The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
스테레오 깊이 추정은 컴퓨터 비전 분야에서 매력적인 주제가 되었습니다. 다양한 알고리즘이 추정 속도와 정밀도를 최적화하기 위해 노력하고 있지만 시스템의 에너지 비용도 임베디드 시스템의 필수 측정 기준입니다. 이러한 다양한 알고리즘 중에서 SGM(Semi-Global Matching)은 정확성과 속도의 균형으로 인해 일부 실제 응용 프로그램에서 인기 있는 선택이었습니다. 그러나 전력소모로 인해 임베디드 시스템에 적용하기에는 어려움이 있다. 따라서 우리는 Xilinx FPGA(Field-Programmable Gate Array) 플랫폼에서 작동하는 강력한 스테레오 매칭 시스템인 RT-libSGM을 제안합니다. 각 모듈의 전용 설계는 시스템 구조의 유연성을 보장하면서 전체 시스템의 속도를 최적화합니다. M-KUBOS라고 불리는 Zynq FPGA 보드에 대한 평가를 통해 RT-libSGM은 더 낮은 전력 소비로 최첨단 성능을 달성합니다. Tegra X2 GPU에서 작동하는 벤치마크 디자인(libSGM)과 비교할 때 RT-libSGM은 훨씬 낮은 에너지 비용으로 2배 이상 빠르게 실행됩니다.
Kaijie WEI
Keio University
Yuki KUNO
Marelli Corporation
Masatoshi ARAI
Saitama University
Hideharu AMANO
Keio University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kaijie WEI, Yuki KUNO, Masatoshi ARAI, Hideharu AMANO, "RT-libSGM: FPGA-Oriented Real-Time Stereo Matching System with High Scalability" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 3, pp. 337-348, March 2023, doi: 10.1587/transinf.2022EDP7131.
Abstract: Stereo depth estimation has become an attractive topic in the computer vision field. Although various algorithms strive to optimize the speed and the precision of estimation, the energy cost of a system is also an essential metric for an embedded system. Among these various algorithms, Semi-Global Matching (SGM) has been a popular choice for some real-world applications because of its accuracy-and-speed balance. However, its power consumption makes it difficult to be applied to an embedded system. Thus, we propose a robust stereo matching system, RT-libSGM, working on the Xilinx Field-Programmable Gate Array (FPGA) platforms. The dedicated design of each module optimizes the speed of the entire system while ensuring the flexibility of the system structure. Through an evaluation on a Zynq FPGA board called M-KUBOS, RT-libSGM achieves state-of-the-art performance with lower power consumption. Compared with the benchmark design (libSGM) working on the Tegra X2 GPU, RT-libSGM runs more than 2× faster at a much lower energy cost.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7131/_p
부
@ARTICLE{e106-d_3_337,
author={Kaijie WEI, Yuki KUNO, Masatoshi ARAI, Hideharu AMANO, },
journal={IEICE TRANSACTIONS on Information},
title={RT-libSGM: FPGA-Oriented Real-Time Stereo Matching System with High Scalability},
year={2023},
volume={E106-D},
number={3},
pages={337-348},
abstract={Stereo depth estimation has become an attractive topic in the computer vision field. Although various algorithms strive to optimize the speed and the precision of estimation, the energy cost of a system is also an essential metric for an embedded system. Among these various algorithms, Semi-Global Matching (SGM) has been a popular choice for some real-world applications because of its accuracy-and-speed balance. However, its power consumption makes it difficult to be applied to an embedded system. Thus, we propose a robust stereo matching system, RT-libSGM, working on the Xilinx Field-Programmable Gate Array (FPGA) platforms. The dedicated design of each module optimizes the speed of the entire system while ensuring the flexibility of the system structure. Through an evaluation on a Zynq FPGA board called M-KUBOS, RT-libSGM achieves state-of-the-art performance with lower power consumption. Compared with the benchmark design (libSGM) working on the Tegra X2 GPU, RT-libSGM runs more than 2× faster at a much lower energy cost.},
keywords={},
doi={10.1587/transinf.2022EDP7131},
ISSN={1745-1361},
month={March},}
부
TY - JOUR
TI - RT-libSGM: FPGA-Oriented Real-Time Stereo Matching System with High Scalability
T2 - IEICE TRANSACTIONS on Information
SP - 337
EP - 348
AU - Kaijie WEI
AU - Yuki KUNO
AU - Masatoshi ARAI
AU - Hideharu AMANO
PY - 2023
DO - 10.1587/transinf.2022EDP7131
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2023
AB - Stereo depth estimation has become an attractive topic in the computer vision field. Although various algorithms strive to optimize the speed and the precision of estimation, the energy cost of a system is also an essential metric for an embedded system. Among these various algorithms, Semi-Global Matching (SGM) has been a popular choice for some real-world applications because of its accuracy-and-speed balance. However, its power consumption makes it difficult to be applied to an embedded system. Thus, we propose a robust stereo matching system, RT-libSGM, working on the Xilinx Field-Programmable Gate Array (FPGA) platforms. The dedicated design of each module optimizes the speed of the entire system while ensuring the flexibility of the system structure. Through an evaluation on a Zynq FPGA board called M-KUBOS, RT-libSGM achieves state-of-the-art performance with lower power consumption. Compared with the benchmark design (libSGM) working on the Tegra X2 GPU, RT-libSGM runs more than 2× faster at a much lower energy cost.
ER -