Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201553,
        author = {YUVANSHANKAR S and Suresh S and KALEEL AHMED H and Mrs.Padma Priya J},
        title = {Efficient Animal Species Recognition from Camera Trap Images Using YOLOv8 and MobileNet with Automated Background Removal},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5141-5148},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201553},
        abstract = {One of the recent tools of environmental study which has gained significance in studying populations of wildlife is the maintenance of the wildlife through camera trap systems. Nevertheless, by eyeing thousands of captured images, it is time-consuming and not always efficient. The proposed study will provide an automated framework to identify animal species based on camera trap images with the use of deep learning methods to overcome this issue. The proposed system combines the detection of the animal with YOLOv8 with the classification of the species with MobileNet and an automated background removal process that concentrates the model on the area where the animal is located. During the first stage, the detection model is used to detect the location of the animals in the image and a region of interest is extracted. At the second stage, the image, which was cropped, is inputted to a lightweight MobileNet classifier that will identify the animal species. This two-phase pipeline is more background noise reducing than two-stage, has a better classification performance with an equivalent computational efficiency. Experimental analysis shows that the offered method can identify various animal species with higher accuracy and less complexity of the processing and be adopted to apply to large-scale wildlife monitoring. endow it in man make it more in man.},
        keywords = {Animal, Species, Recognition, Camera, Trap, Images, YOLOv2, MobileNet, Background, Removal, Deep, Learning, Computer, Vision, Wildlife, Monitoring, Classification.},
        month = {May},
        }