Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MicroVision: An Open Dataset and Benchmark Models for Detecting Vulnerable Road Users and Micromobility Vehicles

Alexander Rasch, Rahul Rajendra Pai

Abstract

Micromobility is a growing mode of transportation, raising new challenges for traffic safety and planning due to increased interactions in areas where vulnerable road users (VRUs) share the infrastructure with micromobility, including parked micromobility vehicles (MMVs). Approaches to support traffic safety and planning increasingly rely on detecting road users in images -- a computer-vision task relying heavily on the quality of the images to train on. However, existing open image datasets for training such models lack focus and diversity in VRUs and MMVs, for instance, by categorizing both pedestrians and MMV riders as "person", or by not including new MMVs like e-scooters. Furthermore, datasets are often captured from a car perspective and lack data from areas where only VRUs travel (sidewalks, cycle paths). To help close this gap, we introduce the MicroVision dataset: an open image dataset and annotations for training and evaluating models for detecting the most common VRUs (pedestrians, cyclists, e-scooterists) and stationary MMVs (bicycles, e-scooters), from a VRU perspective. The dataset, recorded in Gothenburg (Sweden), consists of more than 8,000 anonymized, full-HD images with more than 30,000 carefully annotated VRUs and MMVs, captured over an entire year and part of almost 2,000 unique interaction scenes. Along with the dataset, we provide first benchmark object-detection models based on state-of-the-art architectures, which achieved a mean average precision of up to 0.723 on an unseen test set. The dataset and model can support traffic safety to distinguish between different VRUs and MMVs, or help monitoring systems identify the use of micromobility. The dataset and model weights can be accessed at https://doi.org/10.71870/eepz-jd52.

MicroVision: An Open Dataset and Benchmark Models for Detecting Vulnerable Road Users and Micromobility Vehicles

Abstract

Micromobility is a growing mode of transportation, raising new challenges for traffic safety and planning due to increased interactions in areas where vulnerable road users (VRUs) share the infrastructure with micromobility, including parked micromobility vehicles (MMVs). Approaches to support traffic safety and planning increasingly rely on detecting road users in images -- a computer-vision task relying heavily on the quality of the images to train on. However, existing open image datasets for training such models lack focus and diversity in VRUs and MMVs, for instance, by categorizing both pedestrians and MMV riders as "person", or by not including new MMVs like e-scooters. Furthermore, datasets are often captured from a car perspective and lack data from areas where only VRUs travel (sidewalks, cycle paths). To help close this gap, we introduce the MicroVision dataset: an open image dataset and annotations for training and evaluating models for detecting the most common VRUs (pedestrians, cyclists, e-scooterists) and stationary MMVs (bicycles, e-scooters), from a VRU perspective. The dataset, recorded in Gothenburg (Sweden), consists of more than 8,000 anonymized, full-HD images with more than 30,000 carefully annotated VRUs and MMVs, captured over an entire year and part of almost 2,000 unique interaction scenes. Along with the dataset, we provide first benchmark object-detection models based on state-of-the-art architectures, which achieved a mean average precision of up to 0.723 on an unseen test set. The dataset and model can support traffic safety to distinguish between different VRUs and MMVs, or help monitoring systems identify the use of micromobility. The dataset and model weights can be accessed at https://doi.org/10.71870/eepz-jd52.
Paper Structure (16 sections, 6 figures, 2 tables)

This paper contains 16 sections, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Data Collection
  5. Frame Extraction
  6. Annotations
  7. Inter-Annotator Agreement
  8. Benchmark Object-Detection Models
  9. Results
  10. The MicroVision Dataset
  11. Object-Detection Benchmark
  12. Discussion
  13. Dataset and Benchmark Models
  14. Implications and Applications
  15. Limitations and Future Work
  16. ...and 1 more sections

Figures (6)

  • Figure 1: Placement of the GoPro Max camera on the e-scooter (a) and bicycle (b) used for data collection.
  • Figure 2: Overview of the data processing pipeline, from raw videos to revised labels used for model training.
  • Figure 3: Example images and annotations from the MicroVision dataset for different object classes (columns) and object sizes (rows).
  • Figure 4: Bounding-box width and height distributions for the different object classes.
  • Figure 5: Successful example predictions on images from unseen test-set scenes for YOLO11 and RF-DETR, shown alongside ground-truth annotations. Numbers indicate predicted confidence scores (threshold = 0.5).
  • ...and 1 more figures