Face recognition for great apes: Identification of primates in videos

摘要

Due to the ongoing biodiversity crisis, many species including great apes such as chimpanzees or gorillas are threatened and need to be protected. To overcome the catastrophic decline of biodiversity, biologists recently started to use remote cameras for wildlife monitoring. However, the manual analysis of the resulting image and video material is extremely tedious, time consuming, and highly cost intensive. To overcome the burden of time-consuming routine work we studied and proposed novel approaches for automatic chimpanzee identification in our previous work. Starting from the assumption that humans and our closest relatives share similar facial properties, algorithms for human face recognition were adapted and extended for this purpose. However, the proposed algorithms were designed to recognize chimpanzee individuals in still images only. In this paper we extend these ideas towards chimpanzee identification in video sequences. Thus, a novel frame weighting approach is presented which significantly improves the system's accuracy.