Protecting endangered megafauna through AI analysis of drone images in a low-connectivity setting: a case study from Namibia.

Assessing the numbers and distribution of at-risk megafauna such as the black rhino (Diceros bicornis) is key to effective conservation, yet such data are difficult to obtain. Many current monitoring technologies are invasive to the target animals and expensive. Satellite monitoring is emerging as a potential tool for very large animals (e.g., elephant) but detecting smaller species requires higher resolution imaging. Drones can deliver the required resolution and speed of monitoring, but challenges remain in delivering automated monitoring systems where internet connectivity is unreliable or absent. This study describes a model built to run on a drone to identify in situ images of megafauna. Compared with previously reported studies, this automated detection framework has a lower hardware cost and can function with a reduced internet bandwidth requirement for local network communication. It proposes the use of a Jetson Xavier NX, onboard a Parrot Anafi drone, connected to the internet throughout the flight to deliver a lightweight web-based notification system upon detection of the target species. The GPS location with the detected target species images is sent using MQ Telemetry Transport (MQTT), a lightweight messaging protocol using a publisher/subscriber architecture for IoT devices. It provides reliable message delivery when internet connection is sporadic. We used a YOLOv5l6 object detection architecture trained to identify a bounding box for one of five objects of interest in a frame of video. At an intersection over union (IoU) threshold of 0.5, our model achieved an average precision (AP) of 0.81 for black rhino (our primary target) and 0.83 for giraffe (Giraffa giraffa). The model was less successful at identifying the other smaller objects which were not our primary targets: 0.34, 0.25, and 0.42 for ostrich (Struthio camelus australis), springbok (Antidorcas marsupialis) and human respectively. We used several techniques to optimize performance and overcome the inherent challenge of small objects (animals) in the data. Although our primary focus for the development of the model was rhino, we included other species classes to emulate field conditions where many animal species are encountered, and thus reduce the false positive occurrence rate for rhino detections. To constrain model overfitting, we trained the model on a dataset with varied terrain, angle and lighting conditions and used data augmentation techniques (i.e., GANs). We used image tiling and a relatively larger (i.e., higher resolution) image input size to compensate for the difficulty faced in detecting small objects when using YOLO. In this study, we demonstrated the potential of a drone-based AI pipeline model to automate the detection of free-ranging megafauna detection in a remote setting and create alerts to a wildlife manager in a relatively poorly connected field environment.

Monitoring rhinoceroses in Namibia's private custodianship properties.

Routinely censusing rhinoceros' populations is central to their conservation and protection from illegal killing. In Namibia, both white (Ceratotherium simum) and black (Diceros bicornis) rhinoceros occur on private land, in the latter case under a custodianship program of the Namibian Ministry of Environment and Tourism (MET). Black rhinoceros custodian landowners are responsible for the protection of the rhinoceroses on their land and are required to report regularly to the MET. Monitoring imposes a financial burden on custodians yet many of the techniques used involve expensive monitoring techniques that include the need for aerial support and/or animal instrumentation. During May and June 2018, WildTrack undertook a pilot study to census black and white rhinoceros on three private custodianship properties in Namibia. We tested three footprint identification methods for obtaining estimates of rhinoceros populations in an effort to provide less costly alternative monitoring options to rhinoceros custodians. The first was a full monitoring protocol with two components: (a) tracking each individual animal and matching them to their footprints, (b) identifying those individuals from the heel lines on the prints. The second method used simple visual heel line identification ex-situ, and the third method used just an objective footprint identification technique. These methods offer different options of fieldwork labour and cost and were designed to offer monitoring options to custodians that provided information about rhinoceros movement and location, with minimal disturbance to the rhinoceros, and best matched their human and economic resources. In this study, we describe the three methods and report the results of the pilot study to compare and evaluate their utility for rhinoceros monitoring. The first method successfully matched each trail photographed to a known rhinoceros at each site. When the other two methods disagreed with the first, they did so by failing to match single trails to a known rhinoceros, thereby creating fictitious identities consisting of a single trail. This failure occurred twice in one application, but otherwise at most once. We expect this failure can be eliminated through more stringent criteria for collecting photographs of footprints. We also briefly compare the use of footprint monitoring with other commonly used monitoring techniques. On this basis, landowners hosting rhinoceros can evaluate which method best suits their needs and resources.

Determining the numbers of a landscape architect species (Tapirus terrestris), using footprints.

BACKGROUND: As a landscape architect and a major seed disperser, the lowland tapir (Tapirus terrestris) is an important indicator of the ecological health of certain habitats. Therefore, reliable data regarding tapir populations are fundamental in understanding ecosystem dynamics, including those associated with the Atlantic Forest in Brazil. Currently, many population monitoring studies use invasive tagging with radio or satellite/Global Positioning System (GPS) collars. These techniques can be costly and unreliable, and the immobilization required carries physiological risks that are undesirable particularly for threatened and elusive species such as the lowland tapir. METHODS: We collected data from one of the last regions with a viable population of lowland tapir in the south-eastern Atlantic Forest, Brazil, using a new non-invasive method for identifying species, the footprint identification technique (FIT). RESULTS: We identified the minimum number of tapirs in the study area and, in addition, we observed that they have overlapping ranges. Four hundred and forty footprints from 46 trails collected from six locations in the study area in a landscape known to contain tapir were analyzed, and 29 individuals were identified from these footprints. DISCUSSION: We demonstrate a practical application of FIT for lowland tapir censusing. Our study shows that FIT is an effective method for the identification of individuals of a threatened species, even when they lack visible natural markings on their bodies. FIT offers several benefits over other methods, especially for tapir management. As a non-invasive method, it can be used to census or monitor species, giving rapid feedback to managers of protected areas.

Spotting Cheetahs: Identifying Individuals by Their Footprints.

The cheetah (Acinonyx jubatus) is Africa's most endangered large felid and listed as Vulnerable with a declining population trend by the IUCN(1). It ranges widely over sub-Saharan Africa and in parts of the Middle East. Cheetah conservationists face two major challenges, conflict with landowners over the killing of domestic livestock, and concern over range contraction. Understanding of the latter remains particularly poor(2). Namibia is believed to support the largest number of cheetahs of any range country, around 30%, but estimates range from 2,905(3) to 13,520(4). The disparity is likely a result of the different techniques used in monitoring. Current techniques, including invasive tagging with VHF or satellite/GPS collars, can be costly and unreliable. The footprint identification technique(5) is a new tool accessible to both field scientists and also citizens with smartphones, who could potentially augment data collection. The footprint identification technique analyzes digital images of footprints captured according to a standardized protocol. Images are optimized and measured in data visualization software. Measurements of distances, angles, and areas of the footprint images are analyzed using a robust cross-validated pairwise discriminant analysis based on a customized model. The final output is in the form of a Ward's cluster dendrogram. A user-friendly graphic user interface (GUI) allows the user immediate access and clear interpretation of classification results. The footprint identification technique algorithms are species specific because each species has a unique anatomy. The technique runs in a data visualization software, using its own scripting language (jsl) that can be customized for the footprint anatomy of any species. An initial classification algorithm is built from a training database of footprints from that species, collected from individuals of known identity. An algorithm derived from a cheetah of known identity is then able to classify free-ranging cheetahs of unknown identity. The footprint identification technique predicts individual cheetah identity with an accuracy of >90%.