Indoor Multipedestrian Multicamera Tracking Based on Fine Spatiotemporal Constraints

Abstract

As indoor space is the primary place for pedestrian activities, obtaining intelligent monitoring of indoor pedestrians is crucial for intelligent video surveillance. Previous studies have verified the effectiveness of spatio-temporal constraints in multitarget multi-camera tracking (MTMCT). Pedestrians are generally subjected to fine spatio-temporal constraints within buildings, based on which the indoor geographic information system (GIS) technology can obtain automatic spatio-temporal modeling. Combined with artificial intelligence (AI) technology, we established a research framework of "GIS+AI+IMPMCT." Specifically, we proposed indoor multi-pedestrian multi-camera tracking (IMPMCT) based on fine spatio-temporal constraints. First, we used GIS to map the indoor monitoring images of buildings and automatically model the fine spatio-temporal relationship among the semantics of the entrance of the surveillance zone. Subsequently, we used the machine learning model of pedestrian localization and tracking to obtain local trajectories of pedestrians and combined them with map information to extract entrance semantics of trajectories. Finally, we used the local trajectory semantics and surveillance entrance semantic constraints to obtain a fine spatio-temporal constraint weight matrix between trajectories and fused pedestrian’s apparent features to obtain trajectory matching results. To verify our method, we established an IMPMCT dataset containing fine indoor spatio-temporal information. Our method obtained an IDF1 of 0.805, which is better than those of other methods. Furthermore, the tracking results obtained by the proposed method contained both image space and geospatial trajectories.