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

TL;DR

This paper presents a self-supervised learning framework for multi-object tracking of passengers and baggage at airport security checkpoints using overhead cameras, enhancing detection accuracy and multi-view tracking efficiency.

Contribution

The novel SSL-based detection and multi-view association approach improves tracking accuracy without increasing inference time in security checkpoint scenarios.

Findings

Detection accuracy improved by up to 42%.

Multi-object tracking accuracy reached 89%.

Inference time remained under 15 ms.

Abstract

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 pseudo-label 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 self-supervised 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.