Coupling-and-Decoupling: A Hierarchical Model for Occlusion-Free Car Detection
详细信息 查看全文
- 作者：Bo Li (20) (21) (22)
Tianfu Wu (21) (22)
Wenze Hu (22) (23)
Mingtao Pei (20) - 刊名：Lecture Notes in Computer Science
- 出版年：2013
- 出版时间：2013
- 年：2013
- 卷：7724
- 期：1
- 页码：176-189
- 全文大小：891KB
- 参考文献：1. Choi, J.Y., Sung, K.S., Yang, Y.K.: Multiple Vehicles Detection and Tracking based on Scale-Invariant Feature Transform. In: ITSC, pp. 528-33 (2007)
2. Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR, pp. 886-93 (2005)
3. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) Results (2007), http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
4. Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Discriminatively Trained Deformable Part Models, Release 4 (2010), http://people.cs.uchicago.edu/~pff/latent-release4/
5. Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object Detection with Discriminatively Trained Part-Based Models. TPAMI?32, 1627-645 (2010) CrossRef
6. Felzenszwalb, P.F., Huttenlocher, D.P.: Distance Transforms of Sampled Functions. Technical report 2004-1963, Cornell University CIS (2004)
7. Gupte, S., Masoud, O., Martin, R.F.K., Papanikolopoulos, N.P.: Detection and Classification of Vehicles. TITS?3, 37-7 (2002)
8. Lai, A.H.S., Fung, G.S.K., Yung, N.H.C.: Vehicle Type Classification from Visual-based Dimension Estimation. In: ITSC, pp. 201-06 (2001)
9. Leotta, M.J., Mundy, J.L.: Vehicle Surveillance with a Generic, Adaptive, 3D Vehicle Model. TPAMI?33, 1457-469 (2011) CrossRef
10. Liu, X., Dai, B., He, H.: Real-Time On-Road Vehicle Detection Combining Specific Shadow Segmentation and SVM Classification. In: ICDMA, pp. 885-88 (2011)
11. Ott, P., Everingham, M.: Shared Parts for Deformable Part-based Models. In: CVPR, pp. 1513-520 (2011)
12. Petrovic, V.S., Cootes, T.F.: Analysis of Features for Rigid Structure Vehicle Type Recognition. In: BMVC, pp. 587-96 (2004)
13. Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large Margin Methods for Structured and Interdependent Output Variables. JMLR?6, 1453-484 (2005)
14. Yu, C.N.J., Joachims, T.: Learning Structural SVMs with Latent Variables. In: ICML, pp. 1169-176 (2009)
15. Yuille, A.L., Rangarajan, A.: The Concave-Convex Procedure (CCCP). In: NIPS, pp. 1033-040 (2001)
16. Zhu, L., Chen, Y., Yuille, A.L., Freeman, W.T.: Latent Hierarchical Structural Learning for Object Detection. In: CVPR, pp. 1062-069 (2010)
17. Zhu, S.C., Mumford, D.: A Stochastic Grammar of Images. FTCGV?2, 259-62 (2006) - 作者单位：Bo Li (20) (21) (22)
Tianfu Wu (21) (22)
Wenze Hu (22) (23)
Mingtao Pei (20)
20. Beijing Lab of Intelligent Information, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, P.R.China
21. BUPT-Seesoft Joint Lab of Visual Computing and Image Communication, Beijing University of Posts and Telecommunications (BUPT), Beijing, 100876, P.R.China
22. Lotus Hill Research Institute, Ezhou, P.R.China
23. Department of Statistics, University of California, Los Angeles, USA - ISSN：1611-3349
文摘
Handling occlusions in object detection is a long-standing problem. This paper addresses the problem of X-to-X-occlusion-free object detection (e.g. car-to-car occlusions in our experiment) by utilizing an intuitive coupling-and-decoupling strategy. In the “coupling-stage, we model the pair of occluding X’s (e.g. car pairs) directly to account for the statistically strong co-occurrence (i.e. coupling). Then, we learn a hierarchical And-Or directed acyclic graph (AOG) model under the latent structural SVM (LSSVM) framework. The learned AOG consists of, from the top to bottom, (i) a root Or-node representing different compositions of occluding X pairs, (ii) a set of And-nodes each of which represents a specific composition of occluding X pairs, (iii) another set of And-nodes representing single X’s decomposed from occluding X pairs, and (iv) a set of terminal-nodes which represent the appearance templates for the X pairs, single X’s and latent parts of the single X’s, respectively. The part appearance templates can also be shared among different single X’s. In detection, a dynamic programming (DP) algorithm is used and as a natural consequence we decouple the two single X’s from the X-to-X occluding pairs. In experiments, we test our method on roadside cars which are collected from real traffic video surveillance environment by ourselves. We compare our model with the state-of-the-art deformable part-based model (DPM) and obtain better detection performance.