Detecting Unsigned Physical Road Incidents from Driver-View Images

• URL: http://arxiv.org/abs/2004.11824v1
• Date: Fri, 24 Apr 2020 16:02:17 GMT
• Title: Detecting Unsigned Physical Road Incidents from Driver-View Images
• Authors: Alex Levering, Martin Tomko, Devis Tuia, Kourosh Khoshelham
• Abstract summary: A critical need is to detect and communicate disruptive incidents early and effectively. We propose a system based on an off-the-shelf deep neural network architecture. We develop a taxonomy for unsigned physical incidents to provide a means of organizing and grouping related incidents.
• Score: 3.840106920708639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety on roads is of uttermost importance, especially in the context of autonomous vehicles. A critical need is to detect and communicate disruptive incidents early and effectively. In this paper we propose a system based on an off-the-shelf deep neural network architecture that is able to detect and recognize types of unsigned (non-placarded, such as traffic signs), physical (visible in images) road incidents. We develop a taxonomy for unsigned physical incidents to provide a means of organizing and grouping related incidents. After selecting eight target types of incidents, we collect a dataset of twelve thousand images gathered from publicly-available web sources. We subsequently fine-tune a convolutional neural network to recognize the eight types of road incidents. The proposed model is able to recognize incidents with a high level of accuracy (higher than 90%). We further show that while our system generalizes well across spatial context by training a classifier on geostratified data in the United Kingdom (with an accuracy of over 90%), the translation to visually less similar environments requires spatially distributed data collection. Note: this is a pre-print version of work accepted in IEEE Transactions on Intelligent Vehicles (T-IV;in press). The paper is currently in production, and the DOI link will be added soon.

Related papers

• IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing [0.6787248655856052]
  IncidentNet is a novel approach for classifying, localizing, and estimating the severity of traffic incidents. Our model works on microscopic traffic data that can be collected using cameras installed at traffic intersections.
  arXiv  Detail & Related papers  (2024-08-02T04:09:15Z)
• Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis [21.02297148118655]
  This paper constructs a large-scale dataset of traffic accident records from official reports of various states in the US. Using this new dataset, we evaluate existing deep-learning methods for predicting the occurrence of accidents on road networks. Our main finding is that graph neural networks such as GraphSAGE can accurately predict the number of accidents on roads with less than 22% mean absolute error.
  arXiv  Detail & Related papers  (2023-10-31T21:43:10Z)
• IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes [79.18349050238413]
  Preparation and training of deploy-able deep learning architectures require the models to be suited to different traffic scenarios. An unstructured and complex driving layout found in several developing countries such as India poses a challenge to these models. We build a new dataset, IDD-3D, which consists of multi-modal data from multiple cameras and LiDAR sensors with 12k annotated driving LiDAR frames.
  arXiv  Detail & Related papers  (2022-10-23T23:03:17Z)
• Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification [168.67190934250868]
  Federated learning empowered connected autonomous vehicle (FLCAV) has been proposed. FLCAV preserves privacy while reducing communication and annotation costs. It is challenging to determine the network resources and road sensor poses for multi-stage training.
  arXiv  Detail & Related papers  (2022-06-03T23:55:45Z)
• Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving [5.037913689432052]
  We propose a systematic study on simple Copy-Paste data augmentation for rare object detection in autonomous driving. Specifically, local adaptive instance-level image transformation is introduced to generate realistic rare object masks. We build a new dataset named NM10k consisting 10k training images, 4k validation images and the corresponding labels.
  arXiv  Detail & Related papers  (2022-05-01T01:45:00Z)
• Intelligent Railway Foreign Object Detection: A Semi-supervised Convolutional Autoencoder Based Method [7.557470133155959]
  We develop a semi-supervised convolutional autoencoder based framework that only requires railway track images without prior knowledge on the foreign objects in the training process. The proposed framework is useful for data analytics via the train Internet-of-Things (IoT) systems.
  arXiv  Detail & Related papers  (2021-08-05T07:32:23Z)
• SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving [94.11868795445798]
  We release a Large-Scale Object Detection benchmark for Autonomous driving, named as SODA10M, containing 10 million unlabeled images and 20K images labeled with 6 representative object categories. To improve diversity, the images are collected every ten seconds per frame within 32 different cities under different weather conditions, periods and location scenes. We provide extensive experiments and deep analyses of existing supervised state-of-the-art detection models, popular self-supervised and semi-supervised approaches, and some insights about how to develop future models.
  arXiv  Detail & Related papers  (2021-06-21T13:55:57Z)
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [77.60050239225086]
  We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images. Our approach is fully automatic without any human interaction. We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
  arXiv  Detail & Related papers  (2020-12-15T03:03:38Z)
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles [103.87351701138554]
  In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. We introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. We show competitive detection and attribute recognition results, as well as a more stable MTL training.
  arXiv  Detail & Related papers  (2020-12-04T15:10:12Z)
• BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments [54.22535063244038]
  We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.
  arXiv  Detail & Related papers  (2020-09-22T08:25:44Z)
• "Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features [5.634825161148484]
  We show how the intrinsic feature maps of an object detection CNN can be used to identify vehicles from a dash-cam feed. A deep neural detection network trained to distinguish between different classes can be successfully used to identify different instances belonging to the same class.
  arXiv  Detail & Related papers  (2020-02-29T13:57:46Z)

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.