Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern)

A Bayesian framework and moving target technology, applied in the field of intelligent video surveillance, can solve problems such as complex optical flow calculation methods, inaccurate optical flow fields, and difficult real-time scenes

Inactive Publication Date: 2010-12-15
云南清眸科技有限公司
View PDF1 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the presence of noise, illumination, occlusion, and shadows in the scene, the calculated optical flow field is not very accurate, and the ca

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 object detecting method based on Bayesian frame and LBP (Local Binary Pattern)
  • Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern)
  • Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] figure 1 Shown is a schematic diagram of the processing process of the present invention, that is, a moving target detection method based on Bayesian framework and LBP. For the video stream data, the present invention method first extracts the video frame image in the video stream data; and pre-processes the video frame image Processing, that is, smoothing the video frame image with a 5*5 Gaussian kernel to eliminate the interference of subtle light changes and other disturbances; and then performing moving target detection based on the background model and Bayesian framework on the smoothed video frame image, Obtain the preliminary moving target; finally, use LBP to describe the detected moving target area texture and the shadow texture of the corresponding area of ​​the background model, remove the shadow in the moving target detection, and increase the robustness of the whole method.

Embodiment 2

[0101] figure 2 For the present invention, namely a kind of flow chart of the moving object detection method based on Bayesian framework and LBP, concrete flow chart is described as follows:

[0102] 1) For the video stream sequence, firstly extract each frame of video image for processing.

[0103] 2) The video frame image is preprocessed, that is, the video frame image is smoothed with a 5*5 Gaussian kernel to eliminate the interference of subtle light changes and other disturbances.

[0104] 3) Moving target detection based on background model and Bayesian framework, including:

[0105] a) Change detection, that is, perform inter-frame difference and background difference on the smoothed video frame image at the same time. If the inter-frame difference and background difference satisfy the condition of no change at the same time, these pixels will be regarded as no change pixels and marked as background Pixels, the follow-up background model update processing and moving ...

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 object detecting method based on a Bayesian frame and an LBP (Local Binary Pattern), which relates to the technical field of intellectualized video monitoring. The method comprises the following steps of: 1. extracting a video frame in a video stream; 2. preprocessing the video frame and eliminating the interference of fine light ray change and other disturbance; 3. carrying out moving object detection based on a background model and the Bayesian frame; before detecting, filtering a pixel point with unchanged time difference and background difference and degrading color dimensionality in modeling, wherein the speed of the whole method is improved, and the background model comprises a color characteristic and a symbiotic color characteristic and can favorably detect a moving and static object in a video; and 4. removing a shadow, detecting the texture information of the obtained moving object area and the texture information of a background image corresponding area by utilizing an LBP descriptor and comparing the differences of the texture information for removing the shadow in moving object detection.

Description

(1) Technical field [0001] The invention relates to the technical field of intelligent video monitoring, in particular to a moving target detection method based on a Bayesian framework and LBP. (2) Background technology [0002] Real-time detection of moving targets in intelligent video surveillance systems is a major topic of low-level computer vision processing and digital image processing, mainly to detect whether there are dynamic objects in the static image sequence captured by the camera. Moving target detection is an important prerequisite for target segmentation and extraction, tracking, behavior understanding and event recognition, and is also the basis for video analysis and processing, and video surveillance system automation. Motion detection is a difficult task due to the dynamic changes in real scenes, such as lighting, weather, shadows, the occurrence of sudden events, and the presence of chaotic disturbances in the background (shaking branches, door opening a...

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): G06T7/20H04N7/18
Inventor 刘辉强振平
Owner 云南清眸科技有限公司
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