KAIST Multi-Spectral Day/Night Data Set for Autonomous and Assisted Driving
The DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index.
Abstract
We introduce the KAIST multi-spectral data set, which covers a great range of drivable regions, from urban to residential, for autonomous systems. Our data set provides the different perspectives of the world captured in coarse time slots (day and night), in addition to fine time slots (sunrise, morning, afternoon, sunset, night, and dawn). For all-day perception of autonomous systems, we propose the use of a different spectral sensor, i.e., a thermal imaging camera. Toward this goal, we develop a multi-sensor platform, which supports the use of a co-aligned RGB/Thermal camera, RGB stereo, 3-D LiDAR, and inertial sensors (GPS/IMU) and a related calibration technique. We design a wide range of visual perception tasks including the object detection, drivable region detection, localization, image enhancement, depth estimation, and colorization using a single/multi-spectral approach. In this paper, we provide a description of our benchmark with the recording platform, data format, development toolkits, and lessons about the progress of capturing data sets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recent research showed that drivers exhibit low cognitive load when monitoring automated driving compared to doing a secondary task [288].”
From A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2020) · cites this paper as [288]
In the citing paper
“The KAIST multispectral dataset [17] is a multimodal dataset that consists of RGB and thermal camera, RGB stereo, 3D lidar and GPS/IMU.”
From nuScenes: A Multimodal Dataset for Autonomous Driving (2020) · cites this paper as [17]
In the citing paper
“To encourage robotics research, we also provide the raw CAN bus data (e.g. velocities, accelerations, torque, steering angles, wheel speeds) similar to [65].”
From nuScenes: A Multimodal Dataset for Autonomous Driving (2020) · cites this paper as [65]
In the citing paper
“It provides nighttime data, but the size of the dataset is limited and annotations are in 2D.”
From nuScenes: A Multimodal Dataset for Autonomous Driving (2020) · cites this paper as [17]
Citations
Cites
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 5×
“However, we expect that our dataset can be extended to pixel and instance-level segmentation in a similar manner to Cityscapes, which uses RGB stereo pairs.”
BackgroundMethodInfluentialVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 8×
“VirtualKITTI VirtualKITTI [3] is large-scale synthetic dataset which provides photo-realistic virtual worlds with accurate ground truth outcomes for object detection, tracking, scene and instance segmentation, depth, and optical flows.”
BackgroundMethodInfluentialStereo Processing by Semiglobal Matching and Mutual Information
Hirschmuller, H. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1166 · Cited by 4,195
Zhang, R., Isola, P., & Efros, A. A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,178 · cited 1×
“Recently, deep-learning-based techniques have showed high performance in the RGB domain [28], [29] and in the multispectral domain [30]–[32].”
BackgroundEdge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656
1 year, 1000 km: The Oxford RobotCar dataset
Maddern, W., Pascoe, G., Linegar, C., & Newman, P. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364916679498 · Cited by 1,632
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
Gupta, S., Girshick, R., Arbeláez, P., & Malik, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_23 · Cited by 1,528
Pedestrian detection: A benchmark
Dollar, P., Wojek, C., Schiele, B., & Perona, P. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206631 · Cited by 1,313 · cited 1×
“7) for the process described above was created by modifying and supplementing a toolbox [8] distributed by Piotr.”
MethodMultispectral pedestrian detection: Benchmark dataset and baseline
Hwang, S., Park, J., Kim, N., Choi, Y., & Kweon, I. S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298706 · Cited by 1,249 · cited 8×
“3) Multi-Spectral Pedestrian Dataset: Multi-spectral Pedestrian Dataset [13] is the first large-scale multi-spectral dataset for pedestrian detection in day and night.”
BackgroundMethodInfluentialSelf-citationVirtualWorlds as Proxy for Multi-object Tracking Analysis
Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.470 · Cited by 1,079 · cited 2×
“1) Multi-Modal Stereo Dataset (CVC-15): CVC-15 [35] [36] is stereo dataset which attempts to be a solution to the locating of correspondences between multi-spectral sensors.”
BackgroundStereo Matching by Training a Convolutional Neural Network to Compare Image Patches
Žbontar, J., & LeCun, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.05970 · Cited by 931 · cited 3×
“In other words, we used the RGB patch-matching-based stereo method [9] combined with 3D point-based refinement.”
