YOLO-Based Analysis of Pet Emotional Behavior to Emotion Classification in Dogs and Cats

Abstract

Deep learning research has actively focused on object detection due to its importance for applications such as image and video interpretation. Object detection is an important issue in computer vision and has close-related applications such as surveillance and autonomous vehicles. This paper explores the use of You Only Look Once (YOLO), a state-of-the-art deep learning framework, to detect objects in animal images. As we all know, the YOLO model is known for its high speed and high accuracy, and it has been applied to applications that require real-time processing. In order to optimize the YOLO model for correctly classifying among the images of animals in the presence of people and images of just animals who are happy, sad and excited, images of cats and dogs in three states were made to the pre-trained CNN. From the experimental data, it can be confirmed that there some improvements of using more accurate YOLO versions for recognizing animal emotions, making the accuracy from 70% to 96%. The model was able to achieve a mean Average Precision (mAP) of 91%. The results highlight that the model is well positioned to improve urban safety and security through a highly effective approach to animal detection.