Video behavior identification method based on compression reward and punishment mechanism

A recognition method, reward and punishment technology, applied in the field of computer vision, can solve the problems of poor robustness, large amount of calculation, inability to extract video motion information, etc., and achieve the effect of easy training, small amount of calculation and parameter.

Inactive Publication Date: 2020-05-19
SHANXI UNIV
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a video behavior recognition method based on a compression reward and punishment mechanism to solve the technic

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 behavior identification method based on compression reward and punishment mechanism
  • Video behavior identification method based on compression reward and punishment mechanism
  • Video behavior identification method based on compression reward and punishment mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Experiments were carried out on the mainstream video recognition data sets UCF101 and HMDB51. The video behavior recognition method based on the compression reward and punishment mechanism includes the following steps:

[0050] Step 1, divide the video to be recognized into multiple segments of equal length, specifically: divide the video to be recognized into K segments at equal time intervals{S 1 ,S 2 …S k}, where K chooses 3. Randomly extract stacked optical flow images and RGB video frames from each segment;

[0051] Step 2: Input the stacked optical flow images and RGB video frames into the time and space dual-stream convolutional neural network with compression reward and punishment mechanism, and weight the features extracted by the network through compression and reward and punishment operations. According to the weighted time and space The features make a preliminary prediction of the video behavior on the two channels of time and space respectively. The tim...

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 belongs to the field of computer vision, and relates to a video behavior identification method based on a compression reward and punishment mechanism. The technical problems that an existing video behavior recognition method is large in calculated amount, poor in robustness, low in accuracy and the like are mainly solved. According to the invention, a convolutional neural network containing a compression reward and punishment mechanism is designed for video behavior identification. The network is constructed based on a time segmentation network. The method comprises the followingsteps: firstly, dividing a video into three segments, randomly extracting an optical flow image and an RGB frame from each segment, respectively inputting the optical flow image and the RGB frame into a time and space network, weighting the extracted features through compression and reward and punishment operations, and respectively carrying out preliminary prediction on behaviors of the weightedtime and space features on a time channel and a space channel; fusing the preliminary prediction result of each segment to obtain a video-level prediction result; and finally, fusing the video-levelprediction results to obtain a video behavior recognition result. Experiments are carried out on data sets UCF101 and HMDB51, and results show that compared with other models, the model has higher accuracy.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a video behavior recognition method based on a compression reward and punishment mechanism. Background technique [0002] Video behavior recognition is currently a hot spot in the field of computer vision, and its purpose is to automatically analyze ongoing behavior from a video or image sequence. [0003] Video behavior recognition is divided into traditional methods and methods based on deep learning. Traditional methods include dense trajectory algorithm and improved dense trajectory algorithm. The basic idea of ​​the dense trajectory algorithm is to use the optical flow field to obtain the trajectory in the video sequence, and then calculate the direction gradient histogram, optical flow direction histogram and other features along the trajectory; the improved dense trajectory algorithm uses the optical flow between two frames of video before and after. Streams an...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/40G06V20/46G06N3/045G06F18/2415G06F18/254
Inventor 张丽红郭磊
Owner SHANXI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap