Deep learning based video retrieval method

A deep learning and video technology, applied in the field of computer vision, can solve problems such as inaccurate description of high-dimensional feature differences, and achieve the effects of improving matching accuracy, precise retrieval, and avoiding false detection and missed detection

Active Publication Date: 2018-06-29
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, because video is a complex data structure, existing feature matching methods cannot accurately describe the diffe

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
  • Deep learning based video retrieval method
  • Deep learning based video retrieval method
  • Deep learning based video retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific implementation of the present invention will be further described below in conjunction with the accompanying drawings, but the implementation and protection of the present invention are not limited thereto. realized or understood.

[0030] The embodiment of the present invention provides a video retrieval method based on deep learning, the steps are as follows: figure 1 Shown; The concrete implementation steps of described method are as follows:

[0031] Network training part:

[0032] Step 1) Construct a video preprocessing network, using the network structure of Inception Net V3. Inception Net is a 22-layer deep convolutional neural network. The last layer of the network has the best classification effect, so the output of the last layer is selected as the input feature vector.

[0033] Step 2) Train the video preprocessing network. Use YouTuBe-8M as the training data set, which has 8 million videos and a total of 4800 label categories. In order to e...

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 deep learning based video retrieval method which mainly comprises the following parts: performing video pre-processing by using a convolutional neural network; extracting feature vectors of the video after pre-processing by using a long short-term memory; and finally learning by a similarity learning algorithm to obtain a distance calculation method, and performing similarity calculation according to the method and ranking, so as to obtain a video retrieval result. According to the method disclosed by the invention, scene segmentation and key frame selection are performed by the convolutional neural network, and high-level semantics representing video is extracted, so as to acquire a proper quantity of key frame sequences, and effectively avoid false detection andmissing inspection in shot segmentation. According to method disclosed by the invention, time-order characteristics of the video are extracted by the long short-term memory, so as to obtain a more accurate retrieval result. By similarity learning and a text based matching method, matching accuracy of a similarity measurement method can be promoted. By adopting the method disclosed by the invention, accurate retrieval on a large scale of videos can be realized.

Description

technical field [0001] The invention belongs to the field of computer vision, and especially designs a video retrieval method utilizing deep learning and digital processing technology. Background technique [0002] In recent years, the Internet and multimedia technology have been widely developed and used, and the trend has swept the world. Massive video data is generated in people's daily life, work and study. Facing the explosive growth of multimedia data, we increasingly need a method that can accurately and effectively retrieve and manage massive video. [0003] A complete video retrieval process usually includes three main steps: video preprocessing, that is, the process of removing redundant frames, including shot detection and key frame extraction; video feature extraction; feature matching, that is, similarity calculation. In the field of video preprocessing, existing technologies mainly use pixel difference method, histogram method and edge detection method to perf...

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): G06F17/30G06N3/04
CPCG06F16/783G06N3/045
Inventor 丁泉龙廖奕铖韦岗李杰
Owner SOUTH CHINA UNIV OF TECH
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