Search the Article Database:

Search our library of articles, papers and other published materials. You can use keywords or boolean-style search:

Automated camera trap species recognition made easy: Using entry-level hardware and few training data

Computer vision methods used to analyse camera trap photos are usually computationally expensive, require large training datasets and typically focus on only one species per photograph or rely on static backgrounds between sequential images. In contrast, our proposed method requires only an entry-level computer and relatively few training data while handling multi-species photos with changing backgrounds. It is able to distinguish between four large mammal species common to the Iona–Skeleton Coast TFCA, namely giraffe, impala, oryx and zebra. Trained on

View Details + Download

Waterhole use by African fauna

Water is one of the fundamental requirements of life but there has been little study on the use of water by free-ranging wildlife communities. We investigated the timing of waterhole use by African fauna using webcams to determine whether this mode of data collection was viable, to determine whether animals drank randomly throughout the day, whether there were differences between guilds in waterhole use and finally we created a relative rank of water dependency by comparing waterhole use with the

View Details + Download