Fast motion estimation using feature extraction and XOR operations

Thinh M. Le, W. M. Snelgrove, Sethuraman Panchanathan

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Motion estimation is a temporal image compression technique where an n × n block of pixels in the current frame of a video sequence is represented by a motion vector with respect to the best matched block in a search area of the previous frame, and the DCT coefficients of the estimated error terms. In this paper, a fast technique for motion estimation is proposed and later mapped onto the SIMD structure of the Computational*RAM (C*RAM). C*RAM is a conventional computer DRAM (or SRAM) with built-in logic circuitry at the sense-amplifier to take advantage of the high on-chip memory bandwidth and massively parallel SIMD (Single-Instruction stream, Multiple-Data stream) operations. The proposed technique, first, attempts to reduce the n-bit grayscale frames into 1-bit binary frames using morphological filters, and to search for motions of the extracted features on the binary frames. While the reduction procedure requires a small percentage of computation using the full grayscale, the search procedure is performed by simple XOR logic operations and 1-b distortion accumulations on the entire search area. The second part of the paper presents the mapping of the proposed technique onto the C*RAM architecture.

Original languageEnglish (US)
Pages (from-to)108-118
Number of pages11
JournalUnknown Journal
Volume3311
DOIs
StatePublished - 1998
Externally publishedYes

Fingerprint

Random access storage
Motion estimation
pattern recognition
Feature extraction
Dynamic random access storage
Static random access storage
logic
Data Compression
Image compression
education
Pixels
discrete cosine transform
Bandwidth
Data storage equipment
amplifiers
pixels
chips
bandwidth
filters
coefficients

Keywords

  • Logic in memory
  • Motion Estimation
  • Parallel processing
  • SIMD architecture

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Fast motion estimation using feature extraction and XOR operations. / Le, Thinh M.; Snelgrove, W. M.; Panchanathan, Sethuraman.

In: Unknown Journal, Vol. 3311, 1998, p. 108-118.

Research output: Contribution to journalArticle

Le, Thinh M. ; Snelgrove, W. M. ; Panchanathan, Sethuraman. / Fast motion estimation using feature extraction and XOR operations. In: Unknown Journal. 1998 ; Vol. 3311. pp. 108-118.
@article{acadb787b45d48ed82cac732c850a27a,
title = "Fast motion estimation using feature extraction and XOR operations",
abstract = "Motion estimation is a temporal image compression technique where an n × n block of pixels in the current frame of a video sequence is represented by a motion vector with respect to the best matched block in a search area of the previous frame, and the DCT coefficients of the estimated error terms. In this paper, a fast technique for motion estimation is proposed and later mapped onto the SIMD structure of the Computational*RAM (C*RAM). C*RAM is a conventional computer DRAM (or SRAM) with built-in logic circuitry at the sense-amplifier to take advantage of the high on-chip memory bandwidth and massively parallel SIMD (Single-Instruction stream, Multiple-Data stream) operations. The proposed technique, first, attempts to reduce the n-bit grayscale frames into 1-bit binary frames using morphological filters, and to search for motions of the extracted features on the binary frames. While the reduction procedure requires a small percentage of computation using the full grayscale, the search procedure is performed by simple XOR logic operations and 1-b distortion accumulations on the entire search area. The second part of the paper presents the mapping of the proposed technique onto the C*RAM architecture.",
keywords = "Logic in memory, Motion Estimation, Parallel processing, SIMD architecture",
author = "Le, {Thinh M.} and Snelgrove, {W. M.} and Sethuraman Panchanathan",
year = "1998",
doi = "10.1117/12.304669",
language = "English (US)",
volume = "3311",
pages = "108--118",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",

}

TY - JOUR

T1 - Fast motion estimation using feature extraction and XOR operations

AU - Le, Thinh M.

AU - Snelgrove, W. M.

AU - Panchanathan, Sethuraman

PY - 1998

Y1 - 1998

N2 - Motion estimation is a temporal image compression technique where an n × n block of pixels in the current frame of a video sequence is represented by a motion vector with respect to the best matched block in a search area of the previous frame, and the DCT coefficients of the estimated error terms. In this paper, a fast technique for motion estimation is proposed and later mapped onto the SIMD structure of the Computational*RAM (C*RAM). C*RAM is a conventional computer DRAM (or SRAM) with built-in logic circuitry at the sense-amplifier to take advantage of the high on-chip memory bandwidth and massively parallel SIMD (Single-Instruction stream, Multiple-Data stream) operations. The proposed technique, first, attempts to reduce the n-bit grayscale frames into 1-bit binary frames using morphological filters, and to search for motions of the extracted features on the binary frames. While the reduction procedure requires a small percentage of computation using the full grayscale, the search procedure is performed by simple XOR logic operations and 1-b distortion accumulations on the entire search area. The second part of the paper presents the mapping of the proposed technique onto the C*RAM architecture.

AB - Motion estimation is a temporal image compression technique where an n × n block of pixels in the current frame of a video sequence is represented by a motion vector with respect to the best matched block in a search area of the previous frame, and the DCT coefficients of the estimated error terms. In this paper, a fast technique for motion estimation is proposed and later mapped onto the SIMD structure of the Computational*RAM (C*RAM). C*RAM is a conventional computer DRAM (or SRAM) with built-in logic circuitry at the sense-amplifier to take advantage of the high on-chip memory bandwidth and massively parallel SIMD (Single-Instruction stream, Multiple-Data stream) operations. The proposed technique, first, attempts to reduce the n-bit grayscale frames into 1-bit binary frames using morphological filters, and to search for motions of the extracted features on the binary frames. While the reduction procedure requires a small percentage of computation using the full grayscale, the search procedure is performed by simple XOR logic operations and 1-b distortion accumulations on the entire search area. The second part of the paper presents the mapping of the proposed technique onto the C*RAM architecture.

KW - Logic in memory

KW - Motion Estimation

KW - Parallel processing

KW - SIMD architecture

UR - http://www.scopus.com/inward/record.url?scp=0032374171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032374171&partnerID=8YFLogxK

U2 - 10.1117/12.304669

DO - 10.1117/12.304669

M3 - Article

AN - SCOPUS:0032374171

VL - 3311

SP - 108

EP - 118

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

ER -