Video Tracking of Human with Occlusion Based on MeanShift and Kalman Filter

2013 ◽  
Vol 380-384 ◽  
pp. 3672-3677 ◽  
Author(s):  
Bao Hong Yuan ◽  
De Xiang Zhang ◽  
Kui Fu ◽  
Ling Jun Zhang
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Moving Objects ◽  
Video Tracking ◽  
Moving Object ◽  
Large Area ◽  
Image Region ◽  
Future State ◽  
Kalman Filter Algorithm ◽  
Histogram Similarity

In order to accomplish tracking of moving objects requirements, and overcome the defect of occlusion in the process of tracking moving object, this paper presents a method which uses a combination of MeanShift and Kalman filter algorithm. MeanShift object tracking algorithm uses a histogram to describe the color characteristics of an object, and search the location of an image region that the color histogram is closest to the histogram of the object. Histogram similarity is defined in terms of the Bhattacharya coefficient. When the moving object is a large area blocked, the future state of moving object is estimated by Kalman filter. Experimental results verify that the proposed algorithm achieves efficient tracking of moving objects under the confusing situations.

scholarly journals Moving-Object Tracking with In-Vehicle Multi-Laser Range Sensors

2008 ◽  
Vol 20 (3) ◽  
pp. 367-377 ◽  
Author(s):  
Masafumi Hashimoto ◽  
◽  
Yosuke Matsui ◽  
Kazuhiko Takahashi ◽  
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Moving Objects ◽  
Tracking System ◽  
Moving Object ◽  
Experimental Result ◽  
Coordinate Frame ◽  
Laser Range ◽  
Assignment Algorithm ◽  
Moving Object Tracking

This paper presents a method for moving-object tracking with in-vehicle 2D laser range sensor (LRS) in a cluttered environment. A sensing area of one LRS is limited in orientation, and hence the mobile robot is equipped with multi-LRSs for omnidirectional sensing. Since each LRS takes the laser image on its own local coordinate frame, the laser image is mapped onto a reference coordinate frame so that the object tracking can be achieved by cooperation of multi-LRSs. For mapping the coordinate frames of multi-LRSs are calibrated, that is, the relative positions and orientations of the multi-LRSs are estimated. The calibration is based on Kalman filter and chi-hypothesis testing. Moving-object tracking is achieved by two steps: detection and tracking. Each LRS finds moving objects from its own laser image via a heuristic rule and an occupancy grid based method. It tracks the moving objects via Kalman filter and the assignment algorithm based data association. When the moving objects exist in the overlapped sensing areas of the LRSs, these LRSs exchange the tracking data and fuse them in a decentralized manner. A rule based track management is embedded into the tracking system in order to enhance the tracking performance. The experimental result of three walking-people tracking in an indoor environment validates the proposed method.

scholarly journals Quantized Kalman Filter-Based Pattern Matching for Detection and Tracking of Moving Objects

2019 ◽  
Vol 9 (1) ◽  
pp. 3842-3851
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Pattern Matching ◽  
Kalman Filtering ◽  
Moving Objects ◽  
Moving Object ◽  
Video Frame ◽  
Top Down ◽  
Matching Accuracy ◽  
Detection And Tracking

Detection And Tracking Of Multiple Moving Objects From A Sequence Of Video Frame And Obtaining Visual Records Of Objects Play An Important Role In The Video Surveillance Systems. Transform And Filtering Technique Designed For Video Pattern Matching And Moving Object Detection, Failed To Handle Large Number Of Objects In Video Frame And Further Needs To Be Optimized. Several Existing Methods Perform Detection And Tracking Of Moving Objects. However, The Performance Efficiency Of The Existing Methods Needs To Be Optimized To Achieve More Robust And Reliable Detection And Tracking Of Moving Objects. In Order To Improve The Pattern Matching Accuracy, A Quantized Kalman Filter-Based Pattern Matching (Qkf-Pm) Technique Is Proposed For Detecting And Tracking Of Moving Objects. The Present Phase Includes Three Functionalities: Top-Down Approach, Kernel Pattern Segment Function And Kalman Filtering. First, The Top-Down Approach Based On Kalman Filtering (Kf) Technique Is Performed To Detect The Chromatic Shadows Of Objects. Next, Kernel Pattern Segment Function Creates The Seed Points For Detecting Moving Object Pattern. Finally, Object Tracking Is Performed Using The Proposed Quantized Kalman Filter Based On The Center Of Seed Point Affinity Feature Values Are Used To Track The Moving Objects In A Particular Region Using The Minimum Bounding Box Approach. Experimental Results Reveals That The Proposed Qkf-Pm Technique Achieves Better Performance In Terms Of True Detection Rate, Pattern Matching Accuracy, Pattern Matching Time, And Object Tracking Accuracy With Respect To The Number Of Video Frames Per Second.