MethodInfluentialIizuka, S., Simo-Serra, E., & Ishikawa, H. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925974 · Cited by 814
Automatic camera and range sensor calibration using a single shot
Geiger, A., Moosmann, F., Car, O., & Schuster, B. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224570 · Cited by 647 · cited 1×
“[14] used multiple chess boards or a triaxial calibration target to find the geometric relationship between heterogeneous sensors.”
MethodMultispectral Deep Neural Networks for Pedestrian Detection
Liu, J., Zhang, S., Wang, S., & Metaxas, D. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.73 · Cited by 543
Unsupervised Image-to-Image Translation Networks
Liu, M.-Y., Breuel, T. M., & Kautz, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00848 · Cited by 477 · cited 1×
“Recently, deep-learning-based techniques have showed high performance in the RGB domain [28], [29] and in the multispectral domain [30]–[32].”
BackgroundJoint Depth and Color Camera Calibration with Distortion Correction
Herrera C., D., Kannala, J., & Heikkila, J. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.125 · Cited by 453 · cited 2×
“(b) Herrera and Heikkila [15].”
BackgroundWang, Q., Gao, J., & Yuan, Y. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2749964 · Cited by 243 · cited 1×
“in various conditions ( [18]–[20]).”
TorontoCity: Seeing the World with a Million Eyes
Wang, S., Bai, M., Mattyus, G., Chu, H., Luo, W., Yang, B., Liang, J., Cheverie, J., Fidler, S., & Urtasun, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.327 · Cited by 186 · cited 1×
“TorontoCity TorontoCity dataset [34] provides different perspectives of the world captured from airplanes, drones, as well as cars driving around a city.”
BackgroundFast Extrinsic Calibration of a Laser Rangefinder to a Camera
Unnikrishnan, R., & Hebert, M. (2018) · Figshare · doi:10.1184/r1/6554870 · Cited by 184
Multispectral Image Feature Points
Aguilera, C., Barrera, F., Lumbreras, F., Sappa, A. D., & Toledo, R. (2012) · Sensors · doi:10.3390/s120912661 · Cited by 168 · cited 1×
“1) Multi-Modal Stereo Dataset (CVC-15): CVC-15 [35] [36] is stereo dataset which attempts to be a solution to the locating of correspondences between multi-spectral sensors.”
BackgroundThermal Image Enhancement using Convolutional Neural Network
Choi, Y., Kim, N., Hwang, S., & Kweon, I. S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759059 · Cited by 166
Self-citationTorabi, A., Massé, G., & Bilodeau, G.-A. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.10.006 · Cited by 161 · cited 1×
“4, and they have been used as night vision sensors in many academic and industrial applications [5]–[7].”
MethodInfrared Colorization Using Deep Convolutional Neural Networks
Limmer, M., & Lensch, H. P. A. (2016) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2016.0019 · Cited by 158
A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling
Wang, Q., Gao, J., & Yuan, Y. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2726546 · Cited by 157 · cited 1×
“in various conditions ( [18]–[20]).”
Large-Margin Multi-Modal Deep Learning for RGB-D Object Recognition
Wang, A., Lu, J., Cai, J., Cham, T.-J., & Wang, G. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2476655 · Cited by 153 · cited 1×
“in the challenging scenarios to RGB images ( [13], [21]–[23]).”
BackgroundA Mask-Based Approach for the Geometric Calibration of Thermal-Infrared Cameras
Vidas, S., Lakemond, R., Denman, S., Fookes, C., Sridharan, S., & Wark, T. (2012) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2012.2182851 · Cited by 144 · cited 1×
“(a) Chessboard [10].”
Human Activity Recognition in Thermal Infrared Imagery
Han, J., & Bhanu, B. (2006) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvpr.2005.469 · Cited by 131
Mouats, T., Aouf, N., Sappa, A. D., Aguilera, C., & Toledo, R. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2014.2354731 · Cited by 96 · cited 1×
“[11] proposed a handmade grid-based pattern board which is punched onto a box board to allow heat to penetrate, as shown in Fig.”
BackgroundCross-modal adaptation for RGB-D detection
Hoffman, J., Gupta, S., Leong, J., Guadarrama, S., & Darrell, T. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487708 · Cited by 81 · cited 1×
“in the challenging scenarios to RGB images ( [13], [21]–[23]).”
