Advancing primate surveillance with image recognition techniques from unmanned aerial vehicles

Using unmanned aerial vehicles (UAVs) for surveys on thermostatic animals has gained prominence due to their ability to provide practical and precise dynamic censuses, contributing to developing and refining conservation strategies. However, the practical application of UAVs for animal monitoring necessitates the automation of image interpretation to enhance their effectiveness. Based on our past experiences, we present the Sichuan snub-nosed monkey (Rhinopithecus roxellana) as a case study to illustrate the effective use of thermal cameras mounted on UAVs for monitoring monkey populations in Qinling, a region characterized by magnificent biodiversity. We used the local contrast method for a small infrared target detection algorithm to collect the total population size. Through the experimental group, we determined the average optimal grayscale threshold, while the validation group confirmed that this threshold enables automatic detection and counting of target animals in similar datasets. The precision rate obtained from the experiments ranged from 85.14% to 97.60%. Our findings reveal a negative correlation between the minimum average distance between thermal spots and the count of detected individuals, indicating higher interference in images with closer thermal spots. We propose a formula for adjusting primate population estimates based on detection rates obtained from UAV surveys. Our results demonstrate the practical application of UAV-based thermal imagery and automated detection algorithms for primate monitoring, albeit with consideration of environmental factors and the need for data preprocessing. This study contributes to advancing the application of UAV technology in wildlife monitoring, with implications for conservation management and research. The figure depicts using unmanned aerial vehicle (UAV) aerial survey data of the same area collected using thermal imaging and visible light sources simultaneously during a specific time period. It contrasts the visual effects of Sichuan snub-nosed monkeys in different data sources. The original thermal imaging data readily identify clustered targets, whereas under the same observational scale, targets are difficult to identify in visible light data. However, after local focus adjustment, the rich texture features in visible light data provide abundant species information. In large-scale UAV inspections, thermal imaging technology is more adept at target detection based on species behavior. Therefore, the exploration of computer-based automatic identification methods for the abundance of thermal spot data generated during inspections is the objective of drafting the manuscript "Advancing Primate Surveillance with Image Recognition Techniques from Unmanned Aerial Vehicles." As an essential and highly promising methodological exploration in primate research, we aim to attract more scholars and research groups from academic fields by presenting these findings on the cover, urging their attention and participation in this practical research direction. image Utilization of using unmanned aerial vehicle (UAV) and analyzing the collected thermal images in primate monitoring Computerized primate image recognition based on thermal databases Promoting UAV applications in animal survey and conservation Biological diversity in Qinling, China