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

Target detection method based on channel pruning and full convolution depth learning

A deep learning and target detection technology, applied in the field of computer vision, can solve problems such as sharing, and achieve the effect of reducing reconstruction error, speeding up inference time, and speeding up feature extraction.

Active Publication Date: 2018-07-17
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Purpose of the invention: The purpose of the present invention is to solve the problem of sharing calculations in the existing deep learning target detection method, and improve the reasoning speed of target detection, and propose a target detection method based on channel pruning and full convolution deep learning

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
  • Target detection method based on channel pruning and full convolution depth learning
  • Target detection method based on channel pruning and full convolution depth learning
  • Target detection method based on channel pruning and full convolution depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0048] The purpose of the present invention is to provide a target detection method based on channel pruning and full convolution deep learning. Pruning to achieve the purpose of accelerating feature extraction; then, using the linear least squares method to minimize the reconstruction error and reduce the impact of the pruning channel on the network; finally, model the VGG-16 fully convolutional network and share the region proposal The calculation of the region of interest of the network achieves the purpose of speeding up the inference time.

[0049] A preferred embodiment of the target detection method based on channel pruning and full convolution deep learning of the present invention specifically includes the following steps:

[0050] Step A, using the lasso regression method to realize pruning of redundant channels in each layer of the convoluti...

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 present invention discloses a target detection method based on channel pruning and full convolution depth learning. The method is characterized in that: firstly, a lasso regression method is usedto implement redundant channel pruning on each channel of a convolutional neural network; then, a linear minimum multiplication is used to reconstruct the minimum error; and finally, the full convolutional neural network is used to acquire the region of interest and accelerate the target detection. Experiments conducted by the general Caltech pedestrian detection data set show that the scheme proposed by the present invention can effectively improve the accuracy and rapidity of pedestrian detection.

Description

technical field [0001] The invention relates to a target detection method, in particular to a target detection method based on channel pruning and full convolution deep learning, belonging to the field of computer vision. Background technique [0002] Object detection is one of the most popular research directions in the field of computer vision, and it has a wide range of applications in society, life, rule of law, military and other fields. At present, target detection has been widely used in video surveillance systems, GPS unmanned navigation, license plate detection systems, intelligent alarm systems, robot control systems and other application directions. The principle of target detection can be seen everywhere in our daily life. [0003] Existing object detection methods are classified into traditional object detection methods and object detection based on deep learning methods. Traditional object detection methods are roughly divided into two types, methods based on ...

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): G06T7/00G06N3/04
CPCG06T7/0002G06T2207/20104G06T2207/20081G06N3/045
Inventor 许正朱松豪荆晓远石路路
Owner NANJING UNIV OF POSTS & TELECOMM
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com