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

Video retrieval method based on deep learning and hash coding

A hash coding and deep learning technology, applied in the field of computer vision, can solve the problems of high computing cost, low efficiency, and long time cost of distance measurement, and achieve the effect of speeding up matching, accurate retrieval results, and reducing storage cost

Active Publication Date: 2017-10-03
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main problem with this scheme is that the distance measurement takes a lot of time, especially when the video contains thousands or even tens of thousands of frames of images, this retrieval method will become very inefficient; there are also some methods that take the video as a whole. Modeling representations, such as one of the representative methods, are modeled by covariance statistics, but there is a problem of excessive computational overhead

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 retrieval method based on deep learning and hash coding
  • Video retrieval method based on deep learning and hash coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the purpose, technical solution and advantages of the present invention more clear, the image retrieval method based on deep learning and hash coding provided in the embodiments of the present invention will be described below with reference to the accompanying drawings.

[0032] Deep learning originated from artificial neural networks. In the field of image or video retrieval, deep learning can combine the underlying features of image or video frame image data to form higher-level representation attribute categories or features to discover distributed feature representations of image or video data, thereby Imitate the human brain mechanism to explain image or video data; hash coding is an algorithm with fast query capability and low memory overhead. In the field of image or video retrieval, image or video content can be expressed as binary by using hash coding hash sequence, and use this sequence to represent the features of the image or video.

[0033...

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 network training method for video data on the basis of deep learning and hash coding. The method comprises the following steps: extracting a feature matrix of a video sample by using a deep neural network; carrying out modeling by using the acquired feature matrix of the video sample as a whole body to obtain high-dimensional real value representation of the video sample; and further representing the obtained high-dimensional real value representation into binary hash coding by using a deep network.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a video retrieval method based on deep learning and hash coding. Background technique [0002] With the development of science and technology, the world today has entered the era of big data, especially the rapid growth of video data resources, so the retrieval of large-scale video data to meet user needs has brought new challenges to the field of retrieval technology. A video can be viewed as a collection of continuous still images, that is, a three-dimensional object composed of two-dimensional digital images and a temporal dimension. The problem to be solved for video retrieval is, on the one hand, due to the large scale of the retrieved database, it is necessary to represent the sample data more efficiently to meet the real-time requirements and the constraints of storage overhead; on the other hand, when users use static images to retrieve In the case of video, it i...

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): G06F17/30G06N3/08
CPCG06F16/43G06F16/434G06N3/08
Inventor 陈熙霖乔师师王瑞平
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com