Using Drones with Thermal Imaging to Estimate Population Counts of European Hare (&lt;em&gt;Lepus europaeus&lt;/em&gt;) in Denmark

The Hainan gibbon (Nomascus hainanus) is one of the most endangered primates in the world. Infrared and visible images taken by drones are an important and effective way to observe Hainan gibbons. However, a single infrared or visible image cannot simultaneously observe the movement tracks of Hainan gibbons and the appearance of the rainforest. The fusion of infrared and visible images of the same scene aims to generate a composite image which can provide a more comprehensive description of the scene. We propose a fusion method of infrared and visible images of the Hainan gibbon for the first time, termed Swin-UetFuse. The Swin-UetFuse has a powerful global and long-range semantic information extraction capability, which is very suitable for application in complex tropical rainforest environments. Firstly, the hierarchical Swin Transformer is applied as the encoder to extract the features of different scales of infrared and visible images. Secondly, the features of different scales are fused through the l1-norm strategy. Finally, the Swing Transformer blocks and patch-expanding layers are utilized as the decoder to up-sample the fusion features to obtain the fused image. We used 21 pairs of Hainan gibbon datasets to perform experiments, and the experimental results demonstrate that the proposed method achieves excellent fusion performance. The infrared and visible image fusion technology of drones provides an important reference for the observation and protection of the Hainan gibbons.

Observing Individuals and Behavior of Hainan Gibbons (Nomascus hainanus) Using Drone Infrared and Visible Image Fusion Technology

Li,

Wang,

Zhang

et al. 2023

A Novel Scouring Method to Monitor Nocturnal Mammals Using Uncrewed Aerial Vehicles and Thermal Cameras—A Comparison to Line Transect Spotlight Counts

Povlsen,

Bruhn,

Pertoldi

et al. 2023

Self Cite

Wildlife abundance surveys are important tools for making decisions regarding nature conservation and management. Cryptic and nocturnal mammals can be difficult to monitor, and methods to obtain more accurate data on density and population trends of these species are needed. We propose a novel monitoring method using an aerial drone with a laser rangefinder and high zoom capabilities for thermal imagery. By manually operating the drone, the survey area can be initially scanned in a radius of several kilometers, and when a point of interest is observed, animals could be identified from up to one kilometer away by zooming in while the drone maintains an altitude of 120 m. With the laser rangefinder, a precise coordinate of the detected animal could be recorded instantly. Over ten surveys, the scouring drone method recorded significantly more hares than traditional transect spotlight count surveys, conducted by trained volunteers scanning the same farmland area within the same timeframe (p = 0.002, Wilcoxon paired rank test). The difference between the drone method and the transect spotlight method was hare density-dependent (R = 0.45, p = 0.19, Pearson’s product–moment correlation); the larger the density of hares, the larger the difference between the two methods to the benefit of the drone method. There was a linear relation between the records of deer by the drone and by spotlight (R = 0.69, p = 0.027), while no relation was found between the records of carnivores by drone and spotlight counts. This may be due to carnivores’ speed and vigilance or lack of data. Furthermore, the drone method could cover up to three times the area within the same timeframe as the transect spotlight counts.

Using YOLO Object Detection to Identify Hare and Roe Deer in Thermal Aerial Video Footage—Possible Future Applications in Real-Time Automatic Drone Surveillance and Wildlife Monitoring

Povlsen,

Bruhn,

Durdevic

et al. 2023

Self Cite

Wildlife monitoring can be time-consuming and expensive, but the fast-developing technologies of uncrewed aerial vehicles, sensors, and machine learning pave the way for automated monitoring. In this study, we trained YOLOv5 neural networks to detect points of interest, hare (Lepus europaeus), and roe deer (Capreolus capreolus) in thermal aerial footage and proposed a method to manually assess the parameter mean average precision (mAP) compared to the number of actual false positive and false negative detections in a subsample. This showed that a mAP close to 1 for a trained model does not necessarily mean perfect detection and provided a method to gain insights into the parameters affecting the trained models’ precision. Furthermore, we provided a basic, conceptual algorithm for implementing real-time object detection in uncrewed aircraft systems equipped with thermal sensors, high zoom capabilities, and a laser rangefinder. Real-time object detection is becoming an invaluable complementary tool for the monitoring of cryptic and nocturnal animals with the use of thermal sensors.