Tracking Motion and Proxemics using Thermal-sensor Array

TL;DR

This paper explores privacy-preserving indoor motion tracking and proxemics modeling using an 8x8 infrared thermal sensor array, employing image processing and machine learning techniques to detect movement and group interactions.

Contribution

It introduces a novel approach combining thermal sensor data with cross-correlation and SVM classification for motion detection and proxemics analysis.

Findings

Successfully inferred motion directions with cross-correlation.

Estimated number of human subjects using SVM classification.

Collected and analyzed 902 thermal scenes for validation.

Abstract

Indoor tracking has all-pervasive applications beyond mere surveillance, for example in education, health monitoring, marketing, energy management and so on. Image and video based tracking systems are intrusive. Thermal array sensors on the other hand can provide coarse-grained tracking while preserving privacy of the subjects. The goal of the project is to facilitate motion detection and group proxemics modeling using an 8 x 8 infrared sensor array. Each of the 8 x 8 pixels is a temperature reading in Fahrenheit. We refer to each 8 x 8 matrix as a scene. We collected approximately 902 scenes with different configurations of human groups and different walking directions. We infer direction of motion of a subject across a set of scenes as left-to-right, right-to-left, up-to-down and down-to-up using cross-correlation analysis. We used features from connected component analysis of each background subtracted scene and performed Support Vector Machine classification to estimate number of instances of human subjects in the scene.