On-Line Activities Co-Chairs

Remote gesturing visualization contributes to the efficiency of distant collaboration tasks because it enables coordination among participant's action and talk. This paper presents computer vision improvements of VideoArms, a collaborative system proposed by Tang et al. coupling a sensitive board with a video capture of participant's gesture. The main contributions address robustness, constraints relaxation on lightning condition ,and the types of shared images and objects or gesture to be visualized at the distant place. 1. Remote gesture visualization Remote gesturing visualization brings significant improvements in performing distant collaborative tasks because it allows the coordination among participant's action and talk. As Kraut et al. [5] state, visual information plays at least two inter-related roles in collaborative tasks: conversational grounding and situational awareness. Being aware of the distant gesture helps collaborating more efficiently. There is significantly less talk about the talk (or about the task to be done)[4]. Visual information provides mutual awareness through the identification of the distant user actions. It is particularly effective for multi-users interfaces offering simultaneous interactions of co-located and distant participants. The rapidly arising question is to identify who is doing what at the distant place when solely the action results are visible. Thus, remote gesturing visualization maintains up-to-date mental models of the tasks and others' activities. As a consequence, it helps people "to plan what to say or do next and to coordinate their utterances and actions with those of their partners" [5]. Furthermore, it helps to preserve common social rules within the interaction. It avoids unwanted simultaneous actions on a same object as one will not take an object right from the partner's hands.