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

Viewing angle classification method and device of video, equipment and storage medium

A classification method and viewing angle technology, which is applied in the field of image processing, can solve problems such as unsatisfactory effects and different viewing angles of 6A videos, and achieve the effects of reducing manual classification work, avoiding light differences, and improving classification speed

Pending Publication Date: 2021-04-16
ZHUZHOU CSR TIMES ELECTRIC CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the driver behavior recognition system based on 6A video has a good effect in the early trials, but it is based on the premise of analyzing the video of similar angles of view, and the difference in the installation position and angle of the 6A camera on the locomotive will lead to 6A video. Different angles of view, taking the Harmony electric locomotive as an example, there are two kinds of perspective pictures, the right and the right rear, and the same model is used to analyze the pictures of different perspectives, and the effect is not ideal

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
  • Viewing angle classification method and device of video, equipment and storage medium
  • Viewing angle classification method and device of video, equipment and storage medium
  • Viewing angle classification method and device of video, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Traditional video classification or image classification methods cannot accurately classify video perspectives due to their insufficient resolution of features and the weak connection between image semantics and image feature expressions. Taking the perspective classification of the 6A video of the locomotive on-board safety protection system (6A system) as an example, the image features of the locomotive cab in the 6A video are due to the difference in illumination (such as: the difference in the intensity of light during the day, the difference in the intensity of infrared light when imaging at night) ), the presence or absence of the driver, and the location of the driver present different image features. However, the objects of the video screen are all locomotive cabs, and videos from different perspectives will also show certain common features. , therefore, for the same viewing angle, how to eliminate specific features becomes the key while enhancing common feature...

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 discloses a visual angle classification method for a video, and the method comprises the steps: firstly extracting a plurality of frames of images from a target video when the visual angle of the target video is classified, inputting the images into a pre-trained single-frame image classification model, and obtaining the probability value that each frame of image belongs to different visual angles; obtaining a target probability value of the target video belonging to each visual angle based on the specificity characteristic and the generality characteristic of each frame of image, and automatically obtaining a visual angle classification result of the target video in a mode of comparing the target probability value belonging to the same visual angle with a probability value threshold. Visibly, the method and device can achieve the automatic classification of the video view angles, reduce the manual classification work, and improve the classification speed. Moreover, the common characteristics and the specific characteristics between different frames are also considered, so that the visual angles are accurately classified; the invention further discloses a viewing angle classification device of avideo and equipment and a readable storage medium.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to a method, device, equipment and storage medium for classifying video angles. Background technique [0002] In recent years, with the development of video analysis technology, the analysis and identification of locomotive driver behavior is gradually changing from manual analysis to intelligent analysis. One of the intelligent analysis methods requires the help of the existing locomotive on-board safety protection system (6A system). Video surveillance equipment. [0003] At present, the driver behavior recognition system based on 6A video has a good effect in the early trials, but it is based on the premise of analyzing the video of similar angles of view, and the difference in the installation position and angle of the 6A camera on the locomotive will lead to 6A video. Different angles of view, taking the Harmony electric locomotive as an example, ther...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08
Inventor 彭联贴熊敏君崔宵洋颜家云黎孟张慧源李晨刘昕武褚金鹏刘邦繁孙木兰刘雨聪
Owner ZHUZHOU CSR TIMES ELECTRIC CO LTD