Fast and reliable tracking algorithm for on-road vehicle detection systems

In this paper, we proposes a novel tracking algorithm combining Kalman Filter with mean-shift. Kalman Filter predicts the vehicle position in the next frame. Mean-shift finds the best candidate which has maximum similarity with the tracked vehicle in the predicted area. Kalman Filter updates its state value of vehicle position with the position of the best candidate from the mean-shift tracker. As a result, the proposed algorithm tracks the vehicle without local maximum problem of mean-shift tracker. The proposed algorithm is very fast because it does not perform the redetection process, and it has no detection misses because it finds the best candidate which has maximum similarity with the tracked vehicle in the predicted area. Also, the proposed algorithm has deleting and adding policies for the tracking list management. If a vehicle was consecutively detected in the previous frames, the proposed algorithm assumes that the vehicle exists although the vehicle is not detected in the predicted region at the current frame. If a vehicle was not detected in the previous frames consecutively, the proposed algorithm assumes that the vehicle does not exist although the vehicle is detected in the current frame. We evaluated the performance of the proposed algorithm in terms of processing time and detection ratio. At target board, the proposed algorithm has 40 frames per second, which meets the real time requirements of the ADAS systems. The detection ratio and processing time of the proposed algorithm outperformed our former work.

[1]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Jong Taek Lee,et al.  Real‐Time License Plate Detection in High‐Resolution Videos Using Fastest Available Cascade Classifier and Core Patterns , 2015 .

[3]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Daesung Moon,et al.  Robust Multi-person Tracking for Real-Time Intelligent Video Surveillance , 2015 .

[5]  Dae-Wha Seo,et al.  Mono-camera based side vehicle detection for blind spot detection systems , 2015, 2015 Seventh International Conference on Ubiquitous and Future Networks.

[6]  Zehang Sun,et al.  A real-time precrash vehicle detection system , 2002, Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings..

[7]  Byung Woo Yoon,et al.  Direction‐Based Modified Particle Filter for Vehicle Tracking , 2016 .

[8]  Zehang Sun,et al.  On-road vehicle detection: a review , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Shengcai Liao,et al.  Learning Multi-scale Block Local Binary Patterns for Face Recognition , 2007, ICB.

[10]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Kyu-Dae Ban,et al.  Gender Classification of Low-Resolution Facial Image Based on Pixel Classifier Boosting , 2015 .

[12]  Soo-In Lee,et al.  Mono-camera based vehicle detection using effective candidate generation , 2014, The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014).

[13]  Bin Dai,et al.  A Vehicle Detection Method via Symmetry in Multi-Scale Windows , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.