Object Detection on Traffic Data Using Yolo
Object detection in images is a computer vision task that involves identifying the presence and location of objects within an image. The goal is to identify and localize all objects of interest within an image. Object detection algorithms typically work by dividing the image into smaller regions and...
Saved in:
Published in | 2023 International Conference on Data Science and Network Security (ICDSNS) pp. 1 - 5 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
28.07.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Object detection in images is a computer vision task that involves identifying the presence and location of objects within an image. The goal is to identify and localize all objects of interest within an image. Object detection algorithms typically work by dividing the image into smaller regions and then applying a classifier to each region to determine whether it contains an object or not. Once the regions are classified, the algorithm performs non-maximum suppression to eliminate duplicate detections and refine the bounding boxes around the detected objects. Using the You Only Look Once (YOLO) algorithm, the objective of this paper is to develop an object detection system using machine learning techniques. Convolutional neural networks (CNNs) are used in the YOLO algorithm, which is a well-known real-time object detection method that finds objects in video or image streams. YOLOv3, a more advanced version of the YOLO algorithm, will be used in this paper to detect objects with greater precision and speed. The system's performance will be evaluated on both image and video datasets after it is trained on a large set of images containing various objects. Additionally, the YOLOV3 will investigate data augmentation and transfer learning as means of improving the system's performance. This paper aims to create an accurate and effective object detection system that can be put to use in a variety of real-world applications like robotics, autonomous driving, and surveillance. |
---|---|
DOI: | 10.1109/ICDSNS58469.2023.10245691 |