Design of an Algorithm for Tree Detection and Localization Using CNN Convolutional Neural Networks

Abstract

Image processing is the set of techniques used to adapt and extract the necessary information for a specific application. In the case of aerial vehicles, these techniques are widely used to define the elements of the environment, the device is immersed and based on these, to make decision and plan a new path or define new missions. This paper outlines the development of two convolutional neural networks (CNN) designed to identify and localize trees within images. The development process involved utilizing a dataset comprising 280 images, of which 168 were processed and allocated for training. This augmentation increased the dataset in a ratio of 1:4, enhancing the network’s learning capacity. Out of the 280 images used, the remaining 112 were dedicated for validation purposes. The classification network was designed with 10 layers featured two mutually exclusive and categorized outputs with and without tree; and 13 layers to the regression network include 4 independent outputs corresponding to the location and size of the tree. The outcomes suggest that the proposed networks promise for such applications, however, due to the limitations of the data used for training, the network presented problems of overtraining for the classification CNN and encountered issues and errors for the localization.
Copyright © 2024 Praise Worthy Prize - All rights reserved.