Automated species identification for camera trapping in the Iona Skeleton Coast Trans-Frontier Conservation Area

Author(s)Paul Berry
Year Published2020
JournalThesis for Master of Natural Resources Management degree
Page Numbers i-74
Size1.57 MB

The Iona Skeleton Coast Trans-Frontier Conservation Area (TFCA), straddling the border between Angola and Namibia, has suffered through decades of civil war and poaching. While this history has been detrimental to the community of large mammals in the TFCA, data collected on the mammal populations are insufficient to enable effective management. Survey methods such as aerial counts and community-based monitoring have various shortcomings. Therefore camera trapping, which has become important in surveying wildlife worldwide, could become an essential monitoring tool also for the TFCA. However, camera traps tend to capture huge numbers of images over short periods of time. The cost and time involved in the manual analysis of such large numbers of images is the major limiting factor in camera trapping.

Deep learning-based computer vision methods proposed to date to address this problem were found unsuitable for application to camera trapping in the TFCA, being computationally too expensive, requiring specialised hardware and too much training data, focusing only one species per photograph or relying on static backgrounds between sequential images. On the other hand, the method developed in this study requires only an entry-level computer and relatively little training data while handling multi-species photos with changing backgrounds. It is able to detect and distinguish between humans, vehicles and four large mammal species of importance in the TFCA, namely giraffe, impala, oryx and zebra.

Keywords: Camera trapping, Computer vision models, Object detection, Classifying large mammals, Data management

Author: Paul Berry

Journal: Thesis for Master of Natural Resources Management degree

Terms and Conditions: Any PDF files provided by the GRC are for personal use only and may not be reproduced. The files reflect the holdings of the GRC library and only contain pages relevant to giraffe study, and may not be complete. Users are obliged to follow all copyright restrictions.