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

2025/12/16 by Mengyu Li, Li, Mengyu, Xingcheng Zhou +7
Computer Science · Engineering · #Advanced Neural Network Applications #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2512.14595

openalex publication_date 2025/12/16 · openalex created_date 2025/12/18 · openalex updated_date 2026/07/28

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.

Citations

• Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection
• TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras
• Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
• BoT-SORT: Robust Associations Multi-Pedestrian Tracking
• StrongSORT: Make DeepSORT Great Again
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• YOLOX: Exceeding YOLO Series in 2021
• FAST-Dynamic-Vision: Detection and Tracking Dynamic Objects with Event and Depth Sensing
• Learning to Detect Objects with a 1 Megapixel Event Camera
• DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
• A Large Scale Event-based Detection Dataset for Automotive
• YOLOv3: An Incremental Improvement
• Path Aggregation Network for Instance Segmentation
• DDD17: End-To-End DAVIS Driving Dataset
• Simple Online and Realtime Tracking with a Deep Association Metric
• Feature Pyramid Networks for Object Detection
• MOT16: A Benchmark for Multi-Object Tracking
• You Only Look Once: Unified, Real-Time Object Detection

Related

• TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras
• Event-based vision sensing and its application to pedestrian detection for intelligent transportation and surveillance
• MEVDT: Multi-Modal Event-Based Vehicle Detection and Tracking Dataset
• EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection
• CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios