Vehicle detection from GSV imagery: Predicting travel behaviour for cycling and motorcycling using Computer Vision

• URL: http://arxiv.org/abs/2508.12794v2
• Date: Tue, 19 Aug 2025 14:43:20 GMT
• Title: Vehicle detection from GSV imagery: Predicting travel behaviour for cycling and motorcycling using Computer Vision
• Authors: Kyriaki, Kokka, Rahul Goel, Ali Abbas, Kerry A. Nice, Luca Martial, SM Labib, Rihuan Ke, Carola Bibiane Schönlieb, James Woodcock,
• Abstract summary: This study demonstrates a novel approach using deep learning on street view images to estimate cycling and motorcycling levels across diverse cities worldwide.<n>Data on mode shares of cycling and motorcycling estimated using travel surveys or censuses.<n>Model was applied to 60 cities globally for which we didn't have recent mode share data.
• Score: 13.385410584556135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transportation influence health by shaping exposure to physical activity, air pollution and injury risk. Comparative data on cycling and motorcycling behaviours is scarce, particularly at a global scale. Street view imagery, such as Google Street View (GSV), combined with computer vision, is a valuable resource for efficiently capturing travel behaviour data. This study demonstrates a novel approach using deep learning on street view images to estimate cycling and motorcycling levels across diverse cities worldwide. We utilized data from 185 global cities. The data on mode shares of cycling and motorcycling estimated using travel surveys or censuses. We used GSV images to detect cycles and motorcycles in sampled locations, using 8000 images per city. The YOLOv4 model, fine-tuned using images from six cities, achieved a mean average precision of 89% for detecting cycles and motorcycles. A global prediction model was developed using beta regression with city-level mode shares as outcome, with log transformed explanatory variables of counts of GSV-detected images with cycles and motorcycles, while controlling for population density. We found strong correlations between GSV motorcycle counts and motorcycle mode share (0.78) and moderate correlations between GSV cycle counts and cycling mode share (0.51). Beta regression models predicted mode shares with $R^2$ values of 0.614 for cycling and 0.612 for motorcycling, achieving median absolute errors (MDAE) of 1.3% and 1.4%, respectively. Scatterplots demonstrated consistent prediction accuracy, though cities like Utrecht and Cali were outliers. The model was applied to 60 cities globally for which we didn't have recent mode share data. We provided estimates for some cities in the Middle East, Latin America and East Asia. With computer vision, GSV images capture travel modes and activity, providing insights alongside traditional data sources.

