Members-Internal


Acceleration of Hand-gesture Recognition based on Artificial Deep Neural Network

Background

Hand gestures are a form of non-verbal communication used by individuals in conjunction with speech to communicate. Nowadays, with the increasing use of technology, hand-gesture recognition is considered to be an important aspect of Human-Machine Interaction (HMI), allowing the machine to capture and interpret the user's intent and respond accordingly.

Hand-gesture recognition is an important task in medical settings such as prosthetic control, which can be performed using EMG biomedical signals, hand-gesture images, or a combination of both

Self-driving cars have drawn a lot of attention in recent years, and with help of machine learning, have advanced rapidly. Self-driving cars will have to consistently carryout all driving functions without human assistance. Traffic Hand-gesture Recognition requires fast execution speed.

Research Goal

The goal of my research is to optimize and accelerate in hardware the Japanese Traffic Hand-gesture Command Recognition.

Or

The goal of my research is to accelerate in hardware Hand-gesture Recognition using Images [[Hand Gesture Datasets]]

Research Schedule

DateTask
June 1 - June 31, 2020Read papers, Make an environment to execute programs
July 1 - July 31, 2020Learn about FPGA acceleration
July 1 - September 31, 2020Design a system for FPGA of CNN
September 1 - October 31, 2020Evaluate the performance of FPGA operation
October 1 - November 31, 2020Write paper

Research Progress

RPS: fileRPS1-0629.pdf

References

Midterm Poster

Submission deadline 8/31/2020

Other WWW Reference

Hand-gesture datasets


トップ   新規 一覧 検索 最終更新   ヘルプ   最終更新のRSS