A Hybrid mmWave and Camera System for Long-Range Depth Imaging

TL;DR

This paper introduces Metamoran, a hybrid system combining mmWave radar and camera data to achieve high-resolution, long-range depth imaging in cluttered environments, surpassing existing methods in accuracy and range.

Contribution

The paper presents a novel method to convert camera-derived object shapes into RF I/Q signals, enhancing radar processing for improved long-range depth imaging.

Findings

Estimates static object depth up to 90 m and moving objects up to 305 m.

Achieves median depth error of 28 cm, 13× better than naive radar+camera baseline.

Outperforms monocular depth estimation by 23×.

Abstract

mmWave radars offer excellent depth resolution even at very long ranges owing to their high bandwidth. But their angular resolution is at least an order-of-magnitude worse than camera and lidar systems. Hence, mmWave radar is not a capable 3-D imaging solution in isolation. We propose Metamoran, a system that combines the complimentary strengths of radar and camera to obtain accurate, high resolution depth images over long ranges even in high clutter environments, all from a single fixed vantage point. Metamoran enables rich long-range depth imaging with applications in security and surveillance, roadside safety infrastructure and wide-area mapping. Our approach leverages the high angular resolution from cameras using computer vision techniques, including image segmentation and monocular depth estimation, to obtain object shape. Our core contribution is a method to convert this object shape into an RF I/Q equivalent, which we use in a novel radar processing pipeline to help declutter the scene and capture extremely weak reflections from objects at long distances. We perform a detailed evaluation of Metamoran's depth imaging capabilities in 400 diverse scenes. Our evaluation shows that Metamoran estimates the depth of static objects up to 90 m and moving objects up to 305 m and with a median error of 28 cm, an improvement of 13$\times$ compared to a naive radar+camera baseline and 23$\times$ compared to monocular depth estimation.