Filter-based energy-aware moving salient target detection method

A technology of target detection and energy perception, applied in instrument, calculation, character and pattern recognition, etc., can solve problems such as redundant or wrong information, and achieve low computational complexity, human participation, and computational complexity. Effect

Inactive Publication Date: 2019-04-19
DALIAN NATIONALITIES UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention overcomes the problem of redundant or wrong information in the detection results after feature detection and fusion in the existing target detection technology, and provides a filter-based energy-aware moving salient target detection method, through post-processing of moving salient target detection Filters, a more efficient and accurate method for real-time object active area detection

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
  • Filter-based energy-aware moving salient target detection method
  • Filter-based energy-aware moving salient target detection method
  • Filter-based energy-aware moving salient target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The camera is still and the single target is moving

[0040]In this embodiment, the present invention is applied to the detection of a moving object with a single moving object in a stationary state of the camera. Under this condition, the camera is installed and fixed on the top of a robot or a tripod, and the camera is shot horizontally. In the field of view of the lens, a human target enters the field of view of the camera from far to near at a speed of 0.6m / s. This video is mainly aimed at indoor scenes or when the shooting background is not moving. However, the background contains windows, tables, chairs, boxes and other common indoor furniture items, which have nothing to do with the characters' clothing and clothes. During the shooting, the illumination does not change drastically. The embodiment does not involve low-light special environments such as night vision.

[0041] Example parameter description: video format avi, video frame number 15 frames, video imag...

Embodiment 2

[0044] The camera is still and the two targets are moving

[0045] In this embodiment, the present invention is applied to the detection of a significantly moving object when two moving objects are in a stationary state of the camera. Under this condition, the camera is installed and fixed on the top of a robot or a tripod, and the camera is shot horizontally. Within the field of view of the lens, two human targets move away from the camera from near to far at the speed of 0.6m / s and 0.8m / s respectively. . This video is mainly aimed at indoor scenes or when the shooting background is not moving. However, the background contains windows, tables, chairs, boxes and other common indoor furniture items, which have nothing to do with the characters' clothing and clothes. During the shooting, the illumination does not change drastically. The embodiment does not involve low-light special environments such as night vision. Example parameter description: video format avi, video frame ...

Embodiment 3

[0048] The camera is still and the single target moves at a variable speed

[0049] In this embodiment, the present invention is applied to the detection of a single target moving at a variable speed when the camera is stationary. Under this condition, the camera is installed and fixed on the top of a robot or a tripod, and shoots horizontally. Outside the field of view of the lens, a single human target moves at a speed of 0.6m / s, and then gradually changes the speed to move in any direction. This video is mainly aimed at indoor scenes or when the shooting background is not moving. However, the background contains windows, tables, chairs, boxes and other common indoor furniture items, which have nothing to do with the characters' clothing and clothes. During the shooting, the illumination does not change drastically. The embodiment does not involve low-light special environments such as night vision.

[0050] Example parameter description: video format avi, video frame numbe...

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

A filter-based energy-aware moving salient target detection method, the content of the method is: the video information to be observed is decoded into an independent image frame sequence in YUV420 format, and the resolution is consistent with the input video; the number of skipped frames is set to 0, Read in the current image frame F; through the detection of motion features and salient features, the binarized image frame F is obtained after feature fusion d ; for image F d , perform energy search in the horizontal and vertical directions, divide and calculate the energy threshold, and then perform denoising and smoothing filtering processing respectively to obtain the final target area with significant motion; read the next image frame as input according to the number of skipped frames, and execute the second step in a loop Step, step 3, and step 4, until the last frame of the video is read, the loop is terminated, and the implementation ends. The invention can effectively remove redundant information and erroneous targets, calibrate the actual active area of ​​a moving prominent target, avoid manual selection and initialization of a prominent area, and provide possibility for automatic realization of moving target tracking.

Description

technical field [0001] The invention belongs to the technical field of detection and processing of salient moving objects, in particular to a filter-based method for detecting salient moving objects based on energy perception. Background technique [0002] As a very important research topic in the field of computer vision, salient moving object detection has broad application prospects in video surveillance, industrial control, robot vision and autonomous vehicle navigation. In the target detection technology, with the continuous changes of the application field and the application environment, the requirements are becoming more and more complex, and the requirements for the accuracy, real-time performance, stability and portability of the target detection are getting higher and higher. [0003] At present, target detection technology mainly uses feature detection and feature fusion to locate targets. Due to the variety of application environments, factors such as feature se...

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): G06K9/00G06K9/46
CPCG06V40/20G06V10/462
Inventor 杨大伟毛琳张汝波刘冠群吴俊伟姬梦婷
Owner DALIAN NATIONALITIES UNIVERSITY
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