WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving

Senthil, Yogamani; Witt, Christian; Rashed, Hazem; Nayak, Sanjaya; Mansoor, Saquib; Varley, Padraig; Perrotton, Xavier; O'Dea, Derek; Patrick, Perez; Hughes, Ciáran; Horgan, Jonathan; Sistu, Ganesh; Sumanth, Chennupati; Uřičář, Michal; Milz, Stefan; Simón, Martín; Amende, Karl

doi:10.48550/arxiv.1905.01489

Cited by 10 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works simply project annotated perspective images to the distorted omni-directional or fisheye domain, as a simple way to generate a proxy dataset. Some recent work seeks to address this lack of annotated fisheye datasets [35], [36]. However, no such annotated dataset exists for fisheye images in the underwater domain.…”

Section: Related Workmentioning

confidence: 99%

SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images

Billings¹,

Johnson-Roberson²

2020

Preprint

View full text Add to dashboard Cite

There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the application space for monocular-based methods is expansive, there has been little work on applying these methods with fisheye imaging systems. Also, little exists in the way of annotated fisheye image datasets on which these methods can be developed and tested. The research landscape is even more sparse for object detection methods applied in the underwater domain, fisheye image based or otherwise. In this work, we present a novel framework for adapting a ROI-based 6D object pose estimation method to work on full fisheye images. The method incorporates the gnomic projection of regions of interest from an intermediate spherical image representation to correct for the fisheye distortions. Further, we contribute a fisheye image dataset, called UWHandles, collected in natural underwater environments, with 6D object pose and 2D bounding box annotations.

show abstract

Section: Related Workmentioning

confidence: 99%

SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images

Billings¹,

Johnson-Roberson²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The average percentage of moving pixels in a frame is 0.54%, and the average percentage of static pixels is 99.46%, including background and static objects. The dataset will be released as part of WoodScape project [18].…”

Section: Semi-automated Annotation Proceduresmentioning

confidence: 99%

FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving

Yahiaoui¹,

Rashed²,

Mariotti³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Moving Object Detection (MOD) is an important task for achieving robust autonomous driving. An autonomous vehicle has to estimate collision risk with other interacting objects in the environment and calculate an optional trajectory. Collision risk is typically higher for moving objects than static ones due to the need to estimate the future states and poses of the objects for decision making. This is particularly important for near-range objects around the vehicle which are typically detected by a fisheye surround-view system that captures a 360 • view of the scene. In this work, we propose a CNN architecture for moving object detection using fisheye images that were captured in autonomous driving environment. As motion geometry is highly nonlinear and unique for fisheye cameras, we will make an improved version of the current dataset public to encourage further research. To target embedded deployment, we design a lightweight encoder sharing weights across sequential images. The proposed network runs at 15 fps on a 1 teraflops automotive embedded system at accuracy of 40% IoU and 69.5% mIoU.

show abstract

“…These networks rely only on explicit motion information from optical flow which makes them sensitive to the optical flow estimation errors. Fisheye MOD has been studied in [12] using publicly available fisheye dataset [5] proving the importance temporally sequential images in MOD.…”

Section: Related Workmentioning

confidence: 99%

“…Object detection and semantic segmentation has become a mature algorithm for automated driving [4] but motion segmentation is relatively an unexplored problem. Recent automated driving datasets [5] include moving object detection task.…”

Section: Introductionmentioning

confidence: 99%

RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous Driving

Ramzy,

Rashed,

Sallab

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Moving Object Detection (MOD) is a critical task for autonomous vehicles as moving objects represent higher collision risk than static ones. The trajectory of the ego-vehicle is planned based on the future states of detected moving objects. It is quite challenging as the ego-motion has to be modelled and compensated to be able to understand the motion of the surrounding objects. In this work, we propose a real-time end-to-end CNN architecture for MOD utilizing spatio-temporal context to improve robustness. We construct a novel time-aware architecture exploiting temporal motion information embedded within sequential images in addition to explicit motion maps using optical flow images. We demonstrate the impact of our algorithm on KITTI dataset where we obtain an improvement of 8% relative to the baselines. We compare our algorithm with state-of-the-art methods and achieve competitive results on KITTI-Motion dataset in terms of accuracy at three times better run-time. The proposed algorithm runs at 23 fps on a standard desktop GPU targeting deployment on embedded platforms.

show abstract

WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving

Cited by 10 publications

References 0 publications

SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images

SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images

FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving

RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous Driving

Contact Info

Product

Resources

About