Detection method of small objects in visible light image

A technology of weak and small targets and detection methods, which is applied in image analysis, image data processing, instruments, etc., can solve the problems of large amount of calculation and complicated realization process, and achieve the effect of realizing weak and small target detection.

Inactive Publication Date: 2009-09-02
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the stage of obtaining the binary image containing moving targets, the method uses the first three frames of images in the sequence for background estimation, and uses the automatic threshold segmentation method for grayscale image segmentation. Therefore, the selection of the threshold determines the strength of the detectable target. ; In the stage of target motion trajecto

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
  • Detection method of small objects in visible light image
  • Detection method of small objects in visible light image
  • Detection method of small objects in visible light image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The method of the present invention includes (1) construction of a motion integration model.

[0016] Four models corresponding to the visual attention mechanism are constructed. The first one is the most typical static model in visual attention mechanism. The second is a motion model limited to characterizing motion. The third is a motion-integrated model that combines static and motion, and the last is a condition-restricted model for motion-conditioned constraints.

[0017] (a) Build a static model.

[0018] First, 7 basic features are extracted from the image: 1 grayscale feature F 1 =I; two color features F 2 =(R-G) / I;F 3 =(B-Y) / I; 4 directional features F 4 , F 5 , F 6 , F 7 , where the angle θ ∈ {0°; 45°; 90°; 135°}.

[0019] Secondly, use a multi-scale method to perform feature F under different scales k=1...6 j Feature set F for (j=1...7) j，k The construction of is based on the central peripheral operation mechanism, according to the formula

[002...

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 detection method for small objects in a visible light image. The detection method comprises the following steps: firstly, establishing a motion conformity model and carrying out feature extraction by simulating the sensitivity of human visual sense to the color, the direction and the motion features to establish a visual attention mechanism model; selecting an object detection mechanism and choosing the visual attention mechanism model by means of image visual features in different working modes, thereby carrying out object detection in different working modes; and completing object centroid positioning. Due to carrying out track detection by means of the visual features of an object, the detection method makes full use of visual sensitivity to the color, the gray scale, the direction and the motion and adopts different combinations centralizing the visual attention mechanism model to realize the detection of the small objects in multiple working modes.

Description

technical field [0001] The invention relates to a visible light image processing method, in particular to a detection method for weak and small targets under different working mode conditions in the visible light image. Background technique [0002] The target detection problem under the conditions of various working modes directly determines the detection performance of the astronomical observation system, and effectively solving this problem is of great significance for improving the system performance. The existing faint target detection methods mainly include: the target detection method based on the static background and the target detection method based on the complex moving background. [0003] The document "Study on Algorithm Extraction of Motion Trajectories of Space Objects, Infrared Technology, 2007, 29(8), 459-462" discloses a weak target detection method, which is based on the target extraction algorithm generated by the multi-frame accumulation background mask ...

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): G06T7/00G06T7/20
Inventor 孙瑾秋张艳宁姜磊段锋
Owner NORTHWESTERN POLYTECHNICAL 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