A deep network pedestrian detection method based on shallow feature fusion guidance

A feature fusion, pedestrian detection technology, applied in biometric recognition, neural learning methods, biological neural network models, etc., can solve problems such as missed detection of pedestrian detection algorithms, and achieve good results in solving missed detection, detection accuracy and speed.

Pending Publication Date: 2019-03-29
TAIYUAN UNIV OF TECH
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies in the prior art, the present invention provides a deep network pedestrian detection method based on shallow feat

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
  • A deep network pedestrian detection method based on shallow feature fusion guidance
  • A deep network pedestrian detection method based on shallow feature fusion guidance
  • A deep network pedestrian detection method based on shallow feature fusion guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] (1) Network structure design

[0047] In order to improve the accuracy of pedestrian detection, effectively solve the problem of missed detection in complex scenes and when the target is too small, and enhance the generalization ability of deep learning. Based on Faster R-CNN algorithm detection. Using shallow feature fusion to guide the deep features of the convolutional network, the directional gradient histogram feature, texture feature and convolution feature are fused, with deep learning as the core and shallow features as the guide, realizing the complementary advantages of shallow learning and deep learning. The network structure of the present invention such as figure 1 shown. This network structure design framework includes convolutional layers, pooling layers, and fully connected layers. And an activation function is used in each convolutional layer. After the last convolutional layer, the RPN network is used. The RPN network includes a convolutional layer...

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 the technical field of computer vision object detection, more specifically, to a deep network pedestrian detection method based on shallow feature fusion guidance. On the basis of CNN detection algorithm, a pedestrian detection method in deep network based on shallow feature fusion is proposed. Through the fusion of directional gradient histogram, improved texture featuresand depth network features, accurate pedestrian features are obtained, which are guided by shallow features with depth learning as the core, and complementary advantages of shallow learning and depthlearning are realized. The results show that the improved method has good performance in detection accuracy and speed. the method effectively solves the technical problem of missing detection in complex scenarios and small targets.

Description

technical field [0001] The invention relates to the technical field of computer vision target detection, and more specifically, to a deep network pedestrian detection method based on shallow feature fusion guidance. Background technique [0002] In recent years, the advantages of the entire digital and networked video surveillance system have become more and more obvious. Its high degree of openness, integration and flexibility provides a broader development space for the development of the entire society's informatization. Pedestrian detection is one of its key technologies. However, due to the complexity of the scene where pedestrians are located, different shapes, and distances, it has become a focus to design a robust and accurate pedestrian detection algorithm. [0003] At present, there are two main categories of methods for pedestrian detection: methods based on manual features and methods based on deep convolutional neural networks (Convolutional Neural Networks, CN...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06N3/045G06F18/253
Inventor 邓红霞马垚杨晓峰李海芳杨雅茹
Owner TAIYUAN 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