Motion Planning for USV using Classification Capabilities

Oren Gal


This paper presents an automatic method to acquire, identify, and track obstacles from an Unmanned Surface Vehicle (USV) location in marine environments using 2D Commercial Of The Shelf (COTS) video sensors, and analyzing video streams as input. The guiding line of this research is to develop real-time automatic identification and tracking abilities in marine environment with COTS sensors. The output of this algorithm provides obstacle’s location in x-y coordinates. The ability to recognize and identify obstacles becomes more essential for USV’s autonomous capabilities, such as obstacle avoidance, decision modules, and other Artificial Intelligence (AI) abilities using low cost sensors. Our algorithm is not based on obstacles characterization. Algorithm performances were tested in various scenarios with real-time USV’s video streams, indicating that the algorithm can be used for real-time applications with high success rate and fast time computation.

Full Text:



Bhanu, C. and Holben, R. D.: Model-based segmentation of FLIR images. IEEE Trans. Aerosp. Electron. Syst. 26, 2–10 (1990).

Ben-Yosef, N. Bahat, B. and FeiginBhanu, G. and Holben, C.: Simulation of IR images of natural backgrounds. Appl. Opt. 22, 190–193 (1983).

Ratches, J. A. Walters, C. P. Buser, R. G. and Guenther, B. D.:Aided and automatic target recognition based upon sensor inputs from image forming systems. IEEE Trans. Pattern Anal. Mach. Intell. 19, 1004–1019 (1997).

Casasent, D. P. and Neiberg, L. M.:Classifier and shift-invariant automatic target recognition neural networks. Neural Networks. 8, 1117–1129 (1995).

Schachter, B. J. Lev, A. Zucker, S.W. and Rosenfeld, A.:An application of relaxation methods to edge reinforcement. IEEE Trans. Syst. Man Cybern. 7, 813–816 (1997).

Walters, D. K. W.:Computer vision model based on psychophysical experiments.Pattern Recognition by Humans and Machines, 2 (1986).

Broy, M.: Early vision. In: Rosenfeld,A.. (eds.) Perspectives in Computing, pp. 190-206. Academic Press, New York (1986).

Marham, K. C.:Comparison of segmentation processes for object acquisition in infrared scenes. IEEE Radar Signal Process. 136, 13–21 (1989).

Davies, E.R.:Machine Vision: Theory, Algorithms, Practicalities, 2nd ed., Academic Press, New York. (1997).

Marham, K. C.:Clutter metrics for target detection systems. IEEE Trans. Aerosp. Electron. Syst. 30, 81–91 (1994).

Vijaya, K.:A tutorial survey of composite filter designs for optical correlators. Appl. Opt. 31, 4773–4798 (1992).

Flannery, D. Loomis, J. and Milkovich, M.:Transform-ratio ternary phase-amplitude filter formation for improved correlation discrimination. Appl. Opt. 27, 4079–4083 (1988).

Cybenko, George. : Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems. 2, 303–314, (1989).

Gundogdu, Erhan and Solmaz, Berkan : MARVEL: A Large-Scale Image Dataset for Maritime Vessels. Computer Vision – ACCV 2016. 4, 165–180, (2016).

Zhang, Mabel M and Choi, Jean and Daniilidis, Kostas and Wolf, Michael T and Kanan, Christopher. : Vais: A dataset for recognizing maritime imagery in the visible and infrared spectrums. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2, 10–16 (2015).

Howard, Andrew G and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig : Mobilenets: Efficient convolutional neural networks for mobile vision applications. Mathematics of Control, Signals, and Systems. (2017).

Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali : You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition. 2, 779–788, (2016).

Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron and Bengio, Yoshua : Deep learning. MIT press Cambridge(2016).

Hinton, G and Sejnowski, T : A Theoretical Framework for Back-Propagation.

Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E : Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2, 1097–1105, (2012).


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.