Das, SS (2022) A Data-Set and a Real-Time Method for Detection of Pointing Gesture from Depth Images. In: 6th International Conference on Computer Vision and Image Processing, CVIP 2021, 3 - 5 December 2021, IIT Ropar, Punjab, pp. 209-220.
Full text not available from this repository.Abstract
Nowadays, the trend is to use hand gestures to interact with digital devices such as computers, robots, drones, VR interfaces, etc. While interacting with digital devices, selection, pick and place, and navigation are important tasks which can be performed using pointing gestures. Thus, detection of pointing gestures is an important step for pointing gesture based interaction. In computer vision-based analysis of gestures, depth images of the hand region have been predominantly used. Currently, the only existing method to detect pointing gesture from depth images of the hand region has sub optimal performance as shown in our experiments. This can be attributed to the lack of a large data-set that could be used to detect pointing gestures. To overcome this limitation, we create a new large data-set (1,00,395 samples) for pointing gesture detection using depth images of the hand region. The data-set has a large variation in the hand poses and in the depth of the hand with respect to the depth sensor. The data-set will be made publicly available. We also propose a 3D convolutional neural network based real-time technique for pointing gesture detection from depth images of the hand region. The proposed technique performs much better than the existing technique with respect to various evaluation measures.
| Item Type: | Conference Paper |
|---|---|
| Publication: | Communications in Computer and Information Science |
| Publisher: | Springer Science and Business Media Deutschland GmbH |
| Additional Information: | The copyright for this article belongs to the Springer Science and Business Media Deutschland GmbH. |
| Keywords: | Convolutional neural networks; Gesture recognition; Palmprint recognition; Robots, Data set; Depth image; Device selection; Digital places; Gesture detections; Hand gesture; Large datasets; Natural interactions; Pointing gestures; Real time methods, Digital devices |
| Department/Centre: | Division of Electrical Sciences > Electrical Engineering |
| Date Deposited: | 23 Aug 2022 05:50 |
| Last Modified: | 23 Aug 2022 05:50 |
| URI: | https://eprints.iisc.ac.in/id/eprint/76180 |
Actions (login required)
 |
View Item |
