Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video matching method and device, computer equipment and storage medium

A matching method and video technology, applied in the field of image processing, can solve problems such as inaccurate video matching results and inaccurate fusion features

Pending Publication Date: 2020-09-15
上海眼控科技股份有限公司
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above technology has the problem of inaccurate fusion features, which will lead to inaccurate video matching results.

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 matching method and device, computer equipment and storage medium
  • Video matching method and device, computer equipment and storage medium
  • Video matching method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0060] Video re-ID (re-identification, re-identification) is a derivative task of image re-ID, which is more in line with the actual scene requirements in real life. In video re-ID, it is generally aimed at a target video or a picture sequence composed of multiple video frames, and these video sequences contain the same target person or vehicle. The purpose of video re-ID is: given the target person or vehicle In the video sequence to be retrieved, match the video sequence containing the target person appearing in other cameras. Due to the continuous improvement of the de...

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 matching method and device, computer equipment and a storage medium. The method comprises the following steps: inputting an acquired video source into a feature extraction network for feature extraction to obtain a feature map and a feature vector corresponding to each video frame in the video source, wherein the video source comprises at least one video frame, andeach video frame comprises a to-be-detected object; inputting the feature map corresponding to each video frame into a similarity extraction network for similarity calculation to obtain the similarity between every two adjacent video frames in the video source; performing fusion processing on the feature vectors corresponding to the video frames based on the similarity between every two adjacentvideo frames to obtain fusion features corresponding to the video source; determining a target video sequence matched with the video source in a video library according to the fusion feature corresponding to the video source and the preset video library, wherein the target video sequence comprises at least two target video sources. By adopting the method, the accuracy of a video matching result can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a video matching method, device, computer equipment and storage medium. Background technique [0002] Person Re-Identification (Re-ID for short), also known as cross-mirror tracking technology, refers to retrieving the same target person under different cameras through computer vision technology. When computer vision technology is used to realize pedestrian re-identification, the feature extraction of the target object on each video frame in the video is generally performed through a deep learning network to obtain the extracted features of each video frame, and then the extracted features of each video frame The features are fused to obtain a fusion feature, and the fusion feature is matched with the fusion features corresponding to other videos to determine whether the targets in different videos are the same target. [0003] When fusing the extracted featur...

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): G06K9/00G06K9/62
CPCG06V20/48G06V20/46G06F18/22G06F18/253G06F18/214
Inventor 周康明戚风亮
Owner 上海眼控科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products