DocumentCode
3426933
Title
Modeling Occlusion by Discriminative AND-OR Structures
Author
Bo Li ; Wenze Hu ; Tianfu Wu ; Song-Chun Zhu
Author_Institution
Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
fYear
2013
fDate
1-8 Dec. 2013
Firstpage
2560
Lastpage
2567
Abstract
Occlusion presents a challenge for detecting objects in real world applications. To address this issue, this paper models object occlusion with an AND-OR structure which (i) represents occlusion at semantic part level, and (ii) captures the regularities of different occlusion configurations (i.e., the different combinations of object part visibilities). This paper focuses on car detection on street. Since annotating part occlusion on real images is time-consuming and error-prone, we propose to learn the the AND-OR structure automatically using synthetic images of CAD models placed at different relative positions. The model parameters are learned from real images under the latent structural SVM (LSSVM) framework. In inference, an efficient dynamic programming (DP) algorithm is utilized. In experiments, we test our method on both car detection and car view estimation. Experimental results show that (i) Our CAD simulation strategy is capable of generating occlusion patterns for real scenarios, (ii) The proposed AND-OR structure model is effective for modeling occlusions, which outperforms the deformable part-based model (DPM) DPM, voc5 in car detection on both our self-collected street parking dataset and the Pascal VOC 2007 car dataset pascal-voc-2007}, (iii) The learned model is on-par with the state-of-the-art methods on car view estimation tested on two public datasets.
Keywords
CAD; automobiles; dynamic programming; object detection; support vector machines; AND-OR structure discrimination; CAD simulation strategy; DP algorithm; DPM; LSSVM framework; Pascal VOC 2007 car dataset; car detection; car view estimation; deformable part-based model; dynamic programming algorithm; latent structural SVM; object detection; object occlusion modeling; occlusion configuration; occlusion pattern generation; street parking dataset; synthetic images; Computational modeling; Deformable models; Design automation; Estimation; Solid modeling; Training; Vectors; AND-OR structure; CAD simulation; Car Detection; Occlusion Modeling;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location
Sydney, NSW
ISSN
1550-5499
Type
conf
DOI
10.1109/ICCV.2013.318
Filename
6751429
Link To Document