Treffer: Vision based obstacle detection system for micro aerial vehicles.

This paper proposes an integrated vision based obstacle detection algorithm based on Background subtraction technique, optical flow, Grey Level Co-occurrence Matrix features, Color Histogram Features and Hu Moments for Micro Aerial vehicles (MAVs). Raspberry Pi 3 camera module is mounted on the MAV to acquire the image frames with obstacles. Obstacle detection algorithm is developed using Python programming language. In the feature extraction phase, Haralick Features, Color Histogram Features and Hu Moments Features were extracted from the training image frames. The extracted features are used to train the SVM classifier. In the testing phase, trained object recognition model is used to detect the object in the test image frame. Support vector machines with various kernels such as the linear kernel (LSVM), Gaussian kernel SVM (GSVM), Sigmoid kernel SVM (SSVM) and Polynomial kernel SVM (PSVM) have been employed. Experimental results demonstrate that the SVM with gaussian kernel-based yields the highest accuracy for the classification of object class and non-object class from the testing images. Finally, dynamic obstacles are detected by using the Optical Flow Lukas Kanade tracking method. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)