Real Time Localized Multi Object Detection System.

Saved in:

Bibliographic Details
Title:	Real Time Localized Multi Object Detection System.
Authors:	Sethukarasi, T.¹, Sakthi Siva Parvathi, K. C.¹, Arthi, S. Supraja¹, Yuvasree, R.¹
Source:	Turkish Online Journal of Qualitative Inquiry. 2021, Vol. 12 Issue 4, p2336-2345. 10p.
Subject Terms:	Object recognition (Computer vision), Mobile apps, Construction projects, Cameras
Abstract:	Object discovery is a key skill required in many computer and robotic viewing programs. Recent research in this area has made great strides in many areas. Our project focuses on building a flutter-based mobile app with a beautiful UI using some popular object detection algorithms such as SSD, YOLO, MobileNet and PoseNet. We use real-time data available from Google's open image data sets, COCO, DUTS and PASCAL. To mark the performance of our project, we are training our models with Google Colab's GPU and TensorFlow acquisition API. The trained models are then converted into lightweight TensorFlow Lite files and included in our project guide. We install a camera plugin that allows the camera on our mobile to capture ongoing events and based on the selected algorithm, marking a bounding box around objects and recording it with high accuracy. In this way, our research project makes it easier for ordinary people to use it on a daily basis and discover hidden or suspicious objects in the environment. [ABSTRACT FROM AUTHOR]
	Copyright of Turkish Online Journal of Qualitative Inquiry is the property of Turkish Online Journal of Qualitative Inquiry and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Education Research Complete

Description
Abstract:	Object discovery is a key skill required in many computer and robotic viewing programs. Recent research in this area has made great strides in many areas. Our project focuses on building a flutter-based mobile app with a beautiful UI using some popular object detection algorithms such as SSD, YOLO, MobileNet and PoseNet. We use real-time data available from Google's open image data sets, COCO, DUTS and PASCAL. To mark the performance of our project, we are training our models with Google Colab's GPU and TensorFlow acquisition API. The trained models are then converted into lightweight TensorFlow Lite files and included in our project guide. We install a camera plugin that allows the camera on our mobile to capture ongoing events and based on the selected algorithm, marking a bounding box around objects and recording it with high accuracy. In this way, our research project makes it easier for ordinary people to use it on a daily basis and discover hidden or suspicious objects in the environment. [ABSTRACT FROM AUTHOR]
ISSN:	13096591