Video target detection method based on deep learning

A technology of object detection and deep learning, applied in the field of video object detection based on deep learning, can solve the problems of hindering application, high research cost, and insufficient integration of video time and space context information, so as to improve accuracy and take into account accuracy and real-time effects

Active Publication Date: 2019-04-05
SUN YAT SEN UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technology has the following defects: (1) The feature extraction method based on manual design usually requires relevant domain knowledge or a large amount of statistical data, thus requiring a huge research cost; affect its accuracy
(2) The calculation amount of the feature extraction method based on deep learning is generally huge, which hinders the application in the actual scene
(3) The current target detection...

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 target detection method based on deep learning
  • Video target detection method based on deep learning
  • Video target detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 Shown flow chart, the steps of the present invention include:

[0043] S1: Normalize the training image to a size of 600×1000 pixels, and initialize the parameters of the convolutional neural network;

[0044] S2: Training backbone network, time-space feature extraction network and detection network;

[0045] S21: Randomly select two frames of images within n frames of the same video as training samples. In the specific embodiment of the present invention, n is taken as 10. Since there is no concept of key frames and non-key frames in training, the two frames of images are used in training. The previous frame in is used as the reference frame I k , the latter frame is used as the predicted frame I i ;

[0046] S22: set the reference frame I k As input, through the backbone network N feat , extract image features, and output the corresponding reference frame feature map f k , its formula is expressed as follows:

[0047] f k =N feat (I k )

...

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 target detection method based on deep learning, and is applied to the field of video target detection. According to the method, the convolutional neural network is usedfor extracting image features, and time-is provided; And the spatial feature extraction network is used for extracting spatial context and time context information of the video, fusing image featureswith time and spatial context information, updating a feature map output by the backbone network, and finally inputting the obtained feature map into the detection network to obtain a final detectionresult, thereby giving consideration to the accuracy and real-time performance of target detection. According to the method, the detection accuracy and real-time performance are effectively improved.

Description

technical field [0001] The present invention relates to the field of object detection, and more specifically, to a video object detection method based on deep learning. Background technique [0002] In recent years, deep learning has made unprecedented breakthroughs in the field of computer vision. Through the structure of multi-layer neural network, the overall information of the image is integrated, and the image features are expressed from a higher and more abstract level. At present, the deep learning model based on convolutional neural network (CNN) is widely used in target detection, and has been proved to be better than traditional manual feature methods. [0003] At present, target detection methods are mainly divided into two categories: one is the target detection method based on manual feature extraction, and the other is the target detection method based on deep learning feature extraction. Typical manual features include shape, contour information, etc., and ca...

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): G06K9/00G06K9/32G06T7/269G06N3/04
CPCG06T7/269G06V20/40G06V10/25G06N3/045
Inventor 郑慧诚罗子泉
Owner SUN YAT SEN UNIV
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