BackgroundTime-of-Flight Sensor Calibration for a Color and Depth Camera Pair
Jung, J., Lee, J., Jeong, Y., & Kweon, I. S. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2363827 · Cited by 69 · cited 1×
“[12] was the first to propose pattern which pierces circular holes onto a metal board (Fig.”
BackgroundSelf-citationCATS: A Color and Thermal Stereo Benchmark
Treible, W., Saponaro, P. J., Sorensen, S., Kolagunda, A., O’Neal, M., Phelan, B. R., Sherbondy, K. D., & Kambhamettu, C. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.22 · Cited by 65
Gao, J., Wang, Q., & Yuan, Y. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989027 · Cited by 59
Multispectral Transfer Network: Unsupervised Depth Estimation for All-Day Vision
Kim, N., Choi, Y., Hwang, S., & Kweon, I. S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12297 · Cited by 55
Self-citationMultispectral Deep Neural Networks for Pedestrian DetectionPreprint
Liu, J., Zhang, S., Wang, S., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02644 · Cited by 53
Multispectral piecewise planar stereo using Manhattan-world assumption
Barrera, F., Lumbreras, F., & Sappa, A. D. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.08.009 · Cited by 46 · cited 2×
“Compared to previous multi-spectral datasets [3], [4], we captured fully registered”
BackgroundTowards robust night and day place recognition using visible and thermal imaging
Maddern, W., & Vidas, S. (2012) · QUT ePrints (Queensland University of Technology) · Cited by 44
Thermal-infrared based drivable region detection
Yoon, J. S., Park, K., Hwang, S., Kim, N. I., Choi, Y., Rameau, F., & Kweon, I. S. (2016) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2016.7535507 · Cited by 18 · cited 1×
“For details about the benchmarks and evaluation metrics, we refer the reader to several earlier works [13], [24]–[27], and our project website.”
MethodSelf-citationDoes V-NIR based Image Enhancement Come with Better Features?Preprint
Sharma, V., & Gool, L. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.06521 · Cited by 5 · cited 1×
“Recently, deep-learning-based techniques have showed high performance in the RGB domain [28], [29] and in the multispectral domain [30]–[32].”
Background
Research works printed but not linked: 1
- choi, 2015, All-day visual place recognition: Benchmark dataset and baseline, Proc IEEE Conf Comput Vis Pattern Recognit Workshop (CVPRW), 1
Cited by
nuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
“The KAIST multispectral dataset [17] is a multimodal dataset that consists of RGB and thermal camera, RGB stereo, 3D lidar and GPS/IMU.”
MethodScalability in Perception for Autonomous Driving: Waymo Open Dataset
Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00252 · Cited by 3,437
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889
“KAIST multi-spectral [283] X X X Vehicle X”
BackgroundFeng, D., Haase-Schutz, C., Rosenbaum, L., Hertlein, H., Glaser, C., Timm, F., Wiesbeck, W., & Dietmayer, K. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2972974 · Cited by 1,425
“The KAIST Multispectral Dataset [92] provides both thermal images and LiDAR data.”
BackgroundMethodInfluentialDrone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning
Sun, Y., Cao, B., Zhu, P., & Hu, Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3168279 · Cited by 693
“However, most of these meth- 42 ods were designed for the RGB modality alone, and cannot 43 overcome the challenges in complex scenarios, such as low- 44 light conditions [15], [16].”
Background
Metadata
- Authors
- Choi, Y., Kim, N., Hwang, S., Park, K., Yoon, J. S., An, K., & Kweon, I. S.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- University of Minnesota (US)
- Electronics and Telecommunications Research Institute (KR)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2018-03
- Volume
- 19
- Issue
- 3
- Pages
- 934-948
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2789621390
- Cited by
- 370
- References
- 39
- Citations by year
- 2026: 29 · 2025: 57 · 2024: 60 · 2023: 65 · 2022: 57 · 2021: 49 · 2020: 35 · 2019: 16 · 2018: 2
- FWCI
- 13.54
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- Funders
- Development of Autonomous Emergency Braking System for the Pedestrian Protection Project through the Ministry of Trade, Industry and Energy, South Korea (10044775)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- autonomous driving, assisted driving, infrared thermography, multi-sensor calibration, LiDAR, inertial sensors, object detection, localization, image enhancement, depth estimation, image colorization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.