Objectives: Use 2D lidar to track people and recognize location-driven daily activities.
Method: A low cost, 2D, rotating Lidar system is used to collect the lidar radial distance and angle data. After converting the raw data to Cartesian coordinates, Hausdorff distance is used to detect the presence of a moving user. Then DBSCAN clustering algorithm is used to determine the number of users. Lastly RNN based human activity recognition classification system is built.
Results&Conclusions: The results indicate that it can provide a centimeter-level localization accuracy of 88% when recognizing 17 targeted location-related daily activities.
