Multi-Vehicle Tracking via Real-Time Detection Probes and a Markov Decision Process Policy
Abstract
:1. Introduction
- An offline-trained vehicle detector is customized to generate robust and fine detections by an onboard monocular camera. Data augmentation benefits the detector to meet various traffic conditions in moving scenes.
- A well-designed association strategy adopts multi-dimensional information to score pairwise similarity. A Siamese convolution network is designed to score pairwise similarity, wherein a dual-resolution in two specific channels could efficiently improve the performance of image matching. Any size of the input patches can still maintain the fixed output dimensionality through the SPP layer. A tracking-by-detection framework is applied to accomplish linear assignments by linking new detections with initial tracks.
- The tracking process is formulated as the Markov decision process. Four states are designed to manage the lifetime of each vehicle, which is more adaptable to the changeable traffic scenes. With reinforcement learning, an updated policy is applied to reduce false positives and improve tracking accuracy.
2. Related Work
3. Methods
3.1. Vehicle Detection Probes
3.2. Diversity Feature Extraction
3.2.1. Motion and Size Models
3.2.2. Central-Surround Two-Channel Spatial Pyramid Pooling (SPP) Network
3.2.3. Feature Representation
3.3. Markov Decision Processes (MDPs)
3.3.1. Overview of the MDPs
3.3.2. Policy in the Probationary State
3.3.3. Policy in the Tracked State
3.3.4. Policy in the Temporary Death State
3.3.5. Reinforcement Learning
4. Experiments
4.1. Dataset and Evaluation Metrics
4.2. Performance Evaluation
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Henriques, J.F.; Caseiro, R.; Martins, P.; Batista, J. High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 37, 583–596. [Google Scholar] [CrossRef] [PubMed]
- Danelljan, M.; Hager, G.; Khan, F.S.; Felsberg, M. Learning spatially regularized correlation filters for visual tracking. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015. [Google Scholar]
- Babenko, B.; Yang, M.H.; Belongie, S. Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 2011, 33, 1619–1632. [Google Scholar] [CrossRef] [PubMed]
- Wang, L.; Ouyang, W.; Wang, X.; Lu, H. Visual tracking with fully convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015. [Google Scholar]
- Wang, L.; Ouyang, W.; Wang, X.; Lu, H. STCT: Sequentially Training Convolutional Networks for Visual Tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Chu, Q.; Ouyang, W.; Li, H.; Wang, X.; Liu, B.; Yu, N. Online Multi-Object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017. [Google Scholar]
- Coifman, B.; Beymer, D.; McLauchlan, P.; Malik, J. A real-time computer vision system for vehicle tracking and traffic surveillance. Transp. Res. Part C Emerg. Technol. 1998, 6, 271–288. [Google Scholar] [CrossRef] [Green Version]
- Battiato, S.; Farinella, G.M.; Furnari, A.; Puglisi, G.; Snijders, A.; Spiekstra, J. An integrated system for vehicle tracking and classification. Expert Syst. Appl. 2015, 42, 7263–7275. [Google Scholar] [CrossRef]
- Peña-González, R.H.; Nuño-Maganda, M.A. Computer vision based real-time vehicle tracking and classification system. In Proceedings of the IEEE 57th International Midwest Symposium on Circuits and Systems (MWSCAS), College Station, TX, USA, 3–6 August 2014; pp. 679–682. [Google Scholar]
- Ding, R.; Yu, M.; Oh, H.; Chen, W.H. New multiple-target tracking strategy using domain knowledge and optimization. IEEE Trans. Syst. Man, Cybern. Syst. 2017, 47, 605–616. [Google Scholar] [CrossRef]
- Bae, S.H.; Yoon, K.J. Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking. IEEE Trans. Pattern Anal. Mach. Intell. 2018, 40, 595–610. [Google Scholar] [CrossRef] [PubMed]
- Fagot-Bouquet, L.; Audigier, R.; Dhome, Y.; Lerasle, F. Improving multi-frame data association with sparse representations for robust near-online multi-object tracking. In Proceedings of the 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016. [Google Scholar]
