Open AccessDetecting African hoofed animals in aerial imagery using convolutional neural network
Author(s) -
Yunfei Fang,
Shengzhi Du,
Larbi Boubchir,
Karim Djouani
Publication year - 2021
Publication title -
international journal of robotics and automation (ijra)/iaes international journal of robotics and automation
Language(s) - English
Resource type - Journals
eISSN - 2722-2586
pISSN - 2089-4856
DOI - 10.11591/ijra.v10i2.pp133-143
Subject(s) - convolutional neural network , artificial intelligence , aerial imagery , computer science , object detection , computer vision , feature (linguistics) , object (grammar) , pixel , pattern recognition (psychology) , convolution (computer science) , deep learning , high resolution , prime (order theory) , geography , remote sensing , artificial neural network , mathematics , philosophy , linguistics , combinatorics
Small unmanned aerial vehicles applications had erupted in many fields including conservation management. Automatic object detection methods for such aerial imagery were in high demand to facilitate more efficient and economical wildlife management and research. This paper aimed to detect hoofed animals in aerial images taken from a quad-rotor in Southern Africa. Objects captured in this way were small both in absolute pixels and from an object-to-image ratio point of view, which were not perfectly suit for general purposed object detectors. We proposed a method based on the iconic Faster region-based convolutional neural networks (R-CNN) framework with atrous convolution layers in order to retain the spatial resolution of the feature map to detect small objects. A good choice of anchors was of prime importance in detecting small objects. The performance of the proposed Faster R-CNN with atrous convolutional filters in the backbone network was proven to be outstanding in our scenario by comparing to other object detection architectures.