Jun Saito の履歴(No.7)

Intelligent Recognition of Traffic Hand Sign Command Based on Convolution Neural Network System for Sef-driving Cars

Research Bakground†

Automatic driving is one of the recent research trends.

in this situation, human hand sign(police hand sign) is one of the important factors in autoatic operation.

I propose low-scale NN architecture considering real-time processing and recognition accuracy for HW implementation.

To develop a hand sign neural network architectyure for self driving vehicles.

Read papers, May 31, 2019 [finished] read_paper_jsaito.pdf
Simulate Murakami's work, May 31, 2019 [finished]
Propose own system architecture july 31, 2019
MS exam ducuemnet preparation (recommenation, research proposal and plan), From June 3 -
Implement own system architecture, july 31, 2019
Simulate,August 31
Write GT thesis

Yuji Murakami, Yuichi Okuyama, Abderazek Ben Abdallah, SRAM Based Neural Network System for Traffic-Light Recognition in Autonomous Vehicles, Information Processing Society Tohoku Branch Conference, Feb. 10, 2018. slides.pdf

Yuji Murakami, Design of a Neural Network Architecture for Traffic Light Detection Towards Autonomous Driving Vehicles, Master's Thesis, Graduate School of Computer Science and Engineering, The University of Aizu, 3/2019