DGNN-YOLO: Interpretable Dynamic Graph Neural Networks with YOLO11 for Small Object Detection and Tracking in Traffic Surveillance

2024-11-26

AI Summary

To address the poor robustness of detecting and tracking small targets—such as pedestrians and non-motorized vehicles—in traffic surveillance under occlusion, low-resolution imaging, and dynamically complex scenes, this paper proposes a spatiotemporal modeling framework integrating YOLO11 with a Dynamic Graph Neural Network (DGNN). The DGNN innovatively constructs and incrementally updates an adaptive graph structure in real time to explicitly model spatiotemporal interactions among targets. Additionally, Grad-CAM–based techniques are incorporated to enable model-agnostic interpretability analysis. Experiments on challenging traffic scenarios demonstrate state-of-the-art performance: mAP@0.5:0.95 = 0.6476 (precision = 0.8382, recall = 0.6875), significantly outperforming existing methods—particularly for small targets and severely occluded instances.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate detection and tracking of small objects, such as pedestrians, cyclists, and motorbikes, is critical for traffic surveillance systems, which are crucial for improving road safety and decision-making in intelligent transportation systems. However, traditional methods face challenges such as occlusion, low resolution, and dynamic traffic conditions, necessitating innovative approaches to address these limitations. This paper introduces DGNN-YOLO, a novel framework integrating dynamic graph neural networks (DGNN) with YOLO11 to enhance small-object detection and tracking in traffic surveillance systems. The framework leverages YOLO11's advanced spatial feature extraction capabilities for precise object detection and incorporates a DGNN to model spatial-temporal relationships for robust real-time tracking dynamically. By constructing and updating graph structures, DGNN-YOLO effectively represents objects as nodes and their interactions as edges, thereby ensuring adaptive and accurate tracking in complex and dynamic environments. Additionally, Grad-CAM, Grad-CAM++, and Eigen-CAM visualization techniques were applied to DGNN-YOLO to provide model-agnostic interpretability and deeper insights into the model's decision-making process, enhancing its transparency and trustworthiness. Extensive experiments demonstrated that DGNN-YOLO consistently outperformed state-of-the-art methods in detecting and tracking small objects under diverse traffic conditions, achieving the highest precision (0.8382), recall (0.6875), and mAP@0.5:0.95 (0.6476), showing its robustness and scalability, particularly in challenging scenarios involving small and occluded objects. This study provides a scalable, real-time traffic surveillance and analysis solution, significantly contributing to intelligent transportation systems.

Problem

• Small Object Detection
• Occlusion Handling
• Complex Dynamic Environments

Innovation

• DGNN-YOLO
• Small Object Detection
• Interpretable AI