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

TL;DR

This paper introduces CvHeat-DET, a novel network that leverages dynamic graphs and heat conduction principles to improve event-based object detection by effectively modeling contours and multi-scale features.

Contribution

The paper proposes a contour-aware heat conduction network utilizing dynamic graphs for enhanced event stream object detection, addressing limitations of existing CNN and Transformer-based methods.

Findings

Outperforms existing methods on three benchmark datasets

Effectively models object contours and multi-scale features

Validated through extensive experiments

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.