An IoT System for Smart Building Combining Multiple mmWave FMCW Radars Applied to People Counting

This repository is related with the next paper. Please cite us if this code is useful to you.

Barral, V., Dominguez-Bolano, T., Escudero, C. J., & Garcia-Naya, J. A. An IoT System for Smart Building Combining Multiple mmWave FMCW Radars Applied to People Counting.

Python Scripts

• count_plot.py: Generates a plot comparing image tracking estimation, radar with DBSCAN, and radar with OPTICS. Use example:

python count_plot.py count_video_full.log count_radar_moving_average_30_optics.log count_radar_moving_average_30_dbscan.log "Video" "Radar with OPTICS" "Radar with DBSCAN" average_count_full_optics_dbscan.pdf

Radar measurements

• test_0.bag: FMCW mmWave radar measurements from three IWR6843 devices (ISK and AOP). Is a ROS (Robotic Operative System) log, can be played with rosbag play test_0.bag

Radar people counting logs

• count_radar_moving_average_30_dbscan.log: radar people counting estimation using a 30 seconds moving average and DBSCAN as clustering algorithm.

• count_radar_moving_average_30_optics.log: radar people counting estimation using a 30 seconds moving average and OPTICS as clustering algorithm.

Image tracking

Videos

• test_0_cam_0.mp4: Camera 0 capture.
• test_0_cam_1.mp4: Camera 1 capture.

Image tracking logs

• test_0_cam_0_interp.txt: People count in camera 0
• test_0_cam_1_interp.txt: People count in camera 1

The files have the following format:

frame_number, track_id, bb_left, bb_top, bb_width, bb_height, conf, x, y, z The coordinates x, y, z are always -1 The bb fields define the bounding box of the detection If multiple people are detected in a frame, there are several lines with that frame_number, but with different track_ids.

Image people counting logs

• count_video_full.log: image tracking people counting estimation using a 30 seconds moving average.