Unlock instant, AI-driven research and patent intelligence for your innovation.

Video data processing method and device

A technology of video data and processing methods, applied in the field of image processing, can solve the problems of motion blur, drop, inaccurate target detection results, etc., to achieve the effect of eliminating spatial errors and improving accuracy

Pending Publication Date: 2020-11-10
BEIJING INST OF ENVIRONMENTAL FEATURES
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to solve the problem that the performance of the detection algorithm drops sharply and the target detection result is inaccurate due to problems such as motion blur and occlusion widely existing in the video when the existing single-frame detection algorithm is used to process the video frame by frame

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video data processing method and device
  • Video data processing method and device
  • Video data processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] figure 1 It is a schematic flowchart of the main flow of the video data processing method in Embodiment 1 of the present invention. Such as figure 1 As shown, the video data processing method provided by the embodiment of the present invention includes:

[0030] Step S101: Input the current frame image into the feature extraction network to obtain the feature map of the current frame image.

[0031] Wherein, the current frame image is a frame image extracted from the video to be detected. In this step, the current frame image is input into the feature extraction network to extract rich features from the current frame image. Exemplarily, the feature extraction network may use a convolutional neural network, such as VGG, Resnet (residual network) and other networks.

[0032] Step S102: Determine the optical flow information between the current frame image and the historical frame image, and perform spatial alignment processing on the feature map of the historical fram...

Embodiment 2

[0043] figure 2 It is a schematic flowchart of the main flow of the video data processing method in Embodiment 2 of the present invention. Such as figure 2 Shown, the video data method of the embodiment of the present invention comprises:

[0044] Step S201: Input the current frame image into the feature extraction network to obtain the feature map of the current frame image.

[0045] Wherein, the current frame image is a frame image extracted from the video to be detected. In this step, the current frame image is input into the feature extraction network to extract rich features from the current frame image. Exemplarily, the feature extraction network may use a convolutional neural network, such as VGG, or a Resnet (residual network), FPN (feature map pyramid network) and other networks.

[0046] In an optional implementation, considering that there are often different targets of different sizes and scales in the image, it is easy to miss detection only from a single-sc...

Embodiment 3

[0068] image 3 It is a schematic diagram of the main components of the video data processing device in Embodiment 3 of the present invention. Such as image 3 As shown, the video data processing device 300 of the embodiment of the present invention includes: a feature extraction module 301 , a feature alignment module 302 , a fusion processing module 303 , and a detection module 304 .

[0069]The feature extraction module 301 is configured to input the current frame image into the feature extraction network to obtain a feature map of the current frame image.

[0070] Wherein, the current frame image is a frame image extracted from the video to be detected. Specifically, the feature extraction module 301 inputs the current frame image into the feature extraction network to extract rich features from the current frame image. Exemplarily, the feature extraction network may use a convolutional neural network, such as VGG, Resnet (residual network) and other networks.

[0071]...

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

No PUM Login to View More

Abstract

The invention relates to a video data processing method and device, and relates to the technical field of image processing. The method comprises the following steps: inputting a current frame image into a feature extraction network to obtain a feature map of the current frame image; determining optical flow information between the current frame image and a historical frame image, and performing spatial alignment processing on a feature map of the historical frame image and a feature map of the current frame image according to the optical flow information; wherein the historical frame image isone or more frames of images adjacent to the current frame image in a video; performing fusion processing on the feature map of the current frame image and the feature map of the historical frame image after spatial alignment processing to obtain a fused feature map; and performing target key point detection on the fused feature map to obtain a target key point detection result. Through the abovesteps, the problems that the performance of the detection algorithm is sharply reduced and the target detection result is inaccurate due to the problems of motion blur, shielding and the like widely existing in the video can be solved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a video data processing method and device. Background technique [0002] Human key point detection studies how to accurately identify and locate each key point of the human body in the image. It is the basis of many computer vision applications such as action recognition and human-computer interaction. [0003] With the development of deep learning, deep neural networks have been applied to human key point detection, and the accuracy of human key point detection has been greatly improved. At present, according to whether it is necessary to detect the global human body first, the human body key point detection algorithm can be divided into two types: "bottom-up" and "top-down". Among them, the "bottom-up" algorithm does not need to detect the global human body in the image first, it directly uses the neural network to detect the key points that may exist in the i...

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
no application Login to View More
IPC IPC(8): G06K9/00G06K9/46G06N3/04G06T3/40G06T5/50
CPCG06T5/50G06T3/40G06V40/103G06V20/46G06V10/462G06N3/045
Inventor 张樯李斌赵凯李司同
Owner BEIJING INST OF ENVIRONMENTAL FEATURES
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com