A stereo vision geometric descriptor for place recognition and its GPU acceleration for autonomous vehicles applications

In this paper we present a geometric global descriptor dedicated for place recognition in autonomous vehicles applications that is based on stereo camera generated point clouds. We first present the approach used to record the 3D structure of the visible space. Then, we propose a parametric optimization to achieve the best performance by coupling the dedicated sensor (Stereo Camera) and the used algorithm. Finally, we propose a GPU implementation based on CUDA. Compared to a CPU, processing times on GPU are accelerated 7 times on a Jetson AGX Xavier and 30 times using a GeForce RTX 3080.