High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Real-time Insect Detection in YOLOv5 Model Analysis and Tracking with Deep Sort Model

Author(s):

Surat Banerjee , Freelancer

Keywords:

Insects Especially Lizard and Cockroach Detection, YOLOv5, Deep Learning, Performance Metrics, Dataset, Deep Sort Model

Abstract

Traditional methods for detecting insects, such as lizards and cockroaches, like visual inspections and traps, can be time-consuming and costly, but they can also be effective. In recent years, however, deep learning algorithms have shown promise for detecting insects in images and videos. This paper introduces a YOLO-based deep-learning model for insect detection in various environments. The YOLO algorithm was chosen for its high speed and accuracy in object detection tasks. A dataset of images and videos containing lizards and cockroaches was collected and labeled, and the YOLO model was trained using a custom architecture and hyperparameters. The model's performance was evaluated using various metrics, including precision and recall. The results show that the YOLO-based model achieved high accuracy in detecting insects and tracking with deep sort models. The limitations and potential improvements of the YOLO model for insect detection are also discussed, along with future research directions. Overall, this study demonstrates the potential of machine learning algorithms for addressing pest control challenges in various environments.

Other Details

Paper ID: IJSRDV12I50008
Published in: Volume : 12, Issue : 5
Publication Date: 01/08/2024
Page(s): 1-5

Article Preview

Download Article