TY - GEN
T1 - See through smoke
T2 - 18th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2020
AU - Lu, Chris Xiaoxuan
AU - Rosa, Stefano
AU - Zhao, Peijun
AU - Wang, Bing
AU - Chen, Changhao
AU - Stankovic, John A.
AU - Trigoni, Niki
AU - Markham, Andrew
N1 - Publisher Copyright:
© 2020 ACM.
PY - 2020/6/15
Y1 - 2020/6/15
N2 - This paper presents the design, implementation and evaluation of milliMap, a single-chip millimetre wave (mmWave) radar based indoor mapping system targetted towards low-visibility environments to assist in emergency response. A unique feature of milliMap is that it only leverages a low-cost, off-the-shelf mmWave radar, but can reconstruct a dense grid map with accuracy comparable to lidar, as well as providing semantic annotations of objects on the map. milliMap makes two key technical contributions. First, it autonomously overcomes the sparsity and multi-path noise of mmWave signals by combining cross-modal supervision from a co-located lidar during training and the strong geometric priors of indoor spaces. Second, it takes the spectral response of mmWave reflections as features to robustly identify different types of objects e.g. doors, walls etc. Extensive experiments in different indoor environments show that milliMap can achieve a map reconstruction error less than 0.2m and classify key semantics with an accuracy of ∼ 90%, whilst operating through dense smoke.
AB - This paper presents the design, implementation and evaluation of milliMap, a single-chip millimetre wave (mmWave) radar based indoor mapping system targetted towards low-visibility environments to assist in emergency response. A unique feature of milliMap is that it only leverages a low-cost, off-the-shelf mmWave radar, but can reconstruct a dense grid map with accuracy comparable to lidar, as well as providing semantic annotations of objects on the map. milliMap makes two key technical contributions. First, it autonomously overcomes the sparsity and multi-path noise of mmWave signals by combining cross-modal supervision from a co-located lidar during training and the strong geometric priors of indoor spaces. Second, it takes the spectral response of mmWave reflections as features to robustly identify different types of objects e.g. doors, walls etc. Extensive experiments in different indoor environments show that milliMap can achieve a map reconstruction error less than 0.2m and classify key semantics with an accuracy of ∼ 90%, whilst operating through dense smoke.
KW - Emergency response
KW - Indoor mapping
KW - Millimeter wave radar
KW - Mobile robotics
UR - http://www.scopus.com/inward/record.url?scp=85088142862&partnerID=8YFLogxK
U2 - 10.1145/3386901.3388945
DO - 10.1145/3386901.3388945
M3 - Conference article published in proceeding or book
AN - SCOPUS:85088142862
T3 - MobiSys 2020 - Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
SP - 14
EP - 27
BT - MobiSys 2020 - Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
PB - Association for Computing Machinery, Inc
Y2 - 15 June 2020 through 19 June 2020
ER -