Research of Tracking Algorithm for Moving Object Based on Video Sequence

Zhe Xin Han; Bo Hu Zhang

doi:10.4028/www.scientific.net/AMM.556-562.3088

Paper Titles

Speech Recognition Algorithm Based on Nonlinear Partition and GFCC Features
p.3069

An Improved Moving Object Detection Algorithm Based on Colour Separation
p.3074

Numerical Identification of Ship-Roll Chaos Threshold
p.3078

Transformer Automatic Test System Based on Virtual Instrument
p.3084

Research of Tracking Algorithm for Moving Object Based on Video Sequence
p.3088

Research on the Technology of Data Transmission and Position Detection Based on Induction Radio
p.3093

A New Method Based on Photogrammetry for Hull’s Deformation Measurement and its Accuracy Analysis
p.3097

Target Tracking Cluster-Based Control in a Dynamic Environment
p.3101

Research for the Crack Dynamic Monitoring of Marine Diesel Engine
p.3107

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 556-562Research of Tracking Algorithm for Moving Object...

Research of Tracking Algorithm for Moving Object Based on Video Sequence

Abstract:

The study of tracking algorithm of moving objects is a key technique in computer vision; therefore, the work done by this thesis has important theoretical significance and wide practical value. An algorithm based on the improved three-frame-differencing is introduced in this paper. Firstly, three continuous edge images are obtained by edge extract from three continuous images, then, the motion information is detected with three-frame-differencing, finally, the target is extracted by threshold segmentation and morphology. The method is simple in calculation. The experimental results show that the strong robustness and can accurately detect the moving target. In addition, using the algorithm based on the characteristics of the objects can clearly record the object’s trajectory. Experiments show that the algorithm is effective and feasible in the motion object detection.