Abstract
Object detection is a method for recognizing and detecting various objects present in an image or video by using the combination of learning approaches such as classification, recognition, and object localization. The identification of animal species in the wild through camera traps continues to pose an unsolved challenge, primarily attributed to various difficulties arising from shooting conditions such as fluctuating illumination, diverse weather patterns, seasonal changes, and complex backgrounds. Additionally, the unpredictable movements, diverse shapes and poses, and occlusions caused by natural objects contribute to the complexity, making accurate recognition a persistent issue. This paper utilizes the frameworks of YOLOv5 and Detectron2 for classifying animal images into predefined classes along with annotated regions. These automated frameworks for recognition and subsequent identity detection are applied to the gorillas and monkeys using the Bristol and Monkey Species dataset respectively. The experiments conducted resulted in good results on both the datasets achieving the highest mAP of 95.07 for YOLOv5.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
