ABROA : Audio-Based Room-Occupancy Analysis using Gaussian Mixtures and Hidden Markov Models
This is an incremental contribution to multimodal people counting algorithms, addressing occupancy analysis for applications like retail monitoring.
The paper tackled the problem of analyzing room occupancy using audio data by developing a model based on Gaussian Mixtures and Hidden Markov Models, achieving good accuracy in experiments with retail store audio data.
This paper outlines preliminary steps towards the development of an audio- based room-occupancy analysis model. Our approach borrows from speech recognition tradition and is based on Gaussian Mixtures and Hidden Markov Models. We analyze possible challenges encountered in the development of such a model, and offer several solutions including feature design and prediction strategies. We provide results obtained from experiments with audio data from a retail store in Palo Alto, California. Model assessment is done via leave-two-out Bootstrap and model convergence achieves good accuracy, thus representing a contribution to multimodal people counting algorithms.