During the last few years, abandoned object detection has emerged as a hot topic in the video-surveillance community. As a consequence, a myriad of systems has been proposed for automatic monitoring of public and private places, while addressing several challenges affecting detection performance. Due to the complexity of these systems, researchers often address independently the different analysis stages such as foreground segmentation, stationary object detection, and abandonment validation. Despite the improvements achieved for each stage, the advances are rarely applied to the full pipeline, and therefore, the impact of each stage of improvement on the overall system performance has not been studied. In this paper, we formalize the framework employed by systems for abandoned object detection and provide an extensive review of state-of-the-art approaches for each stage. We also build a multi-configuration system allowing one to select a range of alternatives for each stage with the objective of determining the combination achieving the best performance. This multi-configuration is made available online to the research community. We perform an extensive evaluation by gathering a heterogeneous dataset from existing data. Such a dataset allows considering multiple and different scenarios, whereas presenting various challenges such as illumination changes, shadows, and a high density of moving objects, unlike existing literature focusing on a few sequences. The experimental results identify the most effective configurations and highlight design choices favoring robustness to errors. Moreover, we validated such an optimal configuration on additional datasets not previously considered. We conclude the paper by discussing open research challenges arising from the experimental comparison.

Multi-Target Multi-Camera (MTMC) vehicle tracking is an essential task of visual traffic monitoring, one of the main research fields of Intelligent Transportation Systems. Several offline approaches have been proposed to address this task; however, they are not compatible with real-world applications due to their high latency and post-processing requirements. This lack of suitable approaches motivates our proposal: A new low-latency online approach for MTMC tracking in scenarios with partially overlapping fields of view (FOVs), such as road intersections. Firstly, the proposed approach detects vehicles at each camera. Then, the detections are merged between cameras by applying cross-camera clustering based on appearance and location. Lastly, the clusters containing different detections of the same vehicle are temporally associated to compute the tracks on a frame-by-frame basis. The experiments show promising low-latency results while addressing real-world challenges such as the a priori unknown and time-varying number of targets and the continuous state estimation of them without performing any post-processing of the trajectories. Our code is available at http://www-vpu.eps.uam.es/publications/Online-MTMC-Tracking.

Cross-camera image data association is essential for many multi-camera computer vision tasks, such as multi-camera pedestrian detection, multi-camera multi-target tracking, 3D pose estimation, etc. This association task is typically modeled as a bipartite graph matching problem and often solved by applying minimum-cost flow techniques, which may be computationally demanding for large data. Furthermore, cameras are usually treated by pairs, obtaining local solutions, rather than finding a global solution at once for all multiple cameras. Other key issue is that of the affinity function: the widespread usage of non-learnable pre-defined distances, such as the Euclidean and Cosine ones. This paper proposes an effective approach for cross-camera data-association focused on a global solution, instead of processing cameras by pairs. To avoid the usage of fixed distances and thresholds, we leverage the connectivity of Graph Neural Networks, previously unused in this scope, using a Message Passing Network to jointly learn features and similarity functions. We validate the proposal for pedestrian cross-camera association, showing results over the EPFL multi-camera pedestrian dataset. Our approach considerably outperforms the literature data association techniques, without requiring to be trained in the same scenario in which it is tested. Our code is available at http://www-vpu.eps.uam.es/publications/gnn_cca.