Pedestrian detection method based on deep learning and multi-feature point fusion

A technology of pedestrian detection and deep learning, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problem of mutual occlusion of pedestrians, and achieve the effect of improving accuracy and robustness

Inactive Publication Date: 2017-09-08
SUN YAT SEN UNIV +1
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the shortcomings of existing pedestrian detection methods, the present invention proposes a pedestrian detection method based on deep learning and multi-feature point fusion, which can effectively overc

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
  • Pedestrian detection method based on deep learning and multi-feature point fusion
  • Pedestrian detection method based on deep learning and multi-feature point fusion
  • Pedestrian detection method based on deep learning and multi-feature point fusion

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0019] Example

[0020] A pedestrian detection method based on deep learning and multi-feature point fusion, including training phase and detection phase.

[0021] In the training phase, first collect pedestrian images in the application scenario and mark the head and shoulders of the pedestrians in the image, and then use these pedestrian samples for model training. The model training is divided into two steps: 1) Take the pedestrian's head and shoulders image as the training sample and use the Triplet Loss method to train a binary classification model of the pedestrian's head and shoulders; 2) Use the model parameters obtained in step 1) to train Part of the parameters of the pedestrian detection model are initialized by means of "transfer learning". As the model used in the final detection stage, the pedestrian detection model adopts an end-to-end training method, including the functions of candidate area extraction, pedestrian feature extraction and feature classification.

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 relates to a pedestrian detection method based on deep learning and multi-feature point fusion. The pedestrian detection method is characterized by at a training stage, firstly acquiring a pedestrian image under an application scene, marking the head and shoulder parts of the pedestrians in the image, and then using the pedestrian samples for the model training, wherein the model training comprises two steps of 1) taking the head and shoulder images of the pedestrians as the training samples, training a dichotomy model of the head and shoulder parts of the pedestrians; 2) using the model parameters obtained by the training in the step 1) to initialize partial parameters of a pedestrian detection model in a transfer learning manner. The pedestrian detection method of the present invention can overcome the problem that the pedestrians shield mutually to a certain extent, adopts a deep learning method to extract the pedestrian features, can better overcome the actual application problem that the factors, such as the pedestrian clothing, postures, backgrounds, illumination conditions, etc., change, also can effectively overcome the problems of the pedestrian multiple postures, the pedestrian multiple scales, the pedestrian mutual shielding, etc., and enables the pedestrian detection accuracy and robustness to be improved substantially.

Description

technical field [0001] The invention relates to the technical fields of image processing and computer vision, in particular to a pedestrian detection method based on deep learning and multi-feature point fusion. Background technique [0002] As an important branch of artificial intelligence, computer vision involves cutting-edge technologies in many fields such as image processing, machine learning, pattern recognition, and automatic control. Since the development of computer vision, it has been widely used in many fields such as security monitoring, intelligent transportation, automatic driving, intelligent robot, industrial inspection and aerospace. [0003] Object detection is a hot topic in the field of computer vision, among which pedestrian detection has long been a hot topic in academia and industry. Pedestrian detection technology is that for a given image or video, it is necessary for the computer to automatically determine whether there are pedestrians in the imag...

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): G06K9/00G06K9/62
CPCG06V40/23G06F18/24765G06F18/253G06F18/214
Inventor 刘宁黄德亮姚磊王作辉袁德胜
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