CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis

• URL: http://arxiv.org/abs/2409.19942v2
• Date: Wed, 30 Oct 2024 04:26:52 GMT
• Title: CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis
• Authors: Nishq Poorav Desai, Ali Etemad, Michael Greenspan,
• Abstract summary: CycleCrash is a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations. This dataset enables 9 different cyclist collision prediction and classification tasks focusing on potentially hazardous conditions for cyclists. We propose VidNeXt, a novel method that leverages a ConvNeXt spatial encoder and a non-stationary transformer to capture the temporal dynamics of videos for the tasks defined in our dataset.
• Score: 21.584020544141797
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-driving research often underrepresents cyclist collisions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations, from collisions to safe interactions. This dataset enables 9 different cyclist collision prediction and classification tasks focusing on potentially hazardous conditions for cyclists and is annotated with collision-related, cyclist-related, and scene-related labels. Next, we propose VidNeXt, a novel method that leverages a ConvNeXt spatial encoder and a non-stationary transformer to capture the temporal dynamics of videos for the tasks defined in our dataset. To demonstrate the effectiveness of our method and create additional baselines on CycleCrash, we apply and compare 7 models along with a detailed ablation. We release the dataset and code at https://github.com/DeSinister/CycleCrash/ .

Related papers

• Sparse Sampling is All You Need for Fast Wrong-way Cycling Detection in CCTV Videos [36.1376919510996]
  This paper formulates a problem of detecting wrong-way cycling ratios in CCTV videos. We propose a sparse sampling method called WWC-Predictor to efficiently solve this problem. Our approach achieves an average error rate of a mere 1.475% while taking only 19.12% GPU time.
  arXiv  Detail & Related papers  (2024-05-12T14:16:05Z)
• 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)
• A Benchmark for Cycling Close Pass Near Miss Event Detection from Video Streams [35.17510169229505]
  We introduce a novel benchmark, called Cyc-CP, towards cycling close pass near miss event detection from video streams. We propose two benchmark models based on deep learning techniques for these two problems. Our models can achieve 88.13% and 84.60% accuracy on the real-world dataset.
  arXiv  Detail & Related papers  (2023-04-24T07:30:01Z)
• Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification [59.80753896200009]
  We propose a novel task of damaged object re-identification, which aims at distinguishing changes in visual appearance due to deformations or missing parts from subtle intra-class variations. We leverage the power of computer-generated imagery to create, in a semi-automatic fashion, high-quality synthetic images of the same bike before and after a damage occurs. As a baseline for this task, we propose TransReI3D, a multi-task, transformer-based deep network unifying damage detection.
  arXiv  Detail & Related papers  (2023-04-16T20:23:58Z)
• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving [76.29141888408265]
  We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:37:00Z)
• Monocular Cyclist Detection with Convolutional Neural Networks [0.0]
  This study aims to reduce the number of vehicle-cyclist collisions, which are often caused by poor driver attention to blind spots. We designed a state-of-the-art real-time monocular cyclist detection that can detect cyclists with object detection convolutional neural networks. We conclude that this cyclist detection device can accurately and quickly detect cyclists and has the potential to improve cyclist safety significantly.
  arXiv  Detail & Related papers  (2023-01-16T13:54:13Z)
• COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos [62.34712951567793]
  The ability to forecast human-environment collisions from egocentric observations is vital to enable collision avoidance in applications such as VR, AR, and wearable assistive robotics. We introduce the challenging problem of predicting collisions in diverse environments from multi-view egocentric videos captured from body-mounted cameras. We propose a transformer-based model called COPILOT to perform collision prediction and localization simultaneously.
  arXiv  Detail & Related papers  (2022-10-04T17:49:23Z)
• CycleSense: Detecting Near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors [3.5127092215732176]
  In cities worldwide, cars cause health and traffic problems which could be partly mitigated through an increased modal share of bicycles. Many people, however, avoid cycling due to a lack of perceived safety. For city planners, addressing this is hard as they lack insights into where cyclists feel safe and where they do not.
  arXiv  Detail & Related papers  (2022-04-21T21:43:23Z)
• 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)
• Collision Replay: What Does Bumping Into Things Tell You About Scene Geometry? [87.63134188675717]
  We use examples of collisions to provide supervision for observations at a past frame. We use collision replay to train convolutional neural networks to predict a distribution over collision time from new images. We analyze this approach with an agent that has noisy actuation in a photorealistic simulator.
  arXiv  Detail & Related papers  (2021-05-03T17:59:46Z)
• DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems [9.17424462858218]
  We use dashcam crash videos uploaded to the internet to extract valuable collision data. We tackle the problem of extracting 3D vehicle trajectories from videos recorded by an unknown and uncalibrated monocular camera source.
  arXiv  Detail & Related papers  (2020-03-26T07:03:45Z)

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.