Object Detection and Counting Challenges in Real Street Monitoring: Case Study of Homeless Encampments

Wide area urban street monitoring is highly demanding in various smart city applications. Manual monitoring is both laborious and time-consuming, hence automatic vision-based monitoring is a more feasible alternative. An essential part of vision-based street monitoring is detecting and counting objects of interest. However, these tasks are not straightforward due to various challenges, i.e., noisy conditions in a real environment, such as occlusion and high illumination. This study investigates the impact of these challenges on object detection and counting accuracy, then provides an empirical study to address the challenges with respect to video-based street monitoring. The selected case study demonstrates detecting and counting of homeless encampments in Los Angeles streets using street-level videos collected from a moving vehicle.