Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian detection method and device

A pedestrian detection and pedestrian technology, applied in the field of communication, can solve the problems of pedestrians not considered and the detection results inaccurate.

Inactive Publication Date: 2016-06-15
ZTE CORP
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a pedestrian detection method and device to at least solve the problem in the related art that the pedestrian detection method does not take into account the edge map of the target edge, resulting in inaccurate detection results

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 and device
  • Pedestrian detection method and device
  • Pedestrian detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0162] In this embodiment, a pedestrian profile template is constructed on the known pedestrian database, and the image to be detected is preprocessed, and pedestrian detection in the image is realized by matching the pedestrian profile template with the preprocessed image.

[0163] In this embodiment, the image preprocessing process only needs to implement edge detection. Since there is no height model, a fixed single-scale FDCM method is used in the detection process. Figure 12 is a schematic diagram of pedestrian detection according to a preferred embodiment of the present invention Figure 1 ,Such as Figure 12 shown, including the following:

[0164] Steps S1201-S1203 are the same as the above-mentioned steps S1001-S1003, and will not be repeated here.

[0165] Step S1204, input the image to be detected, perform preprocessing 2 on the image to be detected to obtain an edge map, first convert the original image into a grayscale image; then use the Sobel operator to calc...

Embodiment 2

[0171] In this embodiment, a pedestrian profile template is constructed on the known pedestrian database, a height model is constructed for the input video image, and the video image to be detected is preprocessed by matching the adaptive height pedestrian profile template with the preprocessed image. Pedestrian detection in video images.

[0172] In this embodiment, the image preprocessing process uses background modeling combined with edge detection, and multi-scale FDCM is used to construct a height model. Since the height model is known, the detection process is processed by a single-scale FDCM method. Figure 13 is a schematic diagram of pedestrian detection according to a preferred embodiment of the present invention Figure II ,Such as Figure 13 shown, including the following:

[0173] Steps S1301-S1303 are the same as the above-mentioned steps S1001-S1003, and will not be repeated here.

[0174] Step S1304, input a video sequence, and select an area of ​​interest; ...

Embodiment 3

[0186] In this embodiment, the pedestrian profile template is constructed on the known pedestrian database, the known video image height model is updated, and the video image to be detected is preprocessed, by combining the adaptive height pedestrian profile template with the preprocessed image Perform matching to realize pedestrian detection in video images. The image preprocessing process adopts background modeling combined with edge detection, and uses multi-scale FDCM to update the height model. Since the height model is known, the detection process is processed by single-scale FDCM method. Figure 14 is a schematic diagram of pedestrian detection according to a preferred embodiment of the present invention Figure three ,Such as Figure 14 shown, including the following:

[0187] Steps S1401-S1403 are the same as the above-mentioned steps S1001-S1003, and will not be repeated here.

[0188] Step S1404, input a video sequence, and select an area of ​​interest;

[0189]...

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 discloses a pedestrian detection method and device. The method comprises: performing a monitored video sequence to obtain the foreground picture of the video sequence; obtaining the edge map of a selected area according to the foreground picture; processing the edge points of the edge map to obtain a skeleton map to be detected; and performing pedestrian detection of the skeleton map to be detected according to a pedestrian contour template established in advance. According to the invention, the problem is solved that the method of pedestrian detection does not take an edge map of a target edge into account and results in inaccurate detection results, and the effect of accurate detection results is achieved.

Description

technical field [0001] The present invention relates to the communication field, in particular, to a pedestrian detection method and device. Background technique [0002] At present, pedestrian detection is widely used in various fields such as intelligent human-computer interaction and video surveillance, and has aroused extensive research interest. Existing pedestrian detection techniques are mainly divided into three categories: background model-based pedestrian detection, classifier-based pedestrian detection, and template matching-based pedestrian detection. Pedestrian detection based on the background model is fast, but the accuracy is relatively low. Classifier-based pedestrian detection methods have made great progress in recent years. The core is to select the features that can best distinguish different targets, and then train the classifier offline. This type of method usually has better detection results, but in In some cases, it will fail, such as: the install...

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
CPCG06V10/40G06V30/194
Inventor 邓硕董振江田玉敏郑海红
Owner ZTE CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com