End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera

TL;DR

This paper introduces an end-to-end deep learning approach using monocular camera data to accurately estimate inter-vehicle distance and relative velocity for ADAS, integrating multiple visual cues and a vehicle-centric sampling mechanism.

Contribution

It presents a novel monocular camera-based method that combines deep features, scene geometry, and optical flow, with a vehicle-centric sampling to improve estimation accuracy and robustness.

Findings

Outperforms state-of-the-art methods in accuracy

Achieves real-time computational speed

Has a low memory footprint

Abstract

Inter-vehicle distance and relative velocity estimations are two basic functions for any ADAS (Advanced driver-assistance systems). In this paper, we propose a monocular camera-based inter-vehicle distance and relative velocity estimation method based on end-to-end training of a deep neural network. The key novelty of our method is the integration of multiple visual clues provided by any two time-consecutive monocular frames, which include deep feature clue, scene geometry clue, as well as temporal optical flow clue. We also propose a vehicle-centric sampling mechanism to alleviate the effect of perspective distortion in the motion field (i.e. optical flow). We implement the method by a light-weight deep neural network. Extensive experiments are conducted which confirm the superior performance of our method over other state-of-the-art methods, in terms of estimation accuracy, computational speed, and memory footprint.