Gesture Recognition for Chinese Traffic Police

Abstract

In this paper, we present a five-part body model to recognize gestures made by Chinese traffic police in complex scenes for driver assistance systems and intelligent vehicles. Unlike most previous methods which require a training stage or a 3D measuring device to construct the body part appearance model, we propose to use the max-covering scheme to learn a five-part body model in an automatic way. Experimental results show that good recognition results can be obtained using the proposed method.

I See Your Gesture: A VR-Based Study of Bidirectional Communication between Pedestrians and Automated Vehicles

“…e underlying idea was that future AVs will have difficulty in reading pedestrians' implicit body language and that explicit gestures are therefore needed. Besides, future AVs may have to detect explicit gestures of vulnerable road users for safety reasons (e.g., detection of an extended arm of cyclists [34,36]) and to comply with traffic rules (e.g., being responsive to signals used by traffic police [31][32][33]). Furthermore, as others [8,10,37] have shown as well, the present study demonstrated that an eHMI makes visible the invisible.…”

“…In real-life applications, our hand gesture concept would require the AV computer vision systems to recognize these gestures. Various studies have already been performed in this area, such as the detection of gestures made by police officers [31][32][33] or cyclists [34]. In the present lab-based study, we used a motion suit [9], which allowed us to measure the pedestrians' bodily state.…”