...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Pattern Analysis and Machine Intelligence >Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
【24h】

Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

机译：表示上下文和遮挡的学习与/或模型，用于汽车检测和视点估计

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a method for learning an And-Or model to represent context and occlusion for car detection and viewpoint estimation. The learned And-Or model represents car-to-car context and occlusion configurations at three levels: (i) spatially-aligned cars, (ii) single car under different occlusion configurations, and (iii) a small number of parts. The And-Or model embeds a grammar for representing large structural and appearance variations in a reconfigurable hierarchy. The learning process consists of two stages in a weakly supervised way (i.e., only bounding boxes of single cars are annotated). First, the structure of the And-Or model is learned with three components: (a) mining multi-car contextual patterns based on layouts of annotated single car bounding boxes, (b) mining occlusion configurations between single cars, and (c) learning different combinations of part visibility based on CAD simulations. The And-Or model is organized in a directed and acyclic graph which can be inferred by Dynamic Programming. Second, the model parameters (for appearance, deformation and bias) are jointly trained using Weak-Label Structural SVM. In experiments, we test our model on four car detection datasets—the KITTI dataset [1] , the PASCAL VOC2007 car dataset [2] , and two self-collected car datasets, namely the Street-Parking car dataset and the Parking-Lot car dataset, and three datasets for car viewpoint estimation—the PASCAL VOC2006 car dataset [2] , the 3D car dataset [3] , and the PASCAL3D+ car dataset [4] . Compared with state-of-the-art variants of deformable part-based models and other methods, our model achieves significant improvement consistently on the four detection datasets, and comparable performance on car viewpo- nt estimation.
机译：本文提出了一种学习“或”模型来表示上下文和遮挡的方法，以用于汽车检测和视点估计。所学习的“与”或“或”模型在三个级别上代表了汽车到汽车的环境和遮挡配置：（i）空间对齐的汽车，（ii）具有不同遮挡配置的单辆汽车，以及（iii）少量零件。 And-Or模型嵌入了一种语法，用于在可重新配置的层次结构中表示较大的结构和外观变化。学习过程由弱监督的两个阶段组成（即仅注释单个汽车的边界框）。首先，通过三个部分学习“与”或“奥”模型的结构：（a）基于带注释的单车边界框的布局挖掘多车上下文模式，（b）挖掘单车之间的遮挡配置，以及（c）学习基于CAD模拟的零件可见性的不同组合。 And-Or模型以有向无环图的形式组织，可以通过动态编程来推断。其次，使用弱标签结构SVM共同训练模型参数（用于外观，变形和偏差）。在实验中，我们在四个汽车检测数据集上测试了我们的模型-KITTI数据集[1]，PASCAL VOC2007汽车数据集[2]和两个自收集的汽车数据集，即街边停车汽车数据集和Parking-Lot汽车数据集和三个用于汽车视点估计的数据集-PASCAL VOC2006汽车数据集[2]，3D汽车数据集[3]和PASCAL3D +汽车数据集[4]。与基于可变形零件的模型和其他方法的最新变体相比，我们的模型在四个检测数据集上均实现了显着改进，并且在汽车视点估计方面具有可比的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号