All-Day Visual Place Recognition : Benchmark Dataset and Baseline

This paper introduces all-day dataset captured from KAIST campus for use in mobile robotics, autonomous driving, and recognition researches. Totally, we captured 42 km sequences at 15∼100Hz using multiple sensor modalities such as fully aligned visible and thermal devices, high resolution stereo visible cameras, and a high accuracy GPS/IMU inertial navigation system. Despites of a particular scenario, we provide the first aligned visible/thermal all-day dataset, including various illumination conditions: day, night, sunset, and sunrise. With this dataset, we introduce multi-spectral loop-detector as a baseline. We will open all calibrated and synchronized datasets1, and hope to make a various state of the art computer vision and robotics algorithms.

[1]  Volker Hilsenstein.  Surface Reconstruction of Water Waves using Thermographic Stereo Imaging , 2005 .

[2]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Terry Caelli,et al.  Robust thermal camera calibration and 3D mapping of object surface temperatures , 2006, SPIE Defense + Commercial Sensing.

[4]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Paul Newman,et al.  FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance , 2008, Int. J. Robotics Res..

[6]  Winston Churchill,et al.  The New College Vision and Laser Data Set , 2009, Int. J. Robotics Res..

[7]  Francisco Angel Moreno,et al.  A collection of outdoor robotic datasets with centimeter-accuracy ground truth , 2009, Auton. Robots.

[8]  Gordon Wyeth,et al.  FAB-MAP + RatSLAM: Appearance-based SLAM for multiple times of day , 2010, 2010 IEEE International Conference on Robotics and Automation.

[9]  Wolfram Burgard,et al.  Towards a benchmark for RGB-D SLAM evaluation , 2011, RSS 2011.

[10]  Ryan M. Eustice,et al.  Ford Campus vision and lidar data set , 2011, Int. J. Robotics Res..

[11]  Gordon Wyeth,et al.  SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights , 2012, 2012 IEEE International Conference on Robotics and Automation.

[12]  Qiang Wu,et al.  On splitting dataset: Boosting Locally Adaptive Regression Kernels for car localization , 2012, 2012 12th International Conference on Control Automation Robotics & Vision (ICARCV).

[13]  Dorian Gálvez-López,et al.  Bags of Binary Words for Fast Place Recognition in Image Sequences , 2012, IEEE Transactions on Robotics.

[14]  William P. Maddern,et al.  Towards robust night and day place recognition using visible and thermal imaging , 2012 .

[15]  Sridha Sridharan,et al.  A Mask-Based Approach for the Geometric Calibration of Thermal-Infrared Cameras , 2012, IEEE Transactions on Instrumentation and Measurement.

[16]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[17]  Henning Lategahn,et al.  How to learn an illumination robust image feature for place recognition , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[18]  Peyman Moghadam,et al.  Combining motion and appearance for scene segmentation , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Nabil Aouf,et al.  Multispectral Stereo Odometry , 2015, IEEE Transactions on Intelligent Transportation Systems.

[20]  Namil Kim,et al.  Multispectral pedestrian detection: Benchmark dataset and baseline , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).