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

Environmental saliency detection method simulating midbrain competitive selection mechanism of raptor

A technology for selecting mechanisms and detection methods, applied in the field of computer vision, can solve problems such as increasing computational complexity, computer vision recognition task interference, etc., and achieve the effects of reducing the amount of calculation, efficient and significant target positioning, and improving detection efficiency.

Active Publication Date: 2021-08-27
BEIHANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The redundant information in the scene will increase the computational complexity and bring interference to the computer vision recognition task

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
  • Environmental saliency detection method simulating midbrain competitive selection mechanism of raptor
  • Environmental saliency detection method simulating midbrain competitive selection mechanism of raptor
  • Environmental saliency detection method simulating midbrain competitive selection mechanism of raptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] Next, the effectiveness of the proposed scheme of the present invention will be verified through the specific small target recognition task of the unmanned target drone. In this example, the experimental computer configuration is Intel Core i7-7700HQ processor, 2.80Ghz main frequency, 8G memory, and the software is MATLAB 2017a version.

[0071] The target detection method of unmanned target drone imitating the return inhibition mechanism of the midbrain circuit in the eyes of birds of prey, its realization process is as follows figure 1 As shown, the specific practical steps of this example are as follows:

[0072] Step 1: Camera Calibration

[0073] The actual camera used for scene saliency detection needs to be calibrated. Calibration methods based on linear models, two-step methods, and dual-plane calibration methods are commonly used camera calibration methods. Among them, the Zhang Zhengyou calibration method is the most classic and one of the most widely 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an environment saliency detection method simulating a midbrain competitive selection mechanism of a raptor, and the method comprises the following steps: 1, carrying out the calibration of a camera, obtaining the internal and external parameters of the camera, and correcting the image distortion; 2, unifying image illumination intensity, and performing gamma correction; step 3, performing region segmentation by simulating a brauer color mechanism; step 4, detecting a salient region imitating a brauer attention mechanism; 5, simulating a receptive field of the brauchid nuclei; and step 6, fusing the color information and the dynamic target information. The invention has the advantages that 1, the robustness is high, an algorithm is designed according to a raptor eye color imitating mechanism and a raptor midbrain competitive selection mechanism, static characteristics and dynamic characteristics of a salient region are considered, and the accuracy of a salient detection result is ensured; 2, the framework is simple, the target detection calculation amount is saved, and the airborne calculation load requirement is greatly reduced; and 3, considering the difficulty of salient target detection caused by different illumination and different salient object features, so that the invention has higher adaptability to salient target detection in a changing environment.

Description

technical field [0001] The invention relates to an environmental saliency detection method imitating the competitive selection mechanism of the raptor midbrain, and belongs to the field of computer vision. Background technique [0002] With the continuous development of science and technology, in modern warfare, there is a high demand for rapid scene perception and target search. Compared with sensors such as ultrasonic waves and lasers, visual sensors have the advantages of strong adaptability, high sensitivity, and rich information. While video information is becoming more and more abundant, the requirements for computing resources, storage resources, and time resources required to process a large amount of information will be greatly improved. The redundant information in the scene will increase the computational complexity and bring interference to the computer vision recognition task. When facing a relatively complex scene, if we can first focus on a few special areas...

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): G06T7/90G06T7/80G06T7/11G06T5/00G06N3/00
CPCG06T7/80G06T7/11G06T7/90G06N3/006G06T5/80
Inventor 邓亦敏王思远段海滨
Owner BEIHANG UNIV
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