Method for improving target detection performance by improving target classification and positioning accuracy

A target detection and target classification technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as inaccurate positioning, slow training speed, and computer memory consumption, and achieve reasonable design, good effect, and accuracy The effect of classification

Inactive Publication Date: 2017-11-03
ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION +1
View PDF9 Cites 58 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although researchers have proposed many target detection algorithms based on deep learning convolutional neural networks, and these algorithms have achieved good results, there are still many aspects to be improved, such as c...

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
  • Method for improving target detection performance by improving target classification and positioning accuracy
  • Method for improving target detection performance by improving target classification and positioning accuracy
  • Method for improving target detection performance by improving target classification and positioning accuracy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0039] A method to improve object detection performance by improving object classification and localization accuracy, such as figure 1 As shown, firstly, in order to obtain more image information, input the picture with the ground truth of the object into the VGG-16 convolutional neural network to extract image features, and then perform multi-layer fusion of image features to form multiple Feature map; then in order to quickly obtain the object candidate frame, the target candidate frame is generated on the convolutional layer 5 feature map according to a certain aspect ratio and size, and mapped to the multi-feature map for cropping; then in order to obtain more information about the candidate frame , perform multi-feature connection on the clipping results, and input them to the fully connected layer; finally, in order to achieve accurate an...

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 method for improving target detection performance by improving target classification and positioning accuracy. The method is characterized by extracting image characteristics according to a convolution neural network framework, selecting the first M layers of convolution layers to be output and carrying out characteristic fusion so as to form a multi-characteristic characteristic graph; carrying out grid division on the convolution layer M, and predicting target candidate frames with the fixed number and size in each grid; mapping the candidate frames to the characteristic graph for cutting, and carrying out multi-characteristic connection on cutting results; and passing the above results through a whole connection layer, classifying the image characteristics through the Softmax classification algorithm and using the overlapping area loss function to carry out online iteration regression positioning so as to obtain the final target detection result. According to the invention, the method is properly designed; characteristics are extracted through the convolution neural network, and multilayer fusion is performed on the image characteristics; and finally, the Softmax classification algorithm is used for classifying the image characteristics and the overlapping area loss function is used to carry out positioning, so a good target detection result is acquired.

Description

technical field [0001] The invention belongs to the technical field of target detection, in particular to a method for improving target detection performance by improving target classification and positioning accuracy. Background technique [0002] In the perception engineering of human beings in the material world, more than 80% of the information comes from vision. The image is a reflection of objective reality in a certain sense. It transmits information to human beings in different modes, and as an important information carrier, it has the characteristics of intuition, rich content and easy communication. Therefore, various applications based on image processing technology have emerged as the times require. Image target recognition and detection technology is one of the most typical application technologies. The purpose of computer vision research is to use computers to realize human perception, recognition and understanding of the objective world. Object Detection is ...

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): G06K9/62G06K9/46G06N3/04
CPCG06N3/04G06V10/44G06F18/285G06F18/214G06F18/253
Inventor 娄英欣周芸付光涛姜竹青门爱东
Owner ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION
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