Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Masami Ikura"'
Publikováno v:
Songklanakarin Journal of Science and Technology (SJST), Vol 43, Iss 6, Pp 1831-1839 (2021)
This paper proposes a hardware accelerator design for motorcycle detection based on deep learning. We designed the training parameters by K-means algorithm and created the motorcycle dataset from Thailand's urban scene. Due to the rapid evolution o
Externí odkaz:
https://doaj.org/article/a1710f8264c1412c8d7ad6a675ef1504
Autor:
Nattha Jindapetch, Surachate Chumpol, Kiattisak Sengchuai, Apidet Booranawong, Pakpoom Hoyingcharoen, Panadda Solod, Masami Ikura
Publikováno v:
Pertanika Journal of Science and Technology. 29
In this work, we proposed High-Level Synthesis (HLS) optimization processes to improve the speed and the resource usage of complex algorithms, especially nested-loop. The proposed HLS optimization processes are divided into four steps: array sizing i
Autor:
Kiattisak Sengchuai, Apidet Booranawong, Surachate Chumpol, Nattha Jindapetch, Panadda Solod, Pakpoom Hoyingcharoen, Masami Ikura
Publikováno v:
2019 IEEE International Circuits and Systems Symposium (ICSyS).
In this work, we present memory optimization in Hough transform on hardware of programmable logic (PL) part of FPGAs by using array partitioning block, cyclic and complete types at different dimension and different factor on the Xilinx Vivado High Le
Publikováno v:
2018 IEEE 5th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA).
This paper demonstrates how we can compensate the installation errors (roll and pitch angles) by estimating the rotation of the installed IMU. The estimated rotation is then used to compensate the IMU. This is result in better IMU accuracy.
Autor:
Surachate Chumpol, Kanadit Chetpattananondh, Masami Ikura, Nattha Jindapetch, Pakpoom Hoyingcharoen, Saifa Khantasak
Publikováno v:
2018 IEEE 5th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA).
This paper presents a parking violation detection system based on video processing. The proposed system captures and processes the images from a parking violation area, and also identifies the case of no vehicles in the parking area. In this paper, a
Autor:
Watcharapan Suwansantisuk, Surachate Chumpol, Masami Ikura, Pinit Kumhom, Teerasak Chotikawanid, Chanon Khongprasongsiri
Publikováno v:
2018 International Workshop on Advanced Image Technology (IWAIT).
Lane detection plays an important role in advanced driving assistance systems (ADAS). In this paper, a hardware implementation of a real-time lane detection is developed using the Xilinx's Zynq-7000 APSoC platform. The proposed algorithm of lane dete