- Berclaz, J.; Fleuret, F.; Türetken, E.; Fua, P. Multiple object tracking using k-shortest paths optimization. IEEE Trans. Pattern Anal. Mach. Intell. 2011, 33, 1806–1819. [Google Scholar] [CrossRef] [PubMed]
- Milan, A.; Roth, S.; Schindler, K. Continuous energy minimization for multitarget tracking. IEEE Trans. Pattern Anal. Mach. Intell. 2014, 36, 58–72. [Google Scholar] [CrossRef] [PubMed]
- Sadeghian, A.; Alahi, A.; Savarese, S. Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017. [Google Scholar]
- Yoon, J.H.; Lee, C.-R.; Yang, M.-H.; Yoon, K.-J. Online Multi-object Tracking via Structural Constraint Event Aggregation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Leal-Taixé, L.; Fenzi, M.; Kuznetsova, A.; Rosenhahn, B.; Savarese, S. Learning an image-based motion context for multiple people tracking. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; 2014. [Google Scholar]
- Kim, S.; Kwak, S.; Feyereisl, J.; Han, B. Online multi-target tracking by large margin structured learning. In Proceedings of the 11th Asian Conference on Computer Vision, Daejeon, Korea, 5–9 November 2013. [Google Scholar]
- Xiang, Y.; Alahi, A.; Savarese, S. Learning to track: Online multi-object tracking by decision making. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015. [Google Scholar]
- Bae, S.H.; Yoon, K.J. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014. [Google Scholar]
- Kuhn, H.W. The Hungarian method for the assignment problem. In 50 Years of Integer Programming 1958–2008: From the Early Years to the State-of-the-Art; Springer: Berlin/Heidelberg, Germany, 2010; ISBN 9783540682745. [Google Scholar]
- Zagoruyko, S.; Komodakis, N. Learning to compare image patches via convolutional neural networks. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 37, 1904–1916. [Google Scholar] [CrossRef] [PubMed]
- Li, Y.; Huang, C.; Nevatia, R. Learning to associate: Hybridboosted multi-target tracker for crowded scene. In Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Miami, FL, USA, 20–25 June 2009. [Google Scholar]
- Sanchez-Matilla, R.; Poiesi, F.; Cavallaro, A. Online multi-target tracking with strong and weak detections. In Proceedings of the European Conference on Computer Vision; Springer: Berlin, Germany, 2016. [Google Scholar]
- Breitenstein, M.D.; Reichlin, F.; Leibe, B.; Koller-Meier, E.; Van Gool, L. Online multiperson tracking-by-detection from a single, uncalibrated camera. IEEE Trans. Pattern Anal. Mach. Intell. 2011, 33, 1820–1833. [Google Scholar] [CrossRef] [PubMed]
- Wojke, N.; Bewley, A.; Paulus, D. Simple online and realtime tracking with a deep association metric. In Proceedings of the International Conference on Image Processing, Beijing, China, 17–20 September 2018. [Google Scholar]
- Bewley, A.; Ge, Z.; Ott, L.; Ramos, F.; Upcroft, B. Simple online and realtime tracking. In Proceedings of the International Conference on Image Processing, Phoenix, AZ, USA, 25–28 September 2016. [Google Scholar]
- Bromley, J.; Bentz, J.W.; Bottou, L.; Guyon, I.; Lecun, Y.; Moore, C.; Säckinger, E.; Shah, R. Signature Verification using A “siamese” time delay neural network. Int. J. Pattern Recognit. Artif. Intell. 1993. [Google Scholar] [CrossRef]
- Chopra, S.; Hadsell, R.; LeCun, Y. Learning a similarity metric discriminatively, with application to face verification. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, USA, 20–26 June 2005; IEEE: Piscataway, NJ, USA, 2005. [Google Scholar]
- Tao, R.; Gavves, E.; Smeulders, A.W.M. Siamese Instance Search for Tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 26 June–1 July 2016; pp. 1420–1429. [Google Scholar]
- Bellman, R. A Markovian Decision Process. J. Math. Mech. 1957, 6, 679–684. [Google Scholar] [CrossRef] [Green Version]
- Karayev, S.; Fritz, M.; Darrell, T. Anytime recognition of objects and scenes. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014. [Google Scholar]
