Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization

TL;DR

This paper introduces RMGD, a novel local binary descriptor that uses ring-based pooling and multi-grouped features, significantly improving discriminative power and robustness over existing binary descriptors.

Contribution

The paper proposes a new ring-region pooling configuration and an extended Adaboost for bit selection, along with multi-grouped feature integration via SVM, to enhance binary descriptor performance.

Findings

RMGD outperforms state-of-the-art binary descriptors on benchmarks.

The ring-based pooling captures more meaningful spatial information.

Multi-grouped features improve robustness and discriminativeness.

Abstract

Local binary descriptors are attracting increasingly attention due to their great advantages in computational speed, which are able to achieve real-time performance in numerous image/vision applications. Various methods have been proposed to learn data-dependent binary descriptors. However, most existing binary descriptors aim overly at computational simplicity at the expense of significant information loss which causes ambiguity in similarity measure using Hamming distance. In this paper, by considering multiple features might share complementary information, we present a novel local binary descriptor, referred as Ring-based Multi-Grouped Descriptor (RMGD), to successfully bridge the performance gap between current binary and floated-point descriptors. Our contributions are two-fold. Firstly, we introduce a new pooling configuration based on spatial ring-region sampling, allowing