CAD 120 affordance dataset
收藏资源简介：
% ============================================================================== % CAD 120 Affordance Dataset % Version 1.0 % ------------------------------------------------------------------------------ % If you use the dataset please cite: % % Johann Sawatzky, Abhilash Srikantha, Juergen Gall. % Weakly Supervised Affordance Detection. % IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17) % % and % % H. S. Koppula and A. Saxena. % Physically grounded spatio-temporal object affordances. % European Conference on Computer Vision (ECCV'14) % % Any bugs or questions, please email sawatzky AT iai DOT uni-bonn DOT de. % ============================================================================== This is the CAD 120 Affordance Segmentation Dataset based on the Cornell Activity Dataset CAD 120 (see http://pr.cs.cornell.edu/humanactivities/data.php). Content frames/*.png: RGB frames selected from Cornell Activity Dataset. To find out the location of the frame in the original videos, see video_info.txt. object_crop_images/*.png image crops taken from the selected frames and resized to 321*321. Each crop is a padded bounding box of an object the human interacts with in the video. Due to the padding, the crops may contain background and other objects. In each selected frame, each bounding box was processed. The bounding boxes are already given in the Cornell Activity Dataset. The 5-digit number gives the frame number, the second number gives the bounding box number within the frame. segmentation_mat/*.mat 321*321*6 segmentation masks for the image crops. Each channel corresponds to an affordance (openabe, cuttable, pourable, containable, supportable, holdable, in this order). All pixels belonging to a particular affordance are labeled 1 in the respective channel, otherwise 0. segmentation_png/*.png 321*321 png images, each containing the binary mask for one of the affordances. lists/*.txt Lists containing the train and test sets for two splits. The actor split ensures that train and test images stem from different videos with different actors while the object split ensures that train and test data have no (central) object classes in common. The train sets are additionally subdivided into 3 subsets A,B and C. For the actor split, the subsets stem from different videos. For the object split, each subset contains every third crop of the train set. crop_coordinate_info.txt Maps image crops to their coordinates in the frames. hpose_info.txt Maps frames to 2d human pose coordinates. Hand annotated by us. object_info.txt Maps image crops to the (central) object it contains. visible_affordance_info.txt Maps image crops to affordances visible in this crop %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%55 The crops contain the following object classes: 1.table 2.kettle 3.plate 4.bottle 5.thermal cup 6.knife 7.medicine box 8.can 9.microwave 10.paper box 11.bowl 12.mug Affordances in our set: 1.openable 2.cuttable 3.pourable 4.containable 5.supportable 6.holdable Note that our object affordance labeling differs from the Cornell Activity Dataset: E.g. the cap of a pizza box is considered to be supportable.
% ============================================================================== % CAD 120 功能 affordance (Affordance) 数据集 % 版本 1.0 % ------------------------------------------------------------------------------ % 若使用本数据集，请引用以下文献： % % Johann Sawatzky、Abhilash Srikantha、Juergen Gall. % 弱监督功能 affordance 检测 % IEEE 计算机视觉与模式识别会议（CVPR'17） % 以及 % % H. S. Koppula 与 A. Saxena. % 基于物理基础的时空对象功能 affordance % 欧洲计算机视觉大会（ECCV'14） % % 如有任何错误或疑问，请发送邮件至 sawatzky AT iai DOT uni-bonn DOT de。 % ============================================================================== 本数据集为基于康奈尔活动数据集CAD 120的CAD 120功能 affordance 分割数据集，详细信息可参考 http://pr.cs.cornell.edu/humanactivities/data.php。 ### 数据集内容说明 1. **frames/*.png**：从康奈尔活动数据集选取的RGB帧。若需查找该帧在原始视频中的具体位置，请参阅`video_info.txt`文件。 2. **object_crop_images/*.png**：从选定帧中截取的图像块，经缩放至321×321像素。每个图像块对应人类在视频中交互对象的填充式边界框（bounding box），由于填充操作的存在，图像块中可能包含背景区域与其他无关对象。每个选定帧内的所有边界框均已完成处理，边界框信息已包含在康奈尔活动数据集中。文件名中5位数字为帧编号，第二位数字为该帧内的边界框序号。 3. **segmentation_mat/*.mat**：适配图像块的321×321×6维度分割掩码（segmentation mask）。每个通道对应一种功能 affordance，顺序依次为：可打开（openable）、可切割（cuttable）、可倾倒（pourable）、可容纳（containable）、可支撑（supportable）、可握持（holdable）。属于某一特定功能 affordance 的所有像素在对应通道中被标记为1，其余像素标记为0。 4. **segmentation_png/*.png**：321×321像素的PNG图像，每张图像对应一种功能 affordance 的二进制掩码。 5. **lists/*.txt**：包含两种划分方式下的训练集与测试集列表。其中，演员划分（actor split）确保训练与测试图像来自不同演员参与的不同视频；对象划分（object split）确保训练与测试数据无共享的核心对象类别。训练集进一步被划分为A、B、C三个子集：演员划分下，各子集来自不同视频；对象划分下，每个子集包含训练集中每第三个图像块。 6. **crop_coordinate_info.txt**：建立图像块与原始帧中对应坐标的映射关系。 7. **hpose_info.txt**：建立帧与二维人体姿态坐标的映射关系，该信息由人工标注完成。 8. **object_info.txt**：建立图像块与其包含的核心对象的映射关系。 9. **visible_affordance_info.txt**：建立图像块与该图像块中可见的功能 affordance 的映射关系。 ### 数据集涵盖的对象类别 1. 桌子 2. 水壶 3. 盘子 4. 瓶子 5. 保温杯 6. 刀具 7. 药盒 8. 易拉罐 9. 微波炉 10. 纸盒 11. 碗 12. 马克杯 ### 数据集定义的功能 affordance 类别 1. 可打开（openable） 2. 可切割（cuttable） 3. 可倾倒（pourable） 4. 可容纳（containable） 5. 可支撑（supportable） 6. 可握持（holdable） 请注意，本数据集的对象功能 affordance 标注规则与康奈尔活动数据集存在差异：例如，披萨盒的盒盖被归类为可支撑类别。
