Automated elephant detection and classification from aerial infrared and colour images using deep learning

[摘要] ENGLISH ABSTRACT : In this study we attempt to detect and classify elephants in aerial images using deep learning.This is not a trivial task even for a human since elephants naturally blend in with their surroundings,making it a challenging and meaningful problem to solve. Possible applications of this workextend into general animal conservation and search-and-rescue operations, with natural extensionto satellite imagery as input source.We create a region proposal algorithm that relies on digital image processing techniques andmorphological operations on infrared images that correspond to the RGB images. The goal is tocreate a fast and computationally cheap algorithm that reduces the work that needs to be doneby our deep learning classification models. The algorithm reaches our accuracy goal, detecting98% of all ground truth elephants in the dataset. The resulting regions are mapped onto the correspondingRGB images using a plane-to-plane homography along with adjustment heuristics toovercome alignment issues caused by sensor vibration.We train multiple convolutional neural network models, using various network architecturesand weight initialisation techniques, including transfer learning. Two sets of models were trained,in 2015 and 2017 respectively, using different techniques, software, and hardware. The best performingmodel reduces the manual verification workload by 97% while missing only 1% of theelephants detected by the region proposal algorithm.We find that convolutional neural networks, as well as the advancements in deep learning,hold significant promise in detecting elephants from aerial images for real world applications

[发布机构] Stellenbosch University