An IoT-based Bearded Dragon Enclosure Integrating YOLO Object Detection for Monitoring Food and Cleanliness

Among exotic reptiles, bearded dragons (Pogona) are popular pets. As ectotherms, bearded dragons require special food and controlled environments, including temperature, humidity, ultraviolet light, and cleanliness. This research applied the Internet of Things (IoT) to control environments within the pet enclosure. In addition, the You Only Look Once (YOLO) deep learning algorithm applied to convolutional neural networks was used to create object detection to count crickets eaten by a dragon and detect feces inside the enclosure. To find the appropriate YOLO structure, three varied experiments were proposed, including different versions YOLO and sizes as well as hyperparameter tuning. Results were that YOLYv5s with 16 batches and 0.01 learning rate was the appropriate structure with an average precision of 0.8246 and 0.6051 for detecting crickets and feces, respectively, at a mean average precision of 0.7149. The proposed enclosure with object detection may improve efficiency and reduce redundancy in breeder tasks.