Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Video Analysis for the Detection of Animals Using Convolutional Neural Networks and Consumer-Grade Drones

Chalmers, C, Fergus, P, Curbelo Montañez, CA, Longmore, SN and Wich, SA (2021) Video Analysis for the Detection of Animals Using Convolutional Neural Networks and Consumer-Grade Drones. Journal of Unmanned Vehicle Systems. ISSN 2291-3467

[img]
Preview
Text
Video Analysis for the Detection of Animals Using Convolutional Neural Networks and Consumer-Grade Drones.pdf - Accepted Version

Download (552kB) | Preview

Abstract

Determining animal distribution and density is important in conservation. The process is both timeconsuming and labour-intensive. Drones have been used to help mitigate human-intensive tasks by covering large geographical areas over a much shorter timescale. In this paper we investigate this idea further using a proof of concept to detect rhinos and cars from drone footage. The proof of concept utilises off-the-shelf technology and consumer grade drone hardware. The study demonstrates the feasibility of using machine learning (ML) to automate routine conservation tasks such as animal detection and tracking. The prototype has been developed using a DJI Mavic Pro 2 and tested over a Global System for Mobile Communications (GSM) network. The Faster RCNN Resnet 101 architecture is used for transfer learning. Inference is performed with a frame sampling technique to address the required trade-off between precision, processing speed and live video feed synchronisation. Inference models are hosted on a web platform and video streams from the drone (using OcuSync) are transmitted to a Real-Time Messaging Protocol (RTMP) server for subsequent classification. During training, the best model achieves a Mean Average Precision (mAP) of 0.83, Intersection Over Union @(IOU) 0.50 and 0.69 @IOU 0.75, respectively. On testing the system in Knowsley Safari our prototype was able to achieve the following: Sensitivity (Sen): 0.91(0.869,094), Specificity (Spec): 0.78(0.74,0.82) and an Accuracy (ACC): 0.84 (0.81,0.87) when detecting rhinos, and
Sen: 1.00(1.00,1.00), Spec: 1.00(1.00,1.00) and an ACC:1.00(1.00,1.00) when detecting cars. © Canadian Science Publishing

Item Type: Article
Additional Information: © Canadian Science Publishing
Subjects: G Geography. Anthropology. Recreation > GE Environmental Sciences
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QH Natural history > QH301 Biology
Q Science > QL Zoology
T Technology > T Technology (General)
Divisions: Biological & Environmental Sciences (new Sep 19)
Publisher: NRC Research Press
Date Deposited: 19 Apr 2021 09:56
Last Modified: 19 Apr 2021 09:56
DOI or Identification number: 10.1139/juvs-2020-0018
URI: https://researchonline.ljmu.ac.uk/id/eprint/14813

Actions (login required)

View Item View Item