Real Time Vision Based Obstacle Detection System for Micro Aerial Vehicles Navigation using Support Vector Machines

J. Nivesha¹ , B. Anbarasu² , G. Anitha³

Section:Research Paper, Product Type: Journal-Paper
Vol.5 , Issue.9 , pp.23-27, Sep-2019

Online published on Sep 30, 2019

Copyright © J. Nivesha, B. Anbarasu, G. Anitha . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
In this paper, a real-time vision based obstacle detection system for Micro Aerial Vehicles (MAVs) navigation using Support Vector Machines. In the feature extraction stage, features, namely, Haralick Features, Color Histogram Features and Hu Moments Features were extracted from the acquired image frames using raspberry pi 3 camera. Vision based obstacle detection algorithm is implemented on raspberry pi 3 single board computer. In the training phase, 180 images (90 images with obstacle and 90 images without obstacle) are used for training and 20 images (10 images with obstacle and 10 images without obstacle). Support Vector Machines (SVM) classifier is used to classify the acquired test image frame with and without obstacle. This obstacle detection information can be used to avoid collision with the static and dynamic obstacles in the forward flight path of MAV. Experimental results on the different test image frames demonstrate that the proposed vision based obstacle detection algorithm based on Haralick Features, Color Histogram Features and Hu Moments Features extracted for the test image frame and classified with Gaussian kernel SVM Classifier produces high classification accuracy of 78.33 % compared to linear, sigmoid and polynomial kernel SVM classifier.

Key-Words / Index Term :
Object detection, Raspberry Pi, Support Vector Machine, Micro Aerial Vehicle

References :
[1] Y. Fu, D. Ma, H. Zhang, L. Zheng, “Moving object recognition based on SVM and binary decision tree”, In the Proceedings of the Data Driven Control and Learning Systems (DDCLS 2017), Chongqing, China, pp. 495-500, 2017.
[2] E. Jauregi, E. Lazkano, B. Sierra “Object recognition using region detection and feature extraction”, In Proceedings of 10th International Conference Towards Autonomous Robotic Systems (TAROS 2009), pp. 104-111.
[3] S. Bane, D.R. Pawar, “Survey on Feature Extraction methods in Object Recognition”, International Journal of Computer Science and Information Technologies, Vol.5 , pp. 3224-3226, 2014.
[4] O. Chapelle, P. Haffner, V.N. Vapnik, “Support vector machines for histogram-based image classification”, IEEE transactions on Neural Networks, Vol. 10, Issue. 5, pp. 1055-1064, 1999.
[5] P.Dollar, C. Wojek, B. Schiele, P. Perona, “Pedestrian detection: An evaluation of the state of the art.”, IEEE transactions on pattern analysis and machine intelligence, Vol. 34, Issue. 4, pp. 743-761, 2012.
[6] P.F. Felzenszwalb, R.B. Girshick, D. McAllester, D. Ramanan, “Object detection with discriminatively trained part-based models”, IEEE transactions on pattern analysis and machine intelligence”, Vol. 32, Issue. 9, pp. 1627-1645, 2010.
[7] S. Kumar, C. Singh, “A study of zernike moments and its use in devnagari handwritten character recognition”, In Proceedings of International Conference on Cognition and Recognition, pp. 514-520, 2005.
[8] D. Liu, J. Chen, G. Wu, H. Duan, “SVM-Based Remote Sensing Image Classification and Monitoring of Lijiang Chenghais”, In Proceedings of 2nd International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE), pp. 1-4, 2012.
[9] M.N. Patel, P. Tandel, “A Survey on Feature Extraction Techniques for Shape based Object Recognition”, International Journal of Computer Applications , Vol. 137, Issue. 6, pp. 16-20, 2016.
[10] C. Qian, H. Qiang, S. Gong, “An Image Classification Algorithm based on SVM”, Applied Mechanics & Materials, Vols. 738-739, pp. 542-545, 2015.
[11] M. Sharif, M.A. Khan, T. Akram, M.Y. Javed, T. Saba, A. Rehman, “A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection”, EURASIP Journal on Image and Video Processing, Vol. 2017, Issue. 1, pp. 89.
[12] K.K. Sung, T. Poggio, “Example-based learning for view-based human face detection”, IEEE Transactions on pattern analysis and machine intelligence, Vol. 20, Issue. 1, pp. 39-51, 1998.
[13] S. Wang, “A review of gradient-based and edge-based feature extraction methods for object detection”, In Proceedings of 2011 IEEE 11th International Conference on Computer and Information Technology (CIT), pp. 277-282, 2011.
[14] P.D. Wardaya, “Support vector machine as a binary classifier for automated object detection in remotely sensed data”, In Proceedings of IOP Conference Series: Earth and Environmental Science, Vol. 18, No. 1, pp. 1-6, 2014.
[15] Y. Zeng, J. Zhang, J.L. Van Genderen, G. Wang, “SVM-based multi-textural image classification and its uncertainty analysis”, In Proceedings of 2012 International Conference on Industrial Control and Electronics Engineering (ICICEE), pp. 1316-1319, 2012.