Abnormal Motion Detection for Intelligent Video Surveillance

2011 ◽  
Vol 58-60 ◽  
pp. 2290-2295 ◽  
Author(s):  
Ruo Hong Huan ◽  
Xiao Mei Tang ◽  
Zhe Hu Wang ◽  
Qing Zhang Chen
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Video Surveillance ◽  
Motion Detection ◽  
Background Subtraction ◽  
Moving Objects ◽  
Video Streams ◽  
Intelligent Video Surveillance ◽  
Tracking Process ◽  
Object Parameters

A method of abnormal motion detection for intelligent video surveillance is presented, which includes object intrusion detection, object overlong stay detection and object overpopulation detection. Background subtraction algorithm is used to detect moving objects in video streams. Kalman filter is applied for object tracking. By the construction of relation matrix, the tracking process is divided into five statuses for prediction and estimation, which are object disappearing, object separating, new object appearing, object sheltering and object matching. The object parameters and predictive information in the next frame which is used to track moving objects is established by Kalman filter. Then, three types of abnormal motion detection are implemented. The relative position of alarm area or guard line with the rectangle boxes of the moving objects is used to detect whether the object is invading. The existing time of the moving objects in monitor area is counted to detect whether the object is staying too long. Moving objects in the monitor area are classified and counted to detect whether the objects are too much. Alarm will be triggered when abnormal motion detection as defined is detected in the monitor area.

Research on Application of Camshift and Kalman Filter Algorithm in Video Object Tracking

2014 ◽  
Vol 1049-1050 ◽  
pp. 1685-1689
Author(s):  
Cheng Yi Guo ◽  
Wen Bing Fan
Keyword(s):  
Kalman Filter ◽  
Search Window ◽  
Large Area ◽  
A Algorithm ◽  
Correct Operation ◽  
Video Object Tracking ◽  
Camshift Algorithm ◽  
Kalman Filter Algorithm ◽  
Color Background ◽  
Research On Application

When the background is complex and there is a lot color similar pixel interference, it may lead to location and size of Camshift algorithm’s search window abnormal so as to tracking failure. Aiming at these problems, this paper proposed a algorithm that combinating Camshift algorithm and Kalman filter. Kalman filter can predict the position of the moving object. Camshift algorithm adjusted the position and size of search window by using the prediction, so as to ensure the correct operation of the Camshift algorithm. Experimental results show that the proposed algorithm can effectively overcome the large area of similar color background and occlusion and many colors similar moving targets interference and other issues, improve the accuracy and robustness of target tracking algorithm.

scholarly journals Detection and tracking of moving object using modified background subtraction and Kalman filter

2021 ◽  
Vol 11 (1) ◽  
pp. 217
Author(s):  
Jeevith S. H. ◽  
Lakshmikanth S.
Keyword(s):  
Kalman Filter ◽  
Background Subtraction ◽  
Moving Objects ◽  
Adaptive Threshold ◽  
Vital Role ◽  
Moving Object ◽  
Navigation Systems ◽  
Subtraction Technique ◽  
Night Time ◽  
Detection And Tracking

Moving object detection and tracking (MODT) is the major challenging issue in computer vision, which plays a vital role in many applications like robotics, surveillance, navigation systems, militaries, environmental monitoring etc. There are several existing techniques, which has been used to detect and track the moving object in Surveillance system. Therefore it is necessary to develop new algorithm or modified algorithm which is robust to work in both day and night time. In this paper, modified BGS technique is proposed. The video is first converted to number of frames, then these frame are applied to modified background subtraction technique with adaptive threshold which gives detected object. Kalman filter technique is used for tracking the detected object. The experimental results shows this proposed method can efficiently and correctly detect and track the moving objects with less processing time which is compared with existing techniques.

Sign in / Sign up

Export Citation Format

Share Document