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

Infrared image remarkable characteristic detection method combining objectivity and background property

An infrared image and feature detection technology, applied in the field of image understanding, can solve problems such as failure to detect significant feature areas, interfere with significant areas, etc., and achieve the effect of improving accuracy and recognition efficiency, high accuracy and recognition efficiency

Inactive Publication Date: 2015-11-04
NANJING UNIV OF SCI & TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the above methods only use pixel-level differences. When detecting salient regions, some salient regions are suppressed or background noise seriously interferes with salient regions, and the complete salient feature regions cannot be detected.

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
  • Infrared image remarkable characteristic detection method combining objectivity and background property
  • Infrared image remarkable characteristic detection method combining objectivity and background property
  • Infrared image remarkable characteristic detection method combining objectivity and background property

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Such as figure 1 As shown, a method for detecting salient features of an infrared image combining objectivity and background of the present invention comprises the following steps:

[0019] Step 1: For a given input image ff, calculate the features of image objectness, which include image multi-scale saliency MS, image color contrast CC and superpixel spanning SS three image feature clues, in the image window The probability of image saliency is inferred in , and the saliency map Sal_o of image objectness is obtained by reasoning under the Bayesian model.

[0020] The calculation method of the multi-scale significance MS is shown in formula (1),

[0021] MS ( w , θ sc ) = Σ p ∈ w I sc ( p ) ...

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 an infrared image remarkable characteristic detection method combining objectivity and background property. The infrared image remarkable characteristic detection method combining objectivity and background property comprises steps of utilizing the objectivity of a remarkable object to determine the position and the area of the remarkable object in an image, reserving the integrity of the remarkable area to obtain an remarkable image under the objectivity, utilizing the background property of the image, smoothing most of the background area of the image with four boundaries of the image as starting points to obtain a remarkable image under the background, performing characteristic integration on a theory, and combining two remarkable images to obtain a final remarkable image. The infrared image remarkable characteristic detection method combining objectivity and background property improves accuracy and identification accuracy of target detection.

Description

technical field [0001] The invention belongs to the field of image understanding, and in particular relates to a method for detecting salient features of an infrared image combining objectivity and background. Background technique [0002] Saliency detection plays an important role in the understanding and analysis methods of night vision images (including low-light, infrared images), and it also plays an important role in machine vision applications. [0003] Document 1 (P. Jiang, H. Ling, J. Yu, and J. Peng. Salient Region Detection by UFO: Uniqueness, Focusness and Objectness, IEEE International Conference on Computer Vision (ICCV), 2013.) uses three clues A combined approach, which exploits the independence, objectivity, and attention correlations to detect salient feature regions in images. [0004] Document 2 (C. Yang, L. Zhang, H. Lu, X. Ruan, and M.-H. Yang. Saliency Detection via Graph-Based Manifold Ranking. In CVPR, 2013) uses the popular sorting method, which ex...

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 Applications(China)
IPC IPC(8): G06T7/00G06K9/46
Inventor 柏连发张毅祁伟韩静岳江陈钱顾国华
Owner NANJING UNIV OF SCI & TECH