Video processing method and device, terminal and storage medium
A video processing and video technology, which is applied in the field of video processing, can solve the problems of loss of effective image information, decreased target detection accuracy, and inability to detect targets, so as to achieve reduced loss, avoid loss of effective image information, and reduce computational complexity. Effect
Active Publication Date: 2021-07-13
杭州赛鲁班网络科技有限公司
View PDF9 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, for the original image with a super-large resolution or a large resolution, when the content detection is performed directly according to the above-mentioned traditional image processing method, the effective information of the image will be seriously lost, resulting in the failure to detect the corresponding target, and the detection accuracy is seriously reduced.
Therefore, the existing image processing methods, when performing content detection on high-resolution or ultra-large-resolution videos, are likely to cause serious loss of effective image information and low computing performance, resulting in a decrease in target detection accuracy or even undetectable problems.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0039] Such as figure 1 Shown, a kind of video processing method comprises the following steps:
[0040] S1: Divide the original video to be processed into image groups, and make N frames of continuous images a Group of Pictures (GoP for short); where N is an integer greater than 1; that is, an image group contains N consecutive frames Image. For example, the first consecutive N frames of images are divided and determined as GoP1, and the consecutive N frames of images are divided and determined as GoP2, and so on, as figure 2 shown.
[0041] The value of N depends on factors such as the frame rate fr of the original video, the calculation time time for each frame image feature extraction, and the delay value delay tolerated by the system.
[0042] N is positively correlated with the frame rate fr of the original video and the delay value delay tolerated by the system, and negatively correlated with the calculation time time for feature extraction of each frame of image. T...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a video processing method and device, a terminal and a storage medium, and the method comprises the steps: carrying out the image grouping and dividing of a to-be-processed original video, enabling N frames of continuous images to be an image group, carrying out the image feature extraction of each frame of image in the image group, including steps of selecting a region to be subjected to feature extraction from each frame of image, carrying out image feature extraction calculation, and outputting features of each frame of image; and calculating the video feature of the current image group according to the feature of each frame of image in the image group. The method has the advantages that effective information of the image is prevented from being lost, and the target detection precision is improved.
Description
technical field [0001] The present invention relates to the technical field of video processing, in particular to a video processing method, device, terminal and storage medium. Background technique [0002] With the gradual and widespread application of smart TVs, mobile phones, etc., and the evolution and application of artificial intelligence technology, image sensing technology and other related technologies, image processing technology is getting more and more attention, and the resolution of original images is getting more and more high. [0003] When processing these original images, a neural network model based on deep learning is usually used for inference. Generally speaking, for mobile terminals such as smartphones based on Android or iOS platforms or cloud service platforms with high concurrency and high throughput, the computing power and memory capacity of a single unit are relatively limited, and the implementation of larger or more complex Neural network mo...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/46
Inventor 黄敦笔杜武平
Owner 杭州赛鲁班网络科技有限公司