An Approach Towards Activity Recognition using AI and ML

Author:

Soniya Rajendra Binnod 1,Dr. Amit K Gaikwad 1

Affiliation:

1. G. H. Raisoni University, Amravati, India

Abstract

The study of correctly identifying human actions that are put to various tests is known as "human activity recognition."Human activity is the constant flow of one or more discrete actions that are necessary for advancement. A series of activities in which an individual enters a room, moves ahead, sits down, stands up, etc. is a specimen of human activity. Human activity recognition can be carried out at many abstract levels and has broad applications in the actual world, such as activity-based search, monitoring of critical sites, patient monitoring, etc. the years, researchers, engineers, and students from all across the world have explored the identification of human action.YoloV4 and DarkNet are two computer vision algorithms used in machine learning-based activity recognition that identify the actions that are performed

Publisher

Naksh Solutions

Reference10 articles.

1. J. Redmon, "YOLO: Real-Time Object Detection," 2020.* Pjred-die.com [online].Accessible at: ¡https://pjreddie.com/darknet/yolo/•[As of December 6, 2020]..

2. Maintaining the 2016 Ranked Keyword Search Method2. "In the next years, the amount of data generated by new surveillance cameras will grow exponentially."[Online, 12 Mar. 2018 Accessed].a website called SecurityInfoWatch.comproduced by new surveillance cameras to rise dramatically in the upcoming years

3. You Only Look Once: Unified, Real-Time Object Detection, by J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, pp. 779-788.10.1109/CVPR.2016.91 is the doi.

4. Evaluation of video activity localizations integrating quality and quantity data by C. Wolf, J. Mille, E. Lombardi, O. Celiktutan, M. Jiu, E.Dogan, G. Eren, M. Baccouche, E. Dellandrea, C.E. Bichot, C. Garcia, B. Sankur, In Computer Vision and Image Understanding (127):14-30, 2014...

5. Xiaoou, Yu Qiao, and Limin WangTang. Using trajectory-pooled deep-convolutional descriptors for action recognition.In CVPR, 2015, pp 4305–4314.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3