Cooperative Vision-Based Localization Networks with Communication Constraints

Abstract

Accurate location information is indispensable for the emerging applications of Internet of Vehicles (IoV), such as automatic driving and formation control. In the real scenario, vision-based localization has demonstrated superior performance to other localization methods for its stability and flexibility. In this paper, a scheme of cooperative vision-based localization with communication constraints is proposed. Vehicles collect images of the environment and distance measurements between each other. Then vehicles transmit the coordinates of feature points and distances with constrained bits to the edge to estimate their positions. The Fisher information matrix (FIM) for absolute localization is first obtained, based on which we derive the relative squared position error bound (SPEB) through subspace projection. Furthermore, we formulate the corresponding bit allocation problem for relative localization. Finally, a variancebased gradient descent (V-GD) algorithm is developed by considering the influence of photographing, distance measurements and quantization noises. Compared with conventional bit allocation methods, numerical results demonstrate the localization performance gain of our proposed algorithm with higher computational efficiency.