MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception

TL;DR

The MMVR dataset provides a large-scale, multi-view radar dataset for indoor perception, supporting object detection, pose estimation, and segmentation, with benchmarks across various environments and subjects.

Contribution

This paper introduces the first large-scale indoor multi-view radar dataset with extensive annotations and benchmarks for perception tasks, enabling advancements in indoor radar-based perception.

Findings

Benchmark results for object detection, pose estimation, and segmentation.

Performance differences between single and multiple subjects in cluttered environments.

Validation of dataset diversity and annotation quality.

Abstract

Compared with an extensive list of automotive radar datasets that support autonomous driving, indoor radar datasets are scarce at a smaller scale in the format of low-resolution radar point clouds and usually under an open-space single-room setting. In this paper, we scale up indoor radar data collection using multi-view high-resolution radar heatmap in a multi-day, multi-room, and multi-subject setting, with an emphasis on the diversity of environment and subjects. Referred to as the millimeter-wave multi-view radar (MMVR) dataset, it consists of $345$K multi-view radar frames collected from $25$ human subjects over $6$ different rooms, $446$K annotated bounding boxes/segmentation instances, and $7.59$ million annotated keypoints to support three major perception tasks of object detection, pose estimation, and instance segmentation, respectively. For each task, we report performance benchmarks under two protocols: a single subject in an open space and multiple subjects in several cluttered rooms with two data splits: random split and cross-environment split over $395$ 1-min data segments. We anticipate that MMVR facilitates indoor radar perception development for indoor vehicle (robot/humanoid) navigation, building energy management, and elderly care for better efficiency, user experience, and safety. The MMVR dataset is available at https://doi.org/10.5281/zenodo.12611978.