LAMAR: LiDAR based Multi-inhabitant Activity Recognition
Mohammad Arif Ul Alam, Fernando Mazzoni, Md Mahmudur Rahman, Jared Q Widberg · 2020
Human activity recognition (HAR) is a an important field of study concerned with identifying the specific movement or action of a person based on sensor data. Movements are often typical activities, such as walking, lying, standing, and sitting which has high significance in assessing health related vital signs. While accuracy of HAR been improved significantly using advanced deep learning techniques, employment of LiDAR (Light detection and Ranging) has been rarely explored due to the high cost of sensor device as well as the complexity of LiDAR point-cloud data. In this paper, we propose LAMAR (LiDAR-based Adaptive Multi-inhabitant Activity Recognition), a low-resolution low-cost (<300$) solid-state LiDAR-based multiple-inhabitant activity recognition system. LAMAR incorporates a series of existing signal processing techniques and a novel adaptive deep learning model to improve multi-inhabitant HAR performance. In this regard, at first, LAMAR posits a voxelized feature representation and clustering based multiple person tracking method to separate individual person related point-clouds. Then, it employes a novel variational autoencoder based domain adaptation technique to improve activity recognition performance by transferring domain knowledge from high resolution to low resolution LiDAR data. Our experimental evaluation on two datasets (one real-time collected data and another publicly available available data) provided significant improvement of HAR performance (94%) in multiple-inhabitant scenario with 63% improvement of multiple person tracking than existing work.