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

A single image pedestrian detection method

A pedestrian detection, single image technology, applied in the field of computer vision and image processing, can solve problems such as inaccuracy, pedestrian detection is easily affected by the environment, etc.

Inactive Publication Date: 2019-03-08
北京畅景立达软件技术有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is to provide a single image pedestrian detection method to solve the disadvantages of pedestrian detection in the prior art that are easily affected by the environment and not accurate enough

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 single image pedestrian detection method
  • A single image pedestrian detection method
  • A single image pedestrian detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. The single image pedestrian detection method proposed by the present invention consists of two parts, the first part is pedestrian detector training, and the second part is pedestrian detection.

[0051] First, the pedestrian detector training part is introduced.

[0052] Step 1: Data preparation, set pedestrian dataset and background dataset

[0053] : Set up the pedestrian dataset and mark the human body rectangle

[0054] collection M Pedestrian data set composed of several images, each image has a width greater than 20 pixels and a height greater than 50 pixels, recorded as ,image contains pedestrian sample, , mark the image on the first j The location of each pedestrian sample is: , where is the coordinates of the uppe...

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 discloses a single image pedestrian detection method, comprising: collecting a pedestrian data set in a real scene, marking the position of pedestrians, and simultaneously collecting a background data set that does not contain pedestrians as training data, using the gradient amplitude Eigen and linear support vector machines to train a "coarse" pedestrian detector to quickly filter non-pedestrian windows. Use this fast pedestrian detector to detect on the pedestrian data set, record the positions of all output windows, and save them as positive windows and negative windows according to the marked pedestrian positions. Using these window samples, a deep network is trained based on cascaded autoencoders to distinguish between pedestrian windows and non-pedestrian windows. Output the final pedestrian detector from "coarse" to "fine", so as to realize the pedestrian detection of the input image.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, and in particular relates to a pedestrian detection method of a single image. Background technique [0002] Pedestrian detection is a hot and difficult point in computer vision technology. It can be understood as judging whether the input image contains pedestrians. If it contains pedestrians, it will give the location information of pedestrians. In recent years, pedestrian detection technology has been widely used in human behavior analysis, video surveillance, and vehicle assistance. Areas such as driving and disaster rescue play a role. [0003] The core issues in pedestrian detection technology can be attributed to three aspects: feature extraction, classification and positioning. The research on these three aspects in the prior art can be classified into two categories: methods based on background modeling and methods based on statistical learning, both of which...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/10G06F18/23G06F18/2451G06F18/214
Inventor 不公告发明人
Owner 北京畅景立达软件技术有限公司