We present a challenging new dataset for autonomous driving: the Oxford RobotCar Dataset. Over the period of May 2014 to December 2015 we traversed a route through central Oxford twice a week on average using the Oxford RobotCar platform, an autonomous Nissan LEAF. This resulted in over 1000 km of recorded driving with almost 20 million images collected from 6 cameras mounted to the vehicle, along with LIDAR, GPS and INS ground truth. Data was collected in all weather conditions, including heavy rain, night, direct sunlight and snow. Road and building works over the period of a year significantly changed sections of the route from the beginning to the end of data collection. By frequently traversing the same route over the period of a year we enable research investigating long-term localization and mapping for autonomous vehicles in real-world, dynamic urban environments. The full dataset is available for download at: http://robotcar-dataset.robots.ox.ac.uk
AgarwalSMierleK and Others (2012) Ceres solver. Available at: http://ceres-solver.org (accessed 1 July 2016).
2.
BenensonROmranMHosangJSchieleB (2014) Ten years of pedestrian detection, what have we learned? In: AgapitoLBronsteinMRotherC (eds) European conference on computer vision (ECCV), Zurich, Switzerland, September 2014, pp.613–627. Switzerland: Springer International Publishing.
3.
Blanco-ClaracoJLMoreno-DueñasFÁGonzález-JiménezJ (2014) The Málaga urban dataset: High-rate stereo and LiDAR in a realistic urban scenario. The International Journal of Robotics Research33(2): 207–214.
4.
BrostowGJFauqueurJCipollaR (2009) Semantic object classes in video: A high-definition ground truth database. Pattern Recognition Letters30(2): 88–97.
5.
ChurchillW (2012) Experience based navigation: Theory, practice and implementation. PhD Thesis, University of Oxford, UK.
6.
CordtsMOmranMRamosS. (2016) The Cityscapes dataset for semantic urban scene understanding. In: AgapitoLBergTKoseckaJ. (eds) Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Zurich, Switzerland, September 2014. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
7.
DollárPWojekCSchieleB. (2009) Pedestrian detection: A benchmark. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, June 2016, pp.304–311. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
8.
EngelJSchöpsTCremersD (2014) LSD-SLAM: Large-scale direct monocular SLAM. In: TuytelaarsTSchieleBPajdlaT. (eds) European conference on computer vision, (ECCV), Zurich, Switzerland, September 2014. pp.834–849. Switzerland: Springer International Publishing.
9.
GeigerALenzPStillerC. (2013) Vision meets robotics: The KITTI dataset. International Journal of Robotics Research32(11) 1231–1237.
10.
GeigerARoserMUrtasunR (2010) Efficient large-scale stereo matching. In: KimmelRKletteRSugimotoA (eds) Asian conference on computer vision (ACCV), Queenstown, New Zealand, November 2010. pp.25–38. Springer: Springer-Verlag Berlin Heidelberg.
11.
GeigerAZieglerJStillerC (2011) Stereoscan: Dense 3D reconstruction in real-time. In: Intelligent vehicles symposium (IV), 2011 IEEE, Baden-Baden, Germany, June 2011. pp.963–968. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
12.
HarrisonANewmanP (2011) TICSync: Knowing when things happened. In: LaValleSAraiHBrockO. (eds) RProceedings of the IEEE conference on robotics and automation (ICRA), Shanghai, China, May 2011. pp.356–363. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
13.
HirschmullerH (2005) Accurate and efficient stereo processing by semi-global matching and mutual information. In: SchmidCSoattoSTomasiC (eds) Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), San Diego, CA, 2005volume 2, pp.807–814. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
14.
KassirAPeynotT (2010) Reliable automatic camera-laser calibration. In: WyethGUpcroftB (eds) Proceedings of the 2010 Australasian conference on robotics & automation, Brisbane, Australia, December 2010. Australia: Australian Robotics and Automation Association.
15.
LinegarCChurchillWNewmanP (2016) Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera. In: BicchiADe LucaA (eds) Proceedings of the IEEE international conference on robotics and automation (ICRA), Stockholm, Sweden, May 2016. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
16.
LongJShelhamerEDarrellT (2015) Fully convolutional networks for semantic segmentation. In: GraumanKLearned-MillerETorralbaA. (eds) Proceedings of the IEEE conference on computer vision and pattern recognition, (CVPR), Boston, MA, July 2015. pp.3431–3440. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
17.
McManusCUpcroftBNewmanP (2015) Learning place-dependant features for long-term vision-based localisation. Autonomous Robots39: 363.
18.
MaddernWHarrisonANewmanP (2012) Lost in translation (and rotation): Fast extrinsic calibration for 2D and 3D LIDARs. In: OhPRoumeliotisSTadakoroS. (eds) Proceedings of the IEEE conference on robotics and automation (ICRA), St Paul, MN, May 2012. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
19.
MaddernWPascoeGNewmanP (2015) Leveraging experience for large-scale LIDAR localisation in changing cities. In: AntonelliGBurschkaDChenI. (eds) Proceedings of the IEEE international conference on robotics and automation (ICRA), Seattle, WA, May 2015. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
20.
MaddernWStewartAMcManusC. (2014) Illumination invariant imaging: Applications in robust vision-based localisation, mapping and classification for autonomous vehicles. In: SunderhaufNCorkePMilfordM (eds) Proceedings of the IEEE conference on robotics and automation (ICRA): Workshop on visual place recognition in changing environments, Hong Kong, May 2014, vol. 2, p.3. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
21.
NistérDNaroditskyOBergenJ (2006) Visual odometry for ground vehicle applications. Journal of Field Robotics23(1): 3–20.
22.
PandeyGMcBrideJREusticeRM (2011) Ford campus vision and LIDAR data set. The International Journal of Robotics Research30(13): 1543–1552.
23.
PascoeGMaddernWNewmanP (2015) Direct visual localisation and calibration for road vehicles in changing city environments. In: SalzmannMPeterssonLAlvarezJ (eds) Proceedings of the IEEE international conference on computer vision: Workshop on computer vision for road scene understanding and autonomous driving, Santiago, Chile, December 2015. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
24.
PfeifferDGehrigSSchneiderN (2013) Exploiting the power of stereo confidences. In: HebertMFreemanBSzeliskiR. (eds) Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Portland, OR, June 2013. pp.297–304. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
25.
PosnerICumminsMNewmanP (2008) Fast probabilistic labeling of city maps. In: TrinkleJ (ed) Proceedings of robotics: Science and systems IV, Zurich, Switzerland, June 2008. Robotics: Science and Systems Foundation, Berlin, Germany.
26.
ScaramuzzaDMartinelliASiegwartR (2006) A toolbox for easily calibrating omnidirectional cameras. In: XiNChiaveriniSKnollA. (eds) Proceedings of the IEEE/RSJ international conference on intelligent robots and systems (IROS), Beijing, China, October 2006. pp.5695–5701. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
27.
SchönbergerJLFrahmJM (2016) Structure-from-motion revisited. In: AgapitoLBergTKoseckaJ. (eds) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June 2016. New York, NY: Institute of Electrical and Electronics Engineers (IEEE).
28.
TipaldiGDMeyer-DeliusDBurgardW (2013) Lifelong localization in changing environments. The International Journal of Robotics Research32(14): 1662–1678.
29.
ViolaPJonesMJSnowD (2005) Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision63(2): 153–161.
