TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios

2025-12-16

AI Summary

To address the lack of dedicated multi-object tracking (MOT) benchmarks for event cameras in intelligent transportation systems (ITS), this paper introduces EC-ITS—the first event-based MOT dataset specifically designed for traffic scenarios, supporting both vehicle and pedestrian detection and tracking. EC-ITS features high-temporal-resolution, low-latency, high-dynamic-range event streams captured under challenging conditions including low illumination and high-speed motion. We propose a lightweight event feature extractor integrated with a detection-driven tracking paradigm to establish a standardized evaluation benchmark. Experimental results demonstrate that our method significantly improves trajectory association stability and tracking accuracy on EC-ITS, effectively mitigating the performance degradation commonly observed with conventional frame-based cameras under low-light and rapid-motion conditions. This work fills a critical gap by providing the first systematic event-based dataset and evaluation framework for ITS applications.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Application Domains: Transportation

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

In Intelligent Transportation Systems (ITS), multi-object tracking is primarily based on frame-based cameras. However, these cameras tend to perform poorly under dim lighting and high-speed motion conditions. Event cameras, characterized by low latency, high dynamic range and high temporal resolution, have considerable potential to mitigate these issues. Compared to frame-based vision, there are far fewer studies on event-based vision. To address this research gap, we introduce an initial pilot dataset tailored for event-based ITS, covering vehicle and pedestrian detection and tracking. We establish a tracking-by-detection benchmark with a specialized feature extractor based on this dataset, achieving excellent performance.

Problem

• Addresses poor performance of frame-based cameras in dim lighting and high-speed motion
• Introduces a dataset for event-based multi-object tracking in traffic scenarios
• Establishes a benchmark for detection and tracking using event camera data

Innovation

• Event cameras for low latency tracking
• Dataset for event-based traffic detection
• Specialized feature extractor benchmark performance