Name
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. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICCV.2013.318 | ICCV |
Keywords | Field | DocType |
car detection,cad,occlusion pattern generation,lssvm framework,pascal voc 2007 car dataset,object occlusion modeling,and-or structure discrimination,real image,automobiles,latent structural svm,different occlusion configuration,cad model,street parking dataset,discriminative and-or structures,synthetic images,and-or structure,car dataset pascal-voc-2007,object detection,modeling occlusion,occlusion pattern,dp algorithm,dynamic programming algorithm,deformable part-based model,car view estimation,dynamic programming,dpm,cad simulation strategy,occlusion configuration,support vector machines,occlusion modeling,cad simulation,annotating part occlusion | CAD,Dynamic programming,Computer vision,Object detection,Occlusion,Pattern recognition,Inference,Computer science,Support vector machine,Artificial intelligence,Real image,Discriminative model | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
17 | 0.64 | 29 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bo Li | 1 | 63 | 4.01 |
| Wenze Hu | 2 | 80 | 5.58 |
| Tianfu Wu | 3 | 331 | 26.72 |
| Song-Chun Zhu | 4 | 6580 | 741.75 |