Approximate bilateral filters for real-time and low-energy imaging applications on FPGAs

被引:3
作者
Spagnolo, Fanny [1 ]
Corsonello, Pasquale [1 ]
Frustaci, Fabio [1 ]
Perri, Stefania [2 ]
机构
[1] Univ Calabria, Dept Informat Modeling Elect & Syst Engn, I-87036 Arcavacata Di Rende, Italy
[2] Univ Calabria, Dept Mech Energy & Management Engn, I-87036 Arcavacata Di Rende, Italy
关键词
Approximate computing; Bilateral filtering; Low-power design; Real-time image processing; FPGA; QUALITY ASSESSMENT; ENHANCEMENT;
D O I
10.1007/s11227-024-06084-y
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Bilateral filtering is an image processing technique commonly adopted as intermediate step of several computer vision tasks. Opposite to the conventional image filtering, which is based on convolving the input pixels with a static kernel, the bilateral filtering computes its weights on the fly according to the current pixel values and some tuning parameters. Such additional elaborations involve nonlinear weighted averaging operations, which make difficult the deployment of bilateral filtering within existing vision technologies based on real-time and low-energy hardware architectures. This paper presents a new approximation strategy that aims to improve the energy efficiency of circuits implementing the bilateral filtering function, while preserving their real-time performances and elaboration accuracy. In contrast to the state-of-the-art, the proposed technique allows the filtering action to be on the fly adapted to both the current pixel values and to the tuning parameters, thus avoiding any architectural modification or tables update. When hardware implemented within the Xilinx Zynq XC7Z020 FPGA device, a 5 x 5 filter based on the proposed method processes 237.6 Mega pixels per second and consumes just 0.92 nJ per pixel, thus improving the energy efficiency by up to 2.8 times over the competitors. The impact of the proposed approximation on three different imaging applications has been also evaluated. Experiments demonstrate reasonable accuracy penalties over the accurate counterparts.
引用
收藏
页码:15894 / 15916
页数:23
相关论文
共 39 条
  • [21] Sable A. H., 2010, 2010 International Conference on Advances in Computer Engineering (ACE), P295, DOI 10.1109/ACE.2010.76
  • [22] Image fusion based on pixel significance using cross bilateral filter
    Shreyamsha Kumar, B. K.
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2015, 9 (05) : 1193 - 1204
  • [23] FPGA-Based Smart Camera System for Real-Time Automated Video Surveillance
    Singh, Sanjay
    Saurav, Sumeet
    Saini, Ravi
    Mandal, Atanendu S.
    Chaudhury, Santanu
    [J]. VLSI DESIGN AND TEST, 2017, 711 : 533 - 544
  • [24] Soria X, 2020, IEEE WINT CONF APPL, P1912, DOI 10.1109/WACV45572.2020.9093290
  • [25] Design of Approximate Bilateral Filters for Image Denoising on FPGAs
    Spagnolo, Fanny
    Corsonello, Pasquale
    Frustaci, Fabio
    Perri, Stefania
    [J]. IEEE ACCESS, 2023, 11 : 1990 - 2000
  • [26] Bilateral filtering for gray and color images
    Tomasi, C
    Manduchi, R
    [J]. SIXTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, 1998, : 839 - 846
  • [27] USC, SIPI IM DAT
  • [28] Trainable joint bilateral filters for enhanced prediction stability in low-dose CT
    Wagner, Fabian
    Thies, Mareike
    Denzinger, Felix
    Gu, Mingxuan
    Patwari, Mayank
    Ploner, Stefan
    Maul, Noah
    Pfaff, Laura
    Huang, Yixing
    Maier, Andreas
    [J]. SCIENTIFIC REPORTS, 2022, 12 (01)
  • [29] Image quality assessment: From error visibility to structural similarity
    Wang, Z
    Bovik, AC
    Sheikh, HR
    Simoncelli, EP
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (04) : 600 - 612
  • [30] Wennersten P, 2017, 2017 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)