Efficient high-resolution template matching with vector quantized nearest neighbour fields

Template matching is a fundamental problem in computer vision with applications in fields including object detection, image registration, and object tracking. Current methods rely on nearest-neighbour (NN) matching, where the query feature space is converted to NN space by representing each query pi...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 151; p. 110386
Main Authors: Gupta, Ankit, Sintorn, Ida-Maria
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.07.2024
Subjects:
Computerized Image Processing
Datoriserad bildbehandling
High-resolution template matching
Object detection
Template matching
Vector quantized nearest neighbour field (VQ-NNF)
Vector quantized nearest neighbour field (VQ-NNF)
Template matching
Object detection
High-resolution template matching
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Template matching is a fundamental problem in computer vision with applications in fields including object detection, image registration, and object tracking. Current methods rely on nearest-neighbour (NN) matching, where the query feature space is converted to NN space by representing each query pixel with its NN in the template. NN-based methods have been shown to perform better in occlusions, appearance changes, and non-rigid transformations; however, they scale poorly with high-resolution data and high feature dimensions. We present an NN-based method that efficiently reduces the NN computations and introduces filtering in the NN fields (NNFs). A vector quantization step is introduced before the NN calculation to represent the template with k features, and the filter response over the NNFs is used to compare the template and query distributions over the features. We show that state-of-the-art performance is achieved in low-resolution data, and our method outperforms previous methods at higher resolution. •Existing methods scale poorly with high-resolution images and high-dimensional features.•Vector quantization in the template features is used to reduce nearest neighbour computations.•Filtering is introduced in the nearest neighbour space to encode spatial information.•State-of-the-art results are generated in runtime and performance for high-resolution datasets.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2024.110386