- Kitani, K.M.; Ziebart, B.D.; Bagnell, J.A.; Hebert, M. Activity forecasting. In Proceedings of the 12th European Conference on Computer Vision, Florence, Italy, 7–13 October 2012. [Google Scholar]
- Russakovsky, O.; Li, L.J.; Fei-Fei, L. Best of both worlds: Human-machine collaboration for object annotation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Rajaram, R.N.; Ohn-Bar, E.; Trivedi, M.M. RefineNet: Refining Object Detectors for Autonomous Driving. IEEE Trans. Intell. Veh. 2016, 1, 358–368. [Google Scholar] [CrossRef]
- Eshed, O.B.; Rajaram, R.N.; Trivedi, M.M. RefineNet: Iterative refinement for accurate object localization. In Proceedings of the IEEE Conference on Intelligent Transportation Systems, Rio de Janeiro, Brazil, 1–4 November 2016. [Google Scholar]
- Geiger, A.; Lenz, P.; Urtasun, R. Are we ready for autonomous driving? the KITTI vision benchmark suite. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012. [Google Scholar]
- Bernardin, K.; Stiefelhagen, R. Evaluating multiple object tracking performance: The CLEAR MOT metrics. J. Image Video Process. 2008. [Google Scholar] [CrossRef]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single shot multibox detector. In Proceedings of the 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016. [Google Scholar]
- Redmon, J.; Farhadi, A. YOLOv3: An Incremental Improvement. arXiv, 2018; arXiv:1804.02767. [Google Scholar]
- Lenz, P.; Geiger, A.; Urtasun, R. FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015. [Google Scholar]
- Yoon, J.H.; Yang, M.H.; Lim, J.; Yoon, K.J. Bayesian multi-object tracking using motion context from multiple objects. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 5–9 January 2015. [Google Scholar]
- Xiang, Y.; Choi, W.; Lin, Y.; Savarese, S. Subcategory-Aware convolutional neural networks for object proposals & detection. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Santa Rosa, CA, USA, 24–31 March 2017. [Google Scholar]
- Gündüz, G.; Acarman, A.T. A Lightweight Online Multiple Object Vehicle Tracking Method. In Proceedings of the IEEE Intelligent Vehicles Symposium, Changshu, China, 26–30 June 2018. [Google Scholar]
- Sharma, S.; Ansari, J.A.; Murthy, J.K.; Krishna, K.M. Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia, 21–25 May 2018. [Google Scholar]
Layer | Type | Kernel Size | Stride |
---|---|---|---|
Input | Raw data | ||
Conv1 | Convolution | 7 × 7 | 2 |
Pool1 | Max pooling | 3 × 3 | 2 |
Conv2 | Convolution | 5 × 5 | 2 |
Pool2 | Max pooling | 3 × 3 | 2 |
Conv3 | Convolution | 3 × 3 | 1 |
Output | FC |
Detector | Evaluation of Detection (AP) | Tracker | Evaluation of Tracking (MOTA) | ||||
---|---|---|---|---|---|---|---|
Campus | Urban | Highway | Campus | Urban | Highway | ||
SSD | 65.25% | 60.16% | 68.84% | Proposed | 70.64% | 72.62% | 74.32% |
YOLOv3 | 63.55% | 62.99% | 70.19% | Proposed | 74.65% | 77.22% | 77.98% |
Detection probes | 68.84% | 63.66% | 72.03% | Proposed | 75.29% | 76.06% | 78.14% |
Method | MOTA ↑ | MOTP ↑ | FRAG ↓ | IDS ↓ | MT ↑ | ML ↓ |
---|---|---|---|---|---|---|
Proposed | 76.53% | 81.19% | 349 | 11 | 82.12% | 9.92% |
SSP [39] | 57.85% | 77.65% | 704 | 7 | 29.38% | 24.31% |
RMOT [40] | 65.83% | 75.42% | 727 | 209 | 40.15% | 9.69% |
MDP [41] | 69.35% | 82.10% | 387 | 130 | 52.15% | 13.38% |
ExtraCK [42] | 79.99% | 82.46% | 938 | 342 | 62.15% | 5.54% |
MOTBeyondPixels [43] | 84.24% | 85.73% | 944 | 468 | 73.23% | 2.77% |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zou, Y.; Zhang, W.; Weng, W.; Meng, Z. Multi-Vehicle Tracking via Real-Time Detection Probes and a Markov Decision Process Policy. Sensors 2019, 19, 1309. https://doi.org/10.3390/s19061309
Zou Y, Zhang W, Weng W, Meng Z. Multi-Vehicle Tracking via Real-Time Detection Probes and a Markov Decision Process Policy. Sensors. 2019; 19(6):1309. https://doi.org/10.3390/s19061309
Chicago/Turabian StyleZou, Yi, Weiwei Zhang, Wendi Weng, and Zhengyun Meng. 2019. "Multi-Vehicle Tracking via Real-Time Detection Probes and a Markov Decision Process Policy" Sensors 19, no. 6: 1309. https://doi.org/10.3390/s19061309