Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring

Abstract

This work presents advancements in multi-class vehicle detection using UAV cameras through the development of spatiotemporal object detection models. The study introduces a Spatio-Temporal Vehicle Detection Dataset (STVD) containing 6, 600 annotated sequential frame images captured by UAVs, enabling comprehensive training and evaluation of algorithms for holistic spatiotemporal perception. A YOLO-based object detection algorithm is enhanced to incorporate temporal dynamics, resulting in improved performance over single frame models. The integration of attention mechanisms into spatiotemporal models is shown to further enhance performance. Experimental validation demonstrates significant progress, with the best spatiotemporal model exhibiting a 16.22% improvement over single frame models, while it is demonstrated that attention mechanisms hold the potential for additional performance gains.

13 pages

References in corpus (7)

• A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
• Attention Mechanisms in Computer Vision: A Survey
• Is Space-Time Attention All You Need for Video Understanding?
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• A survey of the Vision Transformers and their CNN-Transformer based Variants
• Object Detection in Videos with Tubelet Proposal Networks
• Efficient ConvNet-based Object Detection for Unmanned Aerial Vehicles by Selective Tile Processing