An improved method for multiple targets tracking

Abstract

The difficulty of multiple targets tracking is how to quickly fulfill the target matching from one frame image to another and fix the position of the target. In order to accurately choose target feature information for reliable matching, simplify operations under the reliable precondition, and realize precise moving objects tracking, an approach based on Kalman prediction and feature matching was proposed. The position of the target in next frame image was predicted by Kalman, and then the moving objects of two adjacent frames were matched by the centroid and area methods. When occlusion occurs, the best matching result was found to realize tracking by matching matrix algorithm. The simulation results show that the proposed method can achieve multiple targets tracking accurately and in real-time under complicated motion movements.

Keywords

Kalman prediction / feature matching / centroid and area matching equations / image occluded processing / matching matrix algorithm

References

[1] LiJ.-j., ZhuQ., WangY.-nan.. Detecting and tracking method of moving target in complex environment [J]. Chinese Journal of Scientific Instrument, 2010, 31(10): 2242-2247

[2] WangG.-f., OuY.-s., LiuQ.-h., DingYong.. Fast identification and location for series image of airborne electro-optical tracking system [J]. OPTO-Electronic Engineering, 2009, 36(1): 36-40

[3] LshidaT., Wavelet, KorfR. E.. Moving-target search: A real-time search for change goals [J]. IEEE Titans PAMI, 1995, 17(6): 609-619

[4] MaC.-w., CaiR.-jun.. A fast identification & location algorithm for moving targets in TV theodolite tracking system [J]. Acta Photonica Sinica, 2005, 34(1): 134-137

[5] YangT., ZhangY.-n., ZhanfX.-w., ZhangX.-gong.. Scene complexity and invariant feature based real-time aerial video registration algorithm [J]. ACTA Electronica Sinica, 2010, 38(5): 1069-1077

[6] TangY., WeiM., KeJia.. Multi-object tracking algorithm based on data association matrices [J]. Computer Engineering, 2010, 36(23): 158-161

[7] LiuB., JesorskyO., KompeR.. Robust real time multiple object tracking in traffic scenes using an optical matrix range sensor [C]. IEEE International Conference on Intelligent Transportation Systems, 2007Sophia AntipolisIEEE Press742-747

[8] ZhangX.-y., ZhaoR.-c., MaZ.-qiang.. Automatic video object segmentation and tracking using an improved active contour [J]. Journal of Image and Graphics, 2007, 12(3): 439-443

[9] MaB., ShiZ.-k., PiY.-ni.. Image object tracking algorithms analysis [J]. Journal of Xi’dian University: National Science, 2005, 32(3): 477-480

[10] YangP.-h., ZhuJ.-x., YangJing.. Multi-sensor data fusion maneuvering target tracking algorithm [J]. Chinese Journal of Scientific Instrument, 2006, 27(6): 1679-1682

[11] SegenJ., PingaliS.. A camera-based system for tracking people in real time [C]. Proc International Conference on Pattern Recognition, 1996ViennaICPR63-67

[12] MEUTER M, IURGEL U, PARK S, et al. The unscented Kalman filter for pedestrian tracking from a moving host [C]// IEEE Intelligent Vehicles Symposium, 2008: 37–42.

[13] WAN Qin, WANG Yao-nan. Research and implementation of detecting and tracking multiple moving objects method [J]. Application Research of Computers, 2007, (1): 199–202. (in Chinese)

[14] LiX., WangK.-j., WangW., et al. . A multiple object tracking method using Kalman filter [C]. Proc IEEE International Conference on Information and Automation, 2010Harbin, ChinaIEEE Press1862-1866

[15] DingY., YangD.-y., ChenJ.-yin.. Detection and tracking multiple moving objects based on omni directional vision [J]. Computer Systems & Applications, 2008, 2: 50-54