Abstract / Description of output
The key to offering personalized services in smart spaces is knowing where a particular person is with a high degree of accuracy. Visual tracking is one such solution, but concerns arise around the potential leakage of raw video information and many people are not comfortable accepting cameras in their homes or workplaces. We propose a human tracking and identification system (mID11Parts of this work have been previously published in 2019 IEEE 15th International Conference on Distributed Computing in Sensor Systems (DCOSS) Zhao et. al. (2019)[1].) based on millimeter wave radar which has a high tracking accuracy, without being visually compromising. Using a low-cost, commercial, off-the-shelf radar, we first obtain sparse point clouds and form temporally associated trajectories. With the aid of a deep recurrent network, we identify individual users and show how to detect intruders. We evaluate and demonstrate our system, showing median position errors of 0.16 m, identification accuracy of 89% and intruder detection accuracy of 73% for 12 insiders. By increasing observation time from 2 s to 7 s, identification accuracy rises to 99%.
Original language | English |
---|---|
Article number | 102475 |
Number of pages | 11 |
Journal | Ad Hoc Networks |
Volume | 116 |
Early online date | 11 Mar 2021 |
DOIs | |
Publication status | Published - 19 Mar 2021 |
Keywords / Materials (for Non-textual outputs)
- Millimeter wave radar
- Tracking
- Identification
- Intruder detection