• Home
  • Search
  • Distance Quantization Method for Fast Nearest Neighbor Search Computations with applications to Motion Estimation
  • Cite Icon3
  • https://doi.org/10.1109/acssc.2007.4487351Copy DOI Icon

Distance Quantization Method for Fast Nearest Neighbor Search Computations with applications to Motion Estimation

  • Nov 1, 2007
  • Hye-Yeon Cheong +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The problem of given a query vector finding its nearest neighbor within a large set of vectors in high dimensional space arises in many applications. It often poses serious computational challenges due to the size of data point set (database), dimensionality of the search space, and the metric complexity. There exists a wealth of results in the literature that reduce complexity primarily based on altering the data set while still computing the chosen distance metric to full precision. However further significant simplification is attainable with our proposed approach which reduces the search metric computation resolution by applying non-uniform quantization within the metric computation process, in such a way that the minimum distance ranking is most likely to be preserved. This paper provides analytical and experimental studies of our proposed approach. We present an analytical formulation of the search performance measure that gives insight into understanding this approach. Based on this formulation we present a quantizer optimized to minimize the impact of quantization on identifying the nearest neighbor. The main advantages of this approach are that: i) it can reduce the number and complexity of required arithmetic operations significantly, ii) complexity does not increase with the order of l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> norm or input bit size, and increases only slowly with dimensionality, and most importantly iii) the penalty to be paid in performance for the complexity reduction is very small if designed optimally. Motion estimation and compensation for video coding is chosen as an example application. Without requiring any filtering, transform, or sorting process, using a simple hardware oriented mapping, our experimental results show on average 0.05 dB loss using only 1 bit per pixel distance (0.01 dB when 2 bits are used) instead of typical 8 or 16 bits metrics.

Similar Papers
  • Research Article
  • Citations98

Handwritten character classification using nearest neighbor in large databases

  • Jan 01, 1994
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • S.J Smith +3
  • Conference Article

Effective dimensionality reduction in multimedia applications

  • Mar 01, 2009
  • Seungdo Jeong +3
  • Conference Article
  • Citations6

Is similarity search useful for high dimensional spaces?

  • Jan 01, 1999
  • R Weber +1
  • Conference Article
  • Citations4

Dynamic OD Prediction for Urban Networks Based on Automatic Number Plate Recognition Data: Paramertic vs. Non-parametric Approaches

  • Oct 01, 2019
  • Fangfang Zheng +5
  • Conference Article
  • Citations3

Automated Pain Assessment: Is it Useful to Combine Person-Specific Data Samples?

  • Dec 01, 2020
  • Peter Bellmann +1
  • Book Chapter

Morphological Independence for Landmark Detection in Vision Based SLAM

  • Jun 20, 2007
  • Ivan Villaverde +2
  • Conference Article
  • Citations395

Efficient similarity search and classification via rank aggregation

  • Jun 09, 2003
  • Ronald Fagin +2
  • Conference Article
  • Citations1

Similarity search in high-dimensional datasets

  • Jun 17, 2005
  • Raghu Ramakrishnan +2
  • Research Article
  • Citations51

Cardiac motion correction based on partial angle reconstructed images in x‐ray CT

  • May 01, 2015
  • Medical Physics
  • Seungeon Kim +2
  • Research Article
  • Citations117

Voronoi-Based Continuous $k$ Nearest Neighbor Search in Mobile Navigation

  • Jun 01, 2011
  • IEEE Transactions on Industrial Electronics
  • Geng Zhao +6
  • PDF
  • Research Article
  • Citations3

Generating Tree-Lists by Fusing Individual Tree Detection and Nearest Neighbor Imputation Using Airborne LiDAR Data

  • Jan 01, 2018
  • Open Journal of Forestry
  • Joonghoon Shin +1
  • Conference Article
  • Citations3

On the improvement of motion compensation in wavelet transform video coding

  • Dec 02, 1997
  • S Luo
  • Conference Article
  • Citations8

Multi-rate encoding of a video sequence in the DCT domain

  • Aug 07, 2002
  • A Zaccarin +1
  • Research Article
  • Citations1

Multi-resolution motion estimation and compensation based on adjacent prediction of frame difference in wavelet domain

  • May 01, 2009
  • Journal of Electronics (China)
  • Guowei Tang +1
  • Conference Article
  • Citations3

Wavelet-domain shift invariant motion estimation and compensation

  • Oct 20, 2004
  • Weiting Cai +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.