, storage medium and electronic equipment
CN111243046B (en) Image quality detection method, device, electronic equipment and storage medium
CN115567711A (en) Desktop image dynamic acquisition method and device and computer readable storage medium
CN114584781A (en) Video compression method and device and computer readable storage medium
CN110489592B (en) Video classification method, apparatus, computer device and storage medium
CN113179375A (en) Exposure processing method, exposure processing apparatus, electronic device, storage medium, and program product
JP6247062B2 (en) Image management apparatus, image management method, and program
CN111598053B (en) Image data processing method and device, medium and system thereof
CN117522951B (en) Fish monitoring method, device, equipment and storage 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