With advances in consumer electronics, demandshave increased for greater granularity in differentiating andanalyzing human daily activities. Moreover, the potential ofmachine learning, and especially deep learning, has becomeapparent as research proceeds in applications such as monitoringthe elderly, and surveillance for detection of suspicious people andobjects left in public places. Although some techniques have beendeveloped for Human Action Recognition (HAR) using wearablesensors, these devices can place unnecessary mental and physicaldiscomfort on people, especially children and the elderly.Therefore, research has focused on image-based HAR, placing iton the front line of developments in consumer electronics. Thispaper proposes an intelligent human action recognition systemwhich can automatically recognize the human daily activities fromdepth sensors using human skeleton information, combining thetechniques of image processing and deep learning. Moreover, dueto low computational cost and high accuracy outcomes, anapproach using skeleton information has proven very promising,and can be utilized without any restrictions on environments ordomain structures. Therefore, this paper discusses thedevelopment of an effective skeleton information based HARwhich can be used as an embedded system. The experiments areperformed using two famous public datasets of human dailyactivities. According to the experimental results, the proposedsystem outperforms other state-of-the-art methods on bothdatasets.
To View the Abstract Contents
Now it is Your Time to Shine.
Great careers Start Here.
We Guide you to Every Step
Success! You're Awesome
Thank you for filling out your information!
We’ve sent you an email with your Final Year Project PPT file download link at the email address you provided. Please enjoy, and let us know if there’s anything else we can help you with.
To know more details Call 900 31 31 555
The WISEN Team