In this paper we propose a supervised learning system for counting and localizing palm trees in high-resolution, panchromatic satellite imagery (40cm/pixel to 1.5m/pixel). A convolutional neural network classifier trained on a set of palm and no-palm images is applied across a satellite image scene in a sliding window fashion. The resultant confidence map is smoothed with a uniform filter. A non-maximal suppression is applied onto the smoothed confidence map to obtain peaks. Trained with a small dataset of 500 images of size 40x40 cropped from satellite images, the system manages to achieve a tree count accuracy of over 99%.
@article{arxiv.1701.06462,
title = {Using Convolutional Neural Networks to Count Palm Trees in Satellite Images},
author = {Eu Koon Cheang and Teik Koon Cheang and Yong Haur Tay},
journal= {arXiv preprint arXiv:1701.06462},
year = {2017}
}