• Nikita Mohod
• Gauri Deshpande
• Aditya Jagdale
• Vedant Talokar
• Ishika Daga, Manjiri Deole

The research paper provides an overview of various object detection algorithms used in computer vision. These algorithms include deep learning-based methods like Single Shot Detector (SSD), Region-based Convolutional Neural Networks (R-CNNs), You Only Look Once (YOLO), and Objects as Points (OAP). The algorithms are designed to detect objects within images and videos and achieve high accuracy and speed. The information provided in this research can be used as a resource for researchers and practitioners in the field of computer vision. This research paper also provides a discussion about object detection using YOLOv5 and deep learning models in computer vision. The paper covers the preparation of a custom dataset using Roboflow, training of the YOLOv5 model using PyTorch, and evaluating the model's performance using the mean average precision (mAP) metric. The results of the case study show that the trained YOLOv5 model achieved a high mAP of 0.614, indicating its ability to detect objects with high accuracy.

SSD, R-CNN, YOLO, YOLOv5, PyTorch

"Identification of Fish Species using YOLOv5", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.k503-k510, April-2023, Available :http://www.jetir.org/papers/JETIR2304A71.pdf

"Identification of Fish Species using YOLOv5", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppk503-k510, April-2023, Available at : http://www.jetir.org/papers/JETIR2304A71.pdf