An Infrared Pedestrian Saliency Detection Method Based on Probability Propagation

A detection method and remarkable technology, applied in image enhancement, instruments, biological models, etc., and can solve problems such as difficult to apply to complex scenes

Inactive Publication Date: 2020-10-20
BEIHANG UNIV
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing saliency models for infrared images often cannot propose effective features that can reflect salient target features, and are difficult to apply to more complex scenes

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
  • An Infrared Pedestrian Saliency Detection Method Based on Probability Propagation
  • An Infrared Pedestrian Saliency Detection Method Based on Probability Propagation
  • An Infrared Pedestrian Saliency Detection Method Based on Probability Propagation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to better understand the technical solutions of the present invention, the implementation manners of the present invention will be further described below in conjunction with the accompanying drawings.

[0077] Flow chart of the present invention is as figure 1 Shown, a kind of infrared pedestrian saliency detection method based on probability propagation of the present invention, its specific implementation steps are as follows:

[0078] Step 1: Image preprocessing;

[0079] First, the input image is divided into many similar gray levels by superpixel segmentation, the superpixels on the border are reserved, and the average position and average color of each superpixel are calculated;

[0080]

[0081] Step 2: Local stability based on MSER;

[0082] First extract the largest stable extremum region in the infrared image; first binarize the image, and the binarization threshold is set to [0,255]. In the process of changing the threshold, the number of conn...

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

An infrared pedestrian saliency detection method based on probability propagation, the steps are as follows: 1: Image preprocessing; 2: Combine MSER extraction and brightness filtering to obtain local stability based on MSER; 3: First calculate the brightness contrast of each superpixel , on this basis, add weights as a supplement, and get the brightness contrast combined with vertical edges; 4: Construct a saliency propagation model, and achieve the purpose of saliency fusion and optimization through continuous mutual guidance update; through the above steps, for infrared pedestrians The image can get very good saliency detection results, pedestrians are completely highlighted, and the background is almost completely suppressed. It has practical application value in other image processing fields such as target segmentation, target tracking and target retrieval.

Description

[0001] (1) Technical field [0002] The invention relates to an infrared pedestrian saliency detection method based on probability propagation, belonging to the fields of computer vision and digital image processing. It has broad application prospects in the fields of target segmentation and target recognition. [0003] (2) Background technology [0004] Saliency detection focuses on important and prominent regions in the image. This feature makes saliency widely used in vision topics such as object segmentation, image compression, and object detection. However, applying saliency to infrared pedestrian images is still challenging for existing algorithms, but at the same time, this research is also of great practical significance, because infrared pedestrian detection has important applications in the field of intelligent transportation. [0005] Previous saliency models mainly studied the underlying features of salient objects such as color, orientation, and texture. With the ...

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): G06K9/00G06N3/00G06T7/00
CPCG06N3/002G06T7/0002G06T2207/20021G06T2207/30196G06T2207/10048G06V40/103G06V2201/07
Inventor 李露郑玉周付根
Owner BEIHANG 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