The ApolloScape Dataset for Autonomous Driving

Huang, Xinyu; Cheng, Xinjing; Geng, Qichuan; Cao, Binbin; Zhou, Dingfu; Wang, Peng; Lin, Yuanqing; Yang, Ruigang

doi:10.1109/cvprw.2018.00141

Cited by 457 publications

(292 citation statements)

References 11 publications

Supporting

Mentioning

272

Contrasting

Unclassified

Order By: Relevance

“…Autonomous Driving Datasets with Trajectory Data. ApolloScape [26] also uses sensor-equipped vehicles to observe driving trajectories in the wild and presents a forecasting benchmark [41] [37] show how 3D object detection accuracy can be improved by using mapping (ground height estimation) as an additional task in multi-task learning. Suraj et al [40] use dashboardmounted monocular cameras on a fleet of vehicles to build a 3D map via city-scale structure-from-motion for localization of ego-vehicles and trajectory extraction.…”

Section: Related Workmentioning

confidence: 99%

Argoverse: 3D Tracking and Forecasting With Rich Maps

Chang

Ramanan²,

Hays³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,078

788

View full text Add to dashboard Cite

Figure 1: We introduce datasets for 3D tracking and motion forecasting with rich maps for autonomous driving. Our 3D tracking dataset contains sequences of LiDAR measurements, 360 • RGB video, front-facing stereo (middle-right), and 6-dof localization. All sequences are aligned with maps containing lane center lines (magenta), driveable region (orange), and ground height. Sequences are annotated with 3D cuboid tracks (green). A wider map view is shown in the bottom-right. AbstractWe present Argoverse -two datasets designed to support autonomous vehicle machine learning tasks such as 3D tracking and motion forecasting. Argoverse was collected by a fleet of autonomous vehicles in Pittsburgh and Miami. The Argoverse 3D Tracking dataset includes 360 • images from 7 cameras with overlapping fields of view, 3D point clouds from long range LiDAR, 6-DOF pose, and 3D track annotations. Notably, it is the only modern AV dataset that provides forward-facing stereo imagery. The Argoverse Motion Forecasting dataset includes more than 300,000 5 second tracked scenarios with a particular vehicle identified for trajectory forecasting. Argoverse is the first autonomous vehicle dataset to include "HD maps" with 290 km of mapped lanes with geometric and semantic metadata. All data is released under a Creative Commons license at *Equal contribution www.argoverse.org. In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting. Our tracking and forecasting experiments represent only an initial exploration of the use of rich maps in robotic perception. We hope that Argoverse will enable the research community to explore these problems in greater depth.

show abstract

Section: Related Workmentioning

confidence: 99%

Argoverse: 3D Tracking and Forecasting With Rich Maps

Chang

Ramanan²,

Hays³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,078

788

View full text Add to dashboard Cite

show abstract

“…For example, the images are usually taken from arbitrary angles and are not annotated with navigation information or paired with other sensor data. In response to this need, the robotics community has released a number of datasets focusing on active areas of research such as autonomous driving (Cordts et al, ; Geiger, Lenz, Stiller, & Urtasun, ; X. Huang et al, ; Maddern, Pascoe, Linegar, & Newman, ; Pandey, McBride, & Eustice, ; Yu et al, ). By nature, these data are domain specific and do not necessarily translate to agricultural applications.…”

Section: Introductionmentioning

confidence: 99%

A high‐resolution, multimodal data set for agricultural robotics: A Ladybird's‐eye view of Brassica

Bender

Whelan

Sukkarieh

2019

Journal of Field Robotics

View full text Add to dashboard Cite

This article presents an agricultural data set collected by Ladybird, an autonomous field robot designed at the Australian Centre for Field Robotics. The data set contains weekly scans of cauliflower and broccoli (Brassica oleracea) covering a 10 week growth cycle from transplant to harvest. The data set includes ground truth; physical characteristics of the crop; environmental data collected by a weather station and a soil sensor network; and scans of the crop performed by Ladybird, which include stereo color, thermal and hyperspectral imagery. The layout of the farm and data collection methodology are described. A description of Ladybird's capabilities and sensors are provided. Benchmark results are provided to illustrate the contents of the data set and how it can be processed. The hyperspectral data are compiled into hypercubes and the pixels are classified into crop, weed, or soil. An object detector is applied to the color imagery to locate the crop. Our intention in releasing the data set is to facilitate robotics and machine learning research activity in agriculture. The data set can be downloaded from https://doi.org/10.25910/5c941d0c8bccb.

show abstract

“…We carry out experiments on three large stereo images datasets, i.e. KITTI [53], Cityscapes [54] and ApolloScape [18]. For the KITTI dataset, we use the Eigen split [1] for training and testing.…”

Section: Methodsmentioning

confidence: 99%

Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks

Pilzer

Lathuilière

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance. However, they require costly ground truth annotations during training. To cope with this issue, in this paper we present a novel unsupervised deep learning approach for predicting depth maps. We introduce a new network architecture, named Progressive Fusion Network (PFN), that is specifically designed for binocular stereo depth estimation. This network is based on a multi-scale refinement strategy that combines the information provided by both stereo views. In addition, we propose to stack twice this network in order to form a cycle. This cycle approach can be interpreted as a form of data-augmentation since, at training time, the network learns both from the training set images (in the forward half-cycle) but also from the synthesized images (in the backward half-cycle). The architecture is jointly trained with adversarial learning. Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction.

show abstract

The ApolloScape Dataset for Autonomous Driving

Cited by 457 publications

References 11 publications

Argoverse: 3D Tracking and Forecasting With Rich Maps

Argoverse: 3D Tracking and Forecasting With Rich Maps

A high‐resolution, multimodal data set for agricultural robotics: A Ladybird's‐eye view of Brassica

Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks

Contact Info

Product

Resources

About