Singapore Maritime Dataset(SMD)

We have created Singapore Maritime Dataset, using Canon 70D cameras around Singapore waters. All the videos are acquired in high definition (1080X1920 pixels). We divide the dataset into parts, on-shore videos and on-board videos, which are acquired by camera placed on-shore on fixed platform and camera placed on-board a moving vessel, respectively. The videos are acquired at various locations and routes and thus do not necessarily capture the same scene. The third part is Near Infra red (NIR) videos which is also captured using another Canon 70D camera with hot mirror removed and Mid-Opt BP800 Near-IR Bandpass filter.
Acknowledgement- Dataset has been captured by Dilip K. Prasad and annotated by student volunteers. Dataset has been captured on various environmental conditions like before sunrise (40 min before sunrise), sunrise, mid day, afternoon, evening, after sunset (2hrs after sunset), Haze and Rain from July 2015 to May 2016. 

Optical lens used for all the 3 sub-dataset  - Canon EF 70-300mm f/4-5.6 IS USM

Following papers to be cited for using this dataset
D. K. Prasad, D. Rajan, L. Rachmawati, E. Rajabaly, and C. Quek, "Video Processing from Electro-optical Sensors for Object Detection and Tracking in Maritime Environment: A Survey," IEEE Transactions on Intelligent Transportation Systems (IEEE), 18 (8), 1993 - 2016, 2017. (preprint PDF)

Other papers on this dataset from our group
  1. D. K. Prasad, H. Dong, D. Rajan,  and C. Quek, "Are object detection assessment criteria ready for maritime computer vision?," IEEE Transactions on Intelligent Transportation Systems, 2019. 
  2. D. K. Prasad, C.K. Prasath, D. Rajan, L. Rachmawati, E. Rajabally, and C. Quek, "Object detection in maritime environment: Performance evaluation of background subtraction methods," IEEE Transactions on Intelligent Transportation Systems, 22 (5), 1787-1802, 2019.
  3. D. K. Prasad, D. Rajan, L. Rachmawati, E. Rajabally, and C. Quek, “MuSCoWERT: multi-scale consistence of weighted edge Radon transform for horizon detection in maritime images,”  Journal of Optical Society America A, vol. 33, issue 12, pp. 2491-2500, 2016.
  4. D. K. Prasad, C.K. Prasath, D. Rajan, L. Rachmawati, E. Rajabally, and C. Quek, “Maritime situational awareness using adaptive multisensory management under hazy conditions,” 5th International Maritime-Port Technology and Development Conference (MTEC 2017), Singapore, 26-28 April, 2017.
  5. D. K. Prasad, C.K. Prasath, D. Rajan, C. Quek, L. Rachmawati, and  E. Rajabally, “Challenges in video based object detection in maritime scenario using computer vision,” 19th International Conference on Connected Vehicles, Zurich, 13-14 January, 2017. 
  6. D. K. Prasad, D. Rajan, C. Krishna Prasath, L. Rachmawati, E. Rajabally, and C. Quek, “MSCM-LiFe: Multi-Scale Cross Modal Linear Feature for Horizon Detection in Maritime Images,”  IEEE TENCON, Singapore,22-25 Nov, 2016.

Singapore Maritime Dataset (81 videos)

Visible On-Shore dataset (link)(size- 3 GB)
(40 videos, ground truth for horizon, Object detection and Tracking)
Visible On-Board dataset (link) (size- 768 MB)
(11 videos, ground truth for horizon, Object detection, and Tracking)
Near-infra Red On-Shore dataset (link) (size- 1.51 GB)
(30 videos, ground truth for horizon, Object detection, and Tracking)

Sample Visible on-Shore dataset snapshot
MVI_1469_VIS



Sample Visible on-board dataset snapshot
MVI_0797_VIS_OB


Sample NIR on-Shore dataset snapshot
MVI_1463_NIR_RF_1_Ins


Other maritime dataset
A. Horizon detection Ground Truth and videos for Mar-DCT dataset - Link

Please cite reference below for Mar-DCT dataset
D. D. Bloisi, L. Iocchi, A. Pennisi, and L. Tombolini, “ARGOS-Venice boat classification,” in “Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on,” (2015), pp. 1–6.

B. Horizon detection Ground Truth and videos for Buoy dataset - Link
Please cite reference below for Buoy dataset
S. Fefilatyev, V. Smarodzinava, L. O. Hall, and D. B. Goldgof, “Horizon detection using machine learning techniques,” in “International Conference on Machine Learning and Applications,” (2006), pp. 17–21.

M. Kristan, J. Perš, V. Sulic, and S. Kovacic, "A graphical model for rapid obstacle image-map estimation from unmanned surface vehicles"Asian Conference on Computer Vision, ACCV2014, 2014. (link)

Ribeiro, Ricardo, Gonçalo Cruz, Jorge Matos, and Alexandre Bernardino. "A Dataset for Airborne Maritime Surveillance Environments." IEEE Transactions on Circuits and Systems for Video Technology (2017).(link)

L. Patino, T. Cane, A. Vallee, and J. Ferryman, “Pets 2016: Dataset and
challenge,” in Proceedings of the IEEE Conference on Computer Vision
and Pattern Recognition Workshops, 2016, pp. 1–8. (link)