Variational Optical Flow Estimation for Images with Spectral and Photometric Sensor Diversity

被引:0
作者
Bengtsson, Tomas [1 ]
McKelvey, Tomas [1 ]
Lindstrom, Konstantin [2 ]
机构
[1] Chalmers Univ Technol, Dept Signals & Syst, Gothenburg, Sweden
[2] Volvo Cars AB, Gothenburg, Sweden
来源
SIXTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2014) | 2015年 / 9443卷
关键词
Optical flow; Sensor diversity; Infrared; Variational framework;
D O I
10.1117/12.2180109
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Motion estimation of objects in image sequences is an essential computer vision task. To this end, optical flow methods compute pixel-level motion, with the purpose of providing low-level input to higher-level algorithms and applications. Robust flow estimation is crucial for the success of applications, which in turn depends on the quality of the captured image data. This work explores the use of sensor diversity in the image data within a framework for variational optical flow. In particular, a custom image sensor setup intended for vehicle applications is tested. Experimental results demonstrate the improved flow estimation performance when IR sensitivity or flash illumination is added to the system.
引用
收藏
页数:7
相关论文
共 19 条
  • [1] PERFORMANCE OF OPTICAL-FLOW TECHNIQUES
    BARRON, JL
    FLEET, DJ
    BEAUCHEMIN, SS
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) : 43 - 77
  • [2] Color TV: Total variation methods for restoration of vector-valued images
    Blomgren, P
    Chan, TF
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (03) : 304 - 309
  • [3] High accuracy optical flow estimation based on a theory for warping
    Brox, T
    Bruhn, A
    Papenberg, N
    Weickert, J
    [J]. COMPUTER VISION - ECCV 2004, PT 4, 2004, 2034 : 25 - 36
  • [4] Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
    Brox, Thomas
    Malik, Jitendra
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (03) : 500 - 513
  • [5] Image recovery via total variation minimization and related problems
    Chambolle, A
    Lions, PL
    [J]. NUMERISCHE MATHEMATIK, 1997, 76 (02) : 167 - 188
  • [6] Optical flow or image subtraction in human detection from infrared camera on mobile robot
    Fernandez-Caballero, Antonio
    Carlos Castillo, Jose
    Martinez-Cantos, Javier
    Martinez-Tomas, Rafael
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2010, 58 (12) : 1273 - 1281
  • [7] Survey of Pedestrian Detection for Advanced Driver Assistance Systems
    Geronimo, David
    Lopez, Antonio M.
    Sappa, Angel D.
    Graf, Thorsten
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (07) : 1239 - 1258
  • [8] DETERMINING OPTICAL-FLOW
    HORN, BKP
    SCHUNCK, BG
    [J]. ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) : 185 - 203
  • [9] Liu C., 2009, PIXELS EXPLORING NEW
  • [10] Man H., 2007, DEF SEC S INT SOC OP