Dynamic Graph Induced Contour-aware Heat Conduction Network for Event-based Object Detection

2025-05-19

AI Summary

Existing event-stream object detection methods struggle to effectively model sharp object contours and multi-scale spatiotemporal features, while generic heat-conduction backbones are ill-suited for event data. To address this, we propose Dynamic Graph-guided Thermal Conduction Networks (DG-TCN). First, DG-TCN explicitly encodes event-driven contour information as spatially variant thermal diffusivity coefficients, enabling physics-informed, contour-aware feature propagation. Second, it constructs a dynamic graph structure to capture cross-scale spatiotemporal dependencies, integrating multi-scale graph convolutions with contour-modulated feature refinement. Evaluated on three event-based detection benchmarks, DG-TCN achieves state-of-the-art performance. It attains 3.2× faster inference speed than Transformer-based approaches and reduces parameter count by 41%. Moreover, DG-TCN significantly improves both accuracy and efficiency in low-light and high-speed scenarios.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Event-based Vision Sensors (EVS) have demonstrated significant advantages over traditional RGB frame-based cameras in low-light conditions, high-speed motion capture, and low latency. Consequently, object detection based on EVS has attracted increasing attention from researchers. Current event stream object detection algorithms are typically built upon Convolutional Neural Networks (CNNs) or Transformers, which either capture limited local features using convolutional filters or incur high computational costs due to the utilization of self-attention. Recently proposed vision heat conduction backbone networks have shown a good balance between efficiency and accuracy; however, these models are not specifically designed for event stream data. They exhibit weak capability in modeling object contour information and fail to exploit the benefits of multi-scale features. To address these issues, this paper proposes a novel dynamic graph induced contour-aware heat conduction network for event stream based object detection, termed CvHeat-DET. The proposed model effectively leverages the clear contour information inherent in event streams to predict the thermal diffusivity coefficients within the heat conduction model, and integrates hierarchical structural graph features to enhance feature learning across multiple scales. Extensive experiments on three benchmark datasets for event stream-based object detection fully validated the effectiveness of the proposed model. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvDET.

Problem

• Improving object detection in event streams using dynamic graphs
• Enhancing contour modeling in event-based vision sensors
• Balancing efficiency and accuracy in heat conduction networks

Innovation

• Dynamic graph models event stream contours
• Heat conduction balances efficiency and accuracy
• Hierarchical graph enhances multi-scale features