ABSTRACT
This paper presents a novel and efficient object tracking method based on multi-sensor information fusion. Based on the popular detection-tracking framework, we consider the tracking process as 3 conditions and the fusion strategy can be adjusted in different conditions adaptively by designing a new online positive and negative sample classifier selecting method with the guidance of the depth information from the laser scanner. The results of our experiments show good robustness and performance when facing extreme cases such as the object rotation, long-period occlusion, and high similarity between object and background.
- Z.H. Sun, G. Bebis, and R. Miler, "On-road vehicle detection: a review", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, pp 694--710. Google ScholarDigital Library
- C. Stauffer and E. Grimson, "Learning Patterns of Activity Using Real-Time Tracking," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 747--757, Aug. 2000. Google ScholarDigital Library
- M. Lindstrom and J.-O. Eklundh, "Detecting and tracking moving objects from a mobile platform using a laser range scanner," Conf. Intell. Robots Syst., Maui, HI, 2001, vol. 3, pp. 1364--1369.Google Scholar
- W. Zajdel, Z. Zivkovic, and B. J. A. Krose, "Keeping track of humans:Have I seen this person before?" in Proc. IEEE Int. Conf. Robot. Autom.,Barcelona, Spain, 2005, pp. 2093--2098.Google Scholar
- M. Mählisch, R. Schweiger, W. Ritter, K. Dietmayer, Sensorfusion using spatio-temporal aligned video and LIDAR for improved vehicle detection, in:Proceedings of the IEEE Intelligent Vehicles Symposium, 2006, pp. 424--429.Google Scholar
- G. Cielniak, A. Treptow, and T. Duckett, "Quantitative performance eval-uation of a people tracking system on a mobile robot," in Proc. 2nd Eur.Conf. Mobile Robots, Ancona, Italy, 2005.Google Scholar
- Z.Y. Zhang, "Flexible camera calibration by viewing a plane from unknown orientations," IEEE Int. Conf. ICCV, 1999, pp. 666--673.Google Scholar
- Q. Zhang, R. Pless, "Extrinsic calibration of a camera and laser range finder (improves camera calibration)," IEEE/RSJ Int. Conf. IRS, 2004, pp. 2306--2310.Google Scholar
- S. Avidan. Ensemble tracking. In CVPR, volume 2, pages 494--501,2005. Google ScholarDigital Library
- B. babenko. Visual tracking with online Multiple Instance Learning. In Computer Vision and Pattern Recognition, 2009. pages 983--990Google Scholar
- R. T. Collins, Y. Liu, and M. Leordeanu. Online selection of discriminative tracking features. PAMI, 27(10):1631--1643, 2005. Google ScholarDigital Library
- L. Oliveira, U. Nunes, "Semantic fusion of laser and vision in pedestrian detection," Pattern Recognition, 2010, pp. 3648--3659. Google ScholarDigital Library
- X. Song, J. Cui, X. Wang, H. Zhao, and H. Zha, "Tracking interacting targets with laser scanner via on-line supervised learning," Proc. IEEE International Conference on Robotics and Automation, pp. 2271--2276,2008.Google Scholar
Index Terms
- Real-time pedestrian learning-tracking with information fusion
Recommendations
Real-Time Multi-pedestrian Tracking Based on Vision and Depth Information Fusion
Advances in Multimedia Information Processing – PCM 2013AbstractVisual object tracking plays an essential role in vision based applications. Most of the previous Multi-pedestrian Tracking has limitations due to considering each pedestrian with the same motion and appearance model in a uniform observation space,...
Real-time human tracking system with multiple omnidirectional vision sensors
We propose a real-time human tracking system that uses multiple omnidirectional vision sensors. This system estimates and tracks the locations of multiple persons from omnidirectional 360-degree images captured by multiple omnidirectional vision sensors ...
Multi-source data fusion study in scientometrics
This paper provides an introduction to multi-source data fusion (MSDF) and comprehensively overviews the ingredients and challenges of MSDF in scientometrics. As compared to the MSDF methods in the sensor and other fields, and considering the features ...
Comments