Optical Flow Estimation Using High Frame Rate Sequences

• doi: 10.1109/ICIP.2001.958646
• title: Optical flow estimation using high frame rate sequences
• publisher: IEEE
• isbn: 0-7803-6725-1
• issn:
• partnum: 01CH37205
• rank: 3194
• access_type: LOCKED
• content_type: Conferences
• abstract: Gradient-based optical flow estimation methods such as the Lucas-Kanade (1981) method work well for scenes with small displacements but fail when objects move with large displacements. Hierarchical matching-based methods do not suffer from large displacements but are less accurate. By utilizing the high speed imaging capability of CMOS image sensors, the frame rate can be increased to obtain more accurate optical flow with wide range of scene velocities in real time. Further, by integrating the memory and processing with the sensor on the same chip, optical flow estimation using high frame rate sequences can be performed without unduly increasing the off-chip data rate. The paper describes a method for obtaining high accuracy optical flow at a standard frame rate using high frame rate sequences. The Lucas-Kanade method is used to obtain optical flow estimates at high frame rate, which are then accumulated and refined to obtain optical flow estimates at a standard frame rate. The method is tested on video sequences synthetically generated by perspective warping. The results demonstrate significant improvements in optical flow estimation accuracy with moderate memory and computational power requirements.
• article_number: 958646
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=958646
• html_url: https://ieeexplore.ieee.org/document/958646/
• abstract_url: https://ieeexplore.ieee.org/document/958646/
• publication_title: Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)
• conference_location: Thessaloniki, Greece
• conference_dates: 7-10 Oct. 2001
• publication_number: 7594
• is_number: 20718
• publication_year: 2001
• publication_date: 7-10 Oct. 2001
• start_page: 925
• end_page: 928 vol.2
• citing_paper_count: 15
• citing_patent_count: 0
• download_count: 399
• insert_date: 20020807
• index_terms:
  • ieee_terms:
    • Image motion analysis
    • Optical sensors
    • High speed optical techniques
    • Layout
    • Optical imaging
    • CMOS image sensors
    • Integrated optics
    • Testing
    • Video sequences
    • Optical computing
  • dynamic_index_terms:
    • Frame Rate
    • Optical Flow
    • Flow Estimation
    • Computational Flow
    • High Frame Rate
    • Optical Flow Estimation
    • Optical Flow Computation
    • Data Rate
    • Data Evaluation
    • High Speed
    • High Flow
    • Standard Evaluation
    • Standard Rate
    • Image Sensor
    • Camera Sensor
    • Computational Requirements
    • Hierarchical Method
    • Video Sequences
    • Large Displacement
    • Small Displacements
    • Gradient-based Methods
    • Synthetic Generation
    • Image Processing
    • Computational Complexity
    • Low-pass
    • Low-pass Filter
    • Synthetic Sequences
    • Consecutive Frames
    • Motion Vector
    • Motion Blur
    • Maximum Displacement
    • Video Compression
    • Intermediate Frames
    • Shot Noise
    • Poisson Noise
    • Temporal Integration
    • Motion Trajectory
• isbn_formats:
  • format: Print ISBN, value: 0-7803-6725-1, isbnType: Historical
• authors:
  • Author Name: SukHwan Lim
    Affiliation: Department of Electrical Engineering, Information Systems Laboratory, University of Stanford, Stanford, CA, USA
    Author URL: https://ieeexplore.ieee.org/author/37087574423
    ID: 37087574423
    Order: 1
    Author Affiliations:
    • Department of Electrical Engineering, Information Systems Laboratory, University of Stanford, Stanford, CA, USA
  • Author Name: A. El Gamal
    Affiliation: Department of Electrical Engineering, Information Systems Laboratory, University of Stanford, Stanford, CA, USA
    Author URL: https://ieeexplore.ieee.org/author/37274961200
    ID: 37274961200
    Order: 2
    Author Affiliations:
    • Department of Electrical Engineering, Information Systems Laboratory, University of Stanford, Stanford, CA, USA

Image Sensor

• sensor_type: CMOS
• resolution: 1312 x 2000
• dynamic_range: not specified
• pixel_size: not specified
• dark_current: not specified

Optical Data

• focal_length: not specified
• aperture: not specified
• field_of_view: not specified
• distortion: not specified

Performance Metrics

• frame_rate: up to several thousand frames per second

Applications & Benefits

• cell_imaging: not specified
• benefits: Enabling digital imaging in various applications including smartphones, medical devices, and automotive systems.

Supporting Organizations

• supported_by: Agilent, Canon, HP, Interval Research, Kodak

Manuscript Details

• publication_date: 7-10 Oct. 2001

Relevancy Score

• score: 9
• missing_fields:
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise

Processed JSON Filename

request_fc608942-4c40-431d-9e28-ccc7380a8e79-optical_flow_estimation_using_high_frame_rate_sequences.json