Resource-aware distributed particle filtering for cluster-based object tracking in wireless camera networks

Hong, Kimin; Medeiros, Henry; Shin, Paul J.; Park, Johnny

doi:10.1504/ijsnet.2016.078322

Cited by 3 publications

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Tracking Passengers and Baggage Items Using Multiple Overhead Cameras at Security Checkpoints

Siddique

Medeiros

2023

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a Self-Supervised Learning (SSL) technique to provide the model information about instance segmentation uncertainty from overhead images. Our SSL approach improves object detection by employing a test-time data augmentation and a regression-based, rotation-invariant pseudolabel refinement technique. Our pseudo-label generation method provides multiple geometrically-transformed images as inputs to a Convolutional Neural Network (CNN), regresses the augmented detections generated by the network to reduce localization errors, and then clusters them using the mean-shift algorithm. The selfsupervised detector model is used in a single-camera tracking algorithm to generate temporal identifiers for the targets. Our method also incorporates a multi-view trajectory association mechanism to maintain consistent temporal identifiers as passengers travel across camera views. An evaluation of detection, tracking, and association performances on videos obtained from multiple overhead cameras in a realistic airport checkpoint environment demonstrates the effectiveness of the proposed approach. Our results show that self-supervision improves object detection accuracy by up to 42% without increasing the inference time of the model. Our multi-camera association method achieves up to 89% multi-object tracking accuracy with an average computation time of less than 15 ms.

show abstract