WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving

@article{Yogamani2019WoodScapeAM,
  title={WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving},
  author={Senthil Kumar Yogamani and Ciar{\'a}n Hughes and Jonathan Horgan and Ganesh Sistu and Padraig Varley and Derek O'Dea and Michal Uři{\vc}{\'a}ř and Stefan Milz and Martin Simon and Karl Amende and Christian Witt and Hazem Rashed and Sumanth Chennupati and Sanjaya Nayak and Saquib Mansoor and Xavier Perroton and Patrick P{\'e}rez},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={9307-9317}
}
  • S. Yogamani, C. Hughes, +14 authors P. Pérez
  • Published 2019
  • Computer Science, Mathematics
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fisheye automotive dataset, WoodScape, named after Robert Wood who invented the fisheye camera in 1906. WoodScape comprises of four surround view cameras and nine tasks including… Expand
OmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving
TLDR
This work proposes a novel camera geometry based adaptation mechanism to encode the fisheye distortion model both at training and inference and obtains the state-of-the-art results on KITTI for depth estimation and pose estimation tasks and competitive performance on the other tasks. Expand
FisheyeYOLO: Object Detection on Fisheye Cameras for Autonomous Driving
In this paper, we tackle Object Detection in fisheye images and study different object representations. The standard bounding box fails in fisheye cameras due to the strong radial distortion,Expand
Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
TLDR
This paper proposes the concept of Multidimensional Vector to include the utilizable information generated in different dimensions and stages, instead of the descriptive approach for the bird’s eye view (BEV) or a cube of eight points, by breaking down the 3D object detection task into some sub-tasks. Expand
Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems
TLDR
It is proved that tuning an optimal support only requires a limited amount of labeled fisheye images, as a small number of training samples is sufficient to significantly improve an existing model's performance on wide-angle images, and that finetuning the weights of the network is not necessary to achieve high performance once the deformable components are learned. Expand
RotInvMTL: Rotation Invariant MultiNet on Fisheye Images for Autonomous Driving Applications
TLDR
This paper proposes a rotation invariant object detection decoder that adapts to fisheye distortion and shows that it outperforms YOLOv2 by 9% mAP and is an efficient network that performs well for autonomous driving applications. Expand
Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline
TLDR
This work designs a novel curved bounding box model that has optimal properties for fisheye distortion models and designs a curvature adaptive perimeter sampling method for obtaining polygon vertices, improving relative mAP score by 4.9% compared to uniform sampling. Expand
SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras
TLDR
Novel camera-geometry adaptive multiscale convolutions which utilize the camera parameters as a conditional input are presented, enabling the model to generalize to previously unseen fisheye cameras. Expand
SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images
TLDR
A novel framework for adapting a ROI-based 6D object pose estimation method to work on full fisheye images is presented, which incorporates the gnomic projection of regions of interest from an intermediate spherical image representation to correct for the f isheye distortions. Expand
Woodscape Fisheye Semantic Segmentation for Autonomous Driving - CVPR 2021 OmniCV Workshop Challenge
TLDR
A summary of the WoodScape fisheye semantic segmentation challenge for autonomous driving, which attracted the participation of 71 global teams and a total of 395 submissions, and the methods of winning algorithms is summarized. Expand
FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving
TLDR
This work proposes a CNN architecture for moving object detection using fisheye images that were captured in autonomous driving environment and designs a lightweight encoder sharing weights across sequential images to target embedded deployment. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 78 REFERENCES
CNN-based Fisheye Image Real-Time Semantic Segmentation
TLDR
This paper presents a real-time CNN-based semantic segmentation solution for urban traffic images using fisheye cameras and adapts the Efficient Residual Factorized CNN (ERFNet) architecture to handle distorted fish-eye images. Expand
CNN based semantic segmentation for urban traffic scenes using fisheye camera
TLDR
A CNN-based semantic segmentation solution using fisheye camera which covers a large field of view and zoom augmentation, a novel data augmentation policy specially designed for f isheye image, is proposed to improve the net's generalization performance. Expand
nuScenes: A Multimodal Dataset for Autonomous Driving
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as objectExpand
Are we ready for autonomous driving? The KITTI vision benchmark suite
TLDR
The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Expand
Vision meets robotics: The KITTI dataset
TLDR
A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system. Expand
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
TLDR
The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding. Expand
The ApolloScape Dataset for Autonomous Driving
TLDR
A large-scale open dataset that consists of RGB videos and corresponding dense 3D point clouds that can deeply benefit various autonomous driving related applications that include but not limited to 2D/3D scene understanding, localization, transfer learning, and driving simulation is presented. Expand
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
TLDR
This paper generates a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations, and conducts experiments with DCNNs that show how the inclusion of SYnTHIA in the training stage significantly improves performance on the semantic segmentation task. Expand
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
TLDR
This work presents SphereNet, a novel deep learning framework which encodes invariance against such distortions explicitly into convolutional neural networks, and enables the transfer of existing perspective convolutionAL neural network models to the omnidirectional case. Expand
Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning
TLDR
How deep learning can be used to replace parts of the classical Visual SLAM pipeline and the opportunities of using Deep Learning to improve upon state-of-the-art classical methods are discussed. Expand
...
1
2
3
4
5
...