基于鉴别与或结构的遮挡建模

Bo Li, Wenze Hu, Tianfu Wu, Song-Chun Zhu
{"title":"基于鉴别与或结构的遮挡建模","authors":"Bo Li, Wenze Hu, Tianfu Wu, Song-Chun Zhu","doi":"10.1109/ICCV.2013.318","DOIUrl":null,"url":null,"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.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"17 1","pages":"2560-2567"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"35","resultStr":"{\"title\":\"Modeling Occlusion by Discriminative AND-OR Structures\",\"authors\":\"Bo Li, Wenze Hu, Tianfu Wu, Song-Chun Zhu\",\"doi\":\"10.1109/ICCV.2013.318\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":6351,\"journal\":{\"name\":\"2013 IEEE International Conference on Computer Vision\",\"volume\":\"17 1\",\"pages\":\"2560-2567\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"35\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE International Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCV.2013.318\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2013.318","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 35

摘要

遮挡对现实世界中的物体检测提出了挑战。为了解决这一问题,本文使用and - or结构对物体遮挡进行建模,该结构(i)表示语义部分级别的遮挡,(ii)捕获不同遮挡配置(即物体部分可见性的不同组合)的规律。本文主要研究道路上的车辆检测。由于在真实图像上标注局部遮挡非常耗时且容易出错,我们提出使用放置在不同相对位置的CAD模型合成图像自动学习and或结构。在潜在结构支持向量机(LSSVM)框架下,从真实图像中学习模型参数。在推理中,采用了一种高效的动态规划算法。在实验中,我们测试了我们的方法在汽车检测和汽车视图估计。实验结果表明:(1)我们的CAD仿真策略能够生成真实场景的遮挡模式;(2)我们提出的and - or结构模型对于遮挡建模是有效的,在我们的自收集的街道停车数据集和Pascal VOC 2007汽车数据集上,都优于基于变形零件的模型(DPM) DPM, voc5。(iii)学习的模型与在两个公共数据集上测试的最先进的汽车视图估计方法相当。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Modeling Occlusion by Discriminative AND-OR Structures
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信