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

A Video Retrieval and Matching Method Based on Dynamic Programming

A dynamic programming and matching method technology, applied in the field of video retrieval, can solve the problems that the video retrieval scheme is not suitable for large-scale video retrieval, etc., and achieve the effect of improving retrieval recall, accuracy and confidence

Active Publication Date: 2022-04-01
HANGZHOU BINGJIAN TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem that the video retrieval scheme in the prior art is not suitable for large-scale video retrieval; it provides a video retrieval matching method based on dynamic programming

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
  • A Video Retrieval and Matching Method Based on Dynamic Programming
  • A Video Retrieval and Matching Method Based on Dynamic Programming
  • A Video Retrieval and Matching Method Based on Dynamic Programming

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] A kind of video retrieval matching method based on dynamic programming in this embodiment, such as figure 1 shown, including the following steps:

[0069] S1: The video is evenly drawn at a fixed frequency, and each frame is extracted with a pre-trained neural network to extract the feature vector.

[0070] In this embodiment, for existing stock or newly uploaded videos, frames are drawn evenly at 1 frame per second. Each frame of picture extracts feature vectors through a large-scale pre-trained CNN network.

[0071] The CNN network here can be a picture feature extraction network pre-trained on any big data, such as resnet-18 trained on imagenet, or the ViT network released by Google. Its input is an image, and the output is a one-dimensional feature vector.

[0072] For example, the video has 10 seconds, one frame per second, and each frame is extracted to a 1000-dimensional vector through the CNN network, and the frame feature vector sequence is a 10x1000-dimensi...

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 video retrieval and matching method based on dynamic programming. The present invention mainly includes the following steps: extracting video frame feature vectors through the trained picture feature extraction network; registering the stored video into the retrieval library A by splitting mirrors, and extracting high-frequency vectors and registering them in the high-frequency library B; The video is segmented, and the method of nearest neighbor retrieval is used for video retrieval and recall; the similarity matrix of the segment is restored for the retrieved and recalled video, and the dynamic programming algorithm is used to extract the continuous optimal path of similar segments; through the maximum similar segment and search video-level similarity Fine sorting. The dynamic programming-based video retrieval and matching method based on the method proposed by the present invention has high accuracy and recall in the test data set, and has good robustness.

Description

technical field [0001] The invention relates to the field of video retrieval, in particular to a video retrieval and matching method based on dynamic programming. Background technique [0002] At present, the competitive landscape of the short video industry tends to be stable, and the overall development of the industry has entered a mature stage. However, millions of authors enter various online platforms through their accounts and publish tens of millions of works every day. Although the time is short, the content involves background music, video materials, subtitles and other fields, frequent infringement and piracy, and prominent copyright issues . [0003] Video retrieval is a very important but very challenging problem. Some short video creators re-edit other people’s original videos without permission and upload them to the platform as short videos, gaining traffic and advertisements in a short period of time without spending much money. into. However, it is very ...

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 Patents(China)
IPC IPC(8): G06F16/73G06F16/783
CPCG06F16/73G06F16/783
Inventor 丁勇朱子奇丁柱罗绍仪
Owner HANGZHOU BINGJIAN TECH CO LTD