For the purpose of detecting human group activity and its recognition, a novel algorithm based on heat map is presented using PIR sensors in order to optimize the targeted digital advertising in shopping complexes. Firstly, we use the PIR (pyroelectric infrared) sensors to detect the presence of people. The projected algorithm first represents trajectories of people as sequence of “heat sources” followed by the application of a thermal diffusion process to consequently generate a heat map (HM) in order to depict and illustrate the group activities. The heat maps are generated with respect to multiple factors like temporal factors such as time of day and day of week/month, cultural factors such as during festivals or other notable occasions, etc. The generated heat map brings forth an original surface fitting (SF) method, which can also be applied for identifying human group activities in academic buildings and hostel blocks. The proposed heat map can effectively retain the temporal motion knowledge of the crowd of humans, and the proposed surface fitting can efficiently fetch the features of the heat map for activity discovery and perception. By using heat maps in targeted digital advertising, signs and billboards can be optimized.

Group activity recognition, Heat map, Human crowd, Object detection algorithm, PIR sensors, Surface fitting,
EAI/Springer Innovations in Communication and Computing
Erasmus School of Economics

Rajasekaran, R. (Rajkumar), Rasool, F. (Fiza), Srivastava, S. (Sparsh), Masih, J. (Jolly), & Rajest, S.S. (S. Suman). (2020). Heat Maps for Human Group Activity in Academic Blocks. In EAI/Springer Innovations in Communication and Computing. doi:10.1007/978-3-030-44407-5_16