遇见数据集

Re-defined Event-based Dataset of Assembly Tasks (REDAT24)

收藏
Zenodo2025-05-23 更新2026-05-26 收录
官方服务:

资源简介:

Description: The Re-defined Event-based Dataset of Assembly Tasks (REDAT24), features four representative assembly primitive actions, idle, pick, place, and screw. These actions are performed on objects from the open-source benchmark CT-Benchmark. REDAT24 has been recorded to investigate how modifying the definition of movements affect classification of movement primitives of the Event-based Dataset of Assembly Tasks (EDAT24). The EDAT24 includes some transitions considered as parts of the primitive actions, e.g. the approach of the hand to the object before a screw. However, other transitions are not represented: the transition from place or screw to idle are not accounted for. Available Data: The REDAT24 dataset features approximately 50 videos per class recorded with the DAVIS240C event camera, excluding transitions entirely from the gesture definitions. Gesture definitions have been redefined to ensure that each action is independent, with no overlap into subsequent actions, thereby creating clear boundaries between distinct gestures. The event camera captured events and APS frames simultaneously with a resolution of 240 pixels × 180 pixels. The videos last around 2 seconds each, although static gestures like idle and screw tend to be longer than dynamic gestures such as pick and place. Event data is available in the original recorded format, .aedat (AEDAT 2.0), and is accompanied with a .csv file containing the timestamps with the start and end time of the recording, and with a .npy file which contains the information from the events (coordinates x and y, timestamp and polarity). The videos are labelled using the format primitive/task_nSample.aedat, where: primitive corresponds to the various primitive tasks (idle, pick, place, and screw) task corresponds to the name of the part of the CT-Benchmark the user is interacting with. nSample corresponds to the sample number for each task. The Python code used to record, timestamp and convert into .npy is available at here. Note: REDAT24 was captured by a different user than in EDAT24

提供机构:
Zenodo
创建时间:
2025-04-22
二维码
社区交流群
二维码
科研交流群
商业服务