Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Moving target detection method based on deep optical flow and morphological method

A technology for moving targets and detection methods, applied in image data processing, image enhancement, instruments, etc., can solve the problems of incomplete detection target shape, low detection accuracy, etc., achieve strong learning ability, good detection robustness, and calculation effect Good results

Active Publication Date: 2018-04-27
BEIHANG UNIV
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to overcome the problems of low detection accuracy and incomplete shape of the detection target in the prior art, and provide a moving target detection method based on depth optical flow, which uses deep learning to learn the motion optical flow, Then use morphological methods to optimize the detection results, thereby improving the accuracy and robustness of moving target 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
  • Moving target detection method based on deep optical flow and morphological method
  • Moving target detection method based on deep optical flow and morphological method
  • Moving target detection method based on deep optical flow and morphological method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0069] In the present invention, the realization and verification of the moving target detection model concept is to use GPU (GTX1080) as the computing platform, adopt the GPU parallel computing framework, and select Caffe as the CNN (convolutional network) framework.

[0070] Such as figure 1 Shown, the steps of the present invention are: (1) collect video data, label sample video, and be divided into training set and test set at random, to the training set that has been processed and test set, do mean value calculation, form training set mean value file and test Set the mean value file to complete the preprocessing of the training set and test set; (2) Construct a fully convolutional neural network architecture, which consists of two parts, encoding and decoding, and use the training set and test set to train through an adaptive learning rate adjust...

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 moving target detection method based on a deep optical flow and a morphological method, which includes the following steps: (1) collecting video data, marking sample videos,randomly dividing the sample videos into a training set and a testing set, carrying out mean calculation on the processed training set and the processed testing set to form a training set mean file and a testing set mean file, and completing the preprocessing of the training set and the testing set; (2) constructing a fully convolutional neural network architecture composed of a coding part and adecoding part, and carrying out training by using the training set and the testing set through an adaptive learning rate adjustment algorithm to get trained model parameters; (3) inputting image dataneeding detection to a trained fully convolutional neural network to get a corresponding deep optical flow graph; (4) processing the deep optical flow graph through an Otsu threshold adaptive segmentation method; and (5) morphologically processing the data after threshold segmentation, removing outliers and slots, and finally obtaining a detected moving target area.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a method for detecting a moving object. Background technique [0002] Moving object detection is a key technology in the field of video image processing. Moving object detection is to distinguish the moving object in the video or image sequence from the background by a certain method, so as to achieve the purpose of extracting the moving object from the video or image sequence. Moving target detection has been widely used in military target detection and tracking, intelligent human-computer interaction, intelligent transportation and robots. [0003] According to whether the camera is moving or not, the scene of moving object detection can be divided into two types: the case where the camera is still and the case where the camera is moving. When the camera is still, that is, the background of the image is not moving; while in the case of camera movement, the camera is gene...

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): G06T7/246G06N3/04
CPCG06T7/246G06T2207/10016G06T2207/20081G06N3/045
Inventor 张弘张磊李军伟杨一帆
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
Eureka Blog
Learn More
PatSnap group products