Abstract
The robust recognition of objects is an essential element of many maritime video surveillance systems. This paper builds on recent advances in convolutional neural networks (CNN) and proposes a new visible-infrared spectrum architecture for ship recognition. Our architecture is composed of two separate CNN processing streams, which will be consecutively combined with a merge network. This merge allows the classification to be performed and provide a rich semantic information such as appearance. It also allows to remedy some problems related to the quality of the visible images due to the weather conditions (rain, fog, etc.) and very complex maritime environment (foam, etc.). Using this architecture, we are able to achieve an average recognition accuracy of 87%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Withagen, P., Schutte, K., Vossepoel, A., Breuers, M.: Automatic classification of ships from infrared (FLIR) images (1999)
Teutsch, M., Krager, W.: Classification of small boats in infrared images for maritime surveillance. In: 2010 International WaterSide Security Conference, pp. 1–7, November 2010
Kumlu, D., Jenkins, B.K.: Autonomous ship classification using synthetic and real color images (2013)
van den Broek, S.P., Bouma, H., den Hollander, R.J.M., Veerman, H.E.T., Benoist, K.W., Schwering, P.B.W.: Ship recognition for improved persistent tracking with descriptor localization and compact representations (2014)
Pan, B., Jiang, Z., Wu, J., Zhang, H., Luo, P.: Ship recognition based on active learning and composite kernel SVM. In: Tan, T., Ruan, Q., Wang, S., Ma, H., Di, K. (eds.) IGTA 2015. CCIS, vol. 525, pp. 198–207. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-47791-5_23
Bloisi, D.D., Iocchi, L., Pennisi, A., Tombolini, L.: ARGOS-Venice boat classification. In: 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6 (2015)
Makedonas, A., Theoharatos, C., Tsagaris, V., Anastasopoulos, V., Costicoglou, S.: Vessel classification in COSMO-SkyMed SAR data using hierarchical feature selection. In: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XL-7/W3, pp. 975–982 (2015)
Bousetouane, F., Morris, B.: Fast CNN surveillance pipeline for fine-grained vessel classification and detection in maritime scenarios. In: 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 242–248, August 2016
Guo, W., Xia, X.: A ship recognition method of variational inference-based probability generative model using optical remote sensing image. Optik Int. J. Light Electron. Opt. 145(Suppl. C), 365–376 (2017)
Huang, L., Li, W., Chen, C., Zhang, F., Lang, H.: Multiple features learning for ship classification in optical imagery. In: Multimedia Tools and Applications, July 2017
Ødegaard, N., Knapskog, A.O., Cochin, C., Louvigne, J.C.: Classification of ships using real and simulated data in a convolutional neural network. In: 2016 IEEE Radar Conference (RadarConf), pp. 1–6, May 2016
Girshick, R.: Fast R-CNN. In: Proceedings of the International Conference on Computer Vision (ICCV) (2015)
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014, pp. 675–678. ACM, New York (2014)
Zhang, M.M., Choi, J., Daniilidis, K., Wolf, M.T., Kanan, C.: VAIS: a dataset for recognizing maritime imagery in the visible and infrared spectrums. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 10–16, June 2015
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Aziz, K., Bouchara, F. (2018). Multimodal Deep Learning for Robust Recognizing Maritime Imagery in the Visible and Infrared Spectrums. In: Campilho, A., Karray, F., ter Haar Romeny, B. (eds) Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science(), vol 10882. Springer, Cham. https://doi.org/10.1007/978-3-319-93000-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-93000-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92999-6
Online ISBN: 978-3-319-93000-8
eBook Packages: Computer ScienceComputer Science (R0)