Related papers

• PAVE: An End-to-End Dataset for Production Autonomous Vehicle Evaluation [11.024538259188347]
  This dataset contains over 100 hours of naturalistic data from production autonomous-driving vehicle models in the market.<n>For each key frame, 20 Hz vehicle trajectories spanning the past 6 s and future 5 s are provided, along with detailed 2D annotations of surrounding vehicles, pedestrians, traffic lights, and traffic signs.<n>To evaluate the safety of AVs, we employ an end-to-end motion planning model that predicts vehicle trajectories with an Average Displacement Error (ADE) of 1.4 m on autonomous-driving frames.
  arXiv  Detail & Related papers  (2025-11-18T06:41:34Z)
• The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic [6.346576275272361]
  UVH-26 is the first public release by AIM@IISc of a large-scale dataset of annotated traffic-camera images from India.<n>The dataset comprises 26,646 high-resolution (1080p) images sampled from 2800 Bangalore's Safe-City CCTV cameras over a 4-week period.<n>In total, 1.8 million bounding boxes were labeled across 14 vehicle classes specific to India.
  arXiv  Detail & Related papers  (2025-11-04T13:36:03Z)
• BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation [15.126643708837712]
  BikeVAE-GNN is a novel dual-task framework augmenting a Hybrid Graph Neural Network (GNN) with Variational Autoencoder (VAE)<n>BikeVAE-GNN simultaneously performs - regression for bicycling volume estimation and classification for bicycling traffic level categorization.<n>Our experiments show that BikeVAE-GNN outperforms machine learning and baseline GNN models, achieving a mean absolute error (MAE) of 30.82 bicycles per day, accuracy of 99% and F1-score of 0.99.
  arXiv  Detail & Related papers  (2025-07-18T09:18:02Z)
• Evaluating the effects of Data Sparsity on the Link-level Bicycling Volume Estimation: A Graph Convolutional Neural Network Approach [54.84957282120537]
  We present the first study to utilize a Graph Convolutional Network (GCN) architecture to model link-level bicycling volumes.<n>We benchmark it against traditional machine learning models, such as linear regression, support vector machines, and random forest.<n>Our results show that the GCN model outperforms these traditional models in predicting Annual Average Daily Bicycle (AADB) counts.
  arXiv  Detail & Related papers  (2024-10-11T04:53:18Z)
• Pedestrian Environment Model for Automated Driving [54.16257759472116]
  We propose an environment model that includes the position of the pedestrians as well as their pose information. We extract the skeletal information with a neural network human pose estimator from the image. To obtain the 3D information of the position, we aggregate the data from consecutive frames in conjunction with the vehicle position.
  arXiv  Detail & Related papers  (2023-08-17T16:10:58Z)
• Street-View Image Generation from a Bird's-Eye View Layout [95.36869800896335]
  Bird's-Eye View (BEV) Perception has received increasing attention in recent years. Data-driven simulation for autonomous driving has been a focal point of recent research. We propose BEVGen, a conditional generative model that synthesizes realistic and spatially consistent surrounding images.
  arXiv  Detail & Related papers  (2023-01-11T18:39:34Z)
• 4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions [46.03430162297781]
  We present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset.<n>The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions.<n>We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance.
  arXiv  Detail & Related papers  (2022-12-31T13:52:36Z)
• Estimating city-wide hourly bicycle flow using a hybrid LSTM MDN [0.0]
  Efforts to increase the bicycle's mode-share involve many measures, one of them being the improvement of cycling safety. meaningful analysis of cycling safety requires accurate bicycle flow data that is generally sparse or not even available at a segment level. This paper presents a Deep Learning based approach, to estimate hourly bicycle flow in Copenhagen, conditional on weather, temporal and road conditions.
  arXiv  Detail & Related papers  (2022-04-20T17:00:29Z)
• Improving short-term bike sharing demand forecast through an irregular convolutional neural network [16.688608586485316]
  The study proposes an irregular convolutional Long-Short Term Memory model (IrConv+LSTM) to improve short-term bike sharing demand forecast. The proposed model is evaluated with a set of benchmark models in five study sites, which include one dockless bike sharing system in Singapore, and four station-based systems in Chicago, Washington, D.C., New York, and London. The model also achieves superior performance in areas with varying levels of bicycle usage and during peak periods.
  arXiv  Detail & Related papers  (2022-02-09T10:21:45Z)
• Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers [126.81938540470847]
  We propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories. In this work, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene. We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.
  arXiv  Detail & Related papers  (2021-06-22T15:40:21Z)
• One Million Scenes for Autonomous Driving: ONCE Dataset [91.94189514073354]
  We introduce the ONCE dataset for 3D object detection in the autonomous driving scenario. The data is selected from 144 driving hours, which is 20x longer than the largest 3D autonomous driving dataset available. We reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
  arXiv  Detail & Related papers  (2021-06-21T12:28:08Z)
• Assessing bikeability with street view imagery and computer vision [0.0]
  We develop an exhaustive index of bikeability composed of 34 indicators. As they outperformed non-SVI counterparts by a wide margin, SVI indicators are also found to be superior in assessing urban bikeability.
  arXiv  Detail & Related papers  (2021-05-13T14:08:58Z)
• 4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving [43.09957836757648]
  We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving.<n>Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking.
  arXiv  Detail & Related papers  (2020-09-14T12:31:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.