Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Pedestrian detection method

A pedestrian detection, pedestrian technology, applied in the field of computer vision and pattern recognition

Inactive Publication Date: 2014-11-26
成都六活科技有限责任公司
View PDF3 Cites 63 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The present invention improves on the deficiencies of existing pedestrian detection methods to produce a robust and efficient pedestrian detector adapted to changing scenes, and proposes a pedestrian detection method

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
  • Pedestrian detection method
  • Pedestrian detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The embodiment of the present invention proposes a pedestrian detection method, such as image 3 shown, including the following steps:

[0028] Step S1: Prepare the pedestrian positive sample set P (including front, side, and back) and negative sample set N required for training the convolutional neural network. The positive and negative samples that are publicized and recognized in the industry with good effects and rich postures are collected Pedestrian samples in the dataset and some surveillance videos;

[0029] Step S2: preprocessing the sample set and normalizing it to a uniform scale, and generating a data file for training the convolutional neural network; the scale is 64*128 pixels;

[0030] Step S3: Design the structure of the convolutional neural network, perform training, and obtain the weight connection matrix W when the network converges, which will be used in the subsequent detection process;

[0031] Step S4: Carry out adaptive background modeling on t...

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

Provided is a pedestrian detection method. The pedestrian detection method comprises the following steps that a pedestrian positive sample set and a pedestrian negative sample set needed for training a convolutional neural network are prepared; the sample sets are preprocessed and normalized to conform to a unified standard, and a data file is generated; the structure of the convolutional neural network is designed, training is carried out, and a weight connection matrix is obtained during convergence of the network; self-adaptive background modeling is carried out on videos, information of moving objects in each frame is obtained, coarse selection is carried out on detected moving object regions at first, the regions with height to width ratios unsatisfying requirements are excluded, and candidate regions are generated; each candidate region is input into the convolutional neural network, and whether pedestrians exist is judged.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and in particular relates to a pedestrian detection method suitable for intelligent video surveillance. Background technique [0002] Intelligent video surveillance technology is an emerging research direction in the field of computer vision in recent years. It is a computer vision technology based on machine learning and artificial intelligence. It takes pedestrians, vehicles and other moving objects in the video scene as the main research and analysis objects. In the field of intelligent video surveillance research, the research on pedestrian detection technology has attracted the attention of the industry. [0003] In terms of security and law, the intelligent video surveillance system processes and analyzes the video information of the surveillance scene transmitted from the surveillance camera, and gives early warning to suspicious people and events in the scene, thereb...

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): G06K9/66G06K9/46
Inventor 叶茂王梦伟李旭东彭明超苟群森
Owner 成都六活科技有限责任公司
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
Eureka Blog
Learn More
PatSnap group products