Pedestrian detection method based on weighted part model and selective search segmentation

A pedestrian detection and component model technology, applied in the field of pedestrian detection, can solve problems such as the decrease in the detection rate of deformable component models and the limited visibility of pedestrian contours, and achieve the effects of high real-time performance, high processing speed, and speed improvement.

Active Publication Date: 2015-12-09
河北燕大燕软信息系统有限公司
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in crowded scenes, due to the existence of partial occlusion, the visibility of pedestrian silhouettes is limited, and the detection rate of deformable part models decreases.

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 weighted part model and selective search segmentation
  • Pedestrian detection method based on weighted part model and selective search segmentation
  • Pedestrian detection method based on weighted part model and selective search segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The method proposed in this paper will be further explained in combination with the HOG feature pyramid detection process of pedestrians:

[0046] Such as figure 1 In the flow chart of the shown method of the present invention, firstly, the training model is carried out, and the specific process is followed by training samples, initializing the root filter, using standard SVM training, merging containers, using LSVM training, initializing component filters, using LSVM training again, Update component weights to obtain weighted component models. Then carry out image detection. The specific process is to input the image, segment the image (the segmentation process includes selective search, and obtain a useful bounding box), convert the weighted component model model into a cascaded model model, obtain the feature pyramid of the image, and classify the image. Combined detection, get the pedestrian area, remove the repeated area, and get the final pedestrian detection res...

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 pedestrian detection method based on a weighted part model and selectiv search segmentation. The pedestrian detection method based on weighted part model consists of a weighted part model training part and a pedestrian human face detection part. A model construction process comprises steps of setting various weights on various parts on the basis of the construction process of a transformable part model and according to the different conditions of shielding parts of the pedestrian in a crowded scene, and utilizing a hidden support vector machine to perform training weight. The pedestrian detection process comprises steps of extracting HOG characteristic pyramid from an image, performing selective search and segmentation on the image in order to achieve the fact of employing less effective windows to contain more objects, and, on the basis of that, and adopting cascading detection based on threshold cutting to detect the pedestrian. The invention solves the problem of missing detection in a crowding scnene from two aspects, and reduces the invention and improves the pedestrian detection accuracy.

Description

technical field [0001] The invention relates to the field of pedestrian detection, in particular to a pedestrian detection method using a weight-based deformable component model and selective search segmentation. Background technique [0002] Pedestrian detection based on static images is to separate the human body appearing in the image from the background and precisely locate it. It is widely used in human-computer interaction, intelligent video surveillance, intelligent transportation and other fields. It is the basis of target classification and behavior understanding. One of the important topics in the field of vision research. However, when pedestrians are the subject of detection, they often appear in very complex backgrounds, and pedestrians have both rigid and flexible characteristics, and their appearance is easily affected by clothing, scale, occlusion, posture and viewing angle, which also makes pedestrian detection It has not only become one of the key points i...

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
CPCG06V40/164G06F18/23
Inventor 闻佳王雪平孔令富
Owner 河北燕大燕软信息系统有限公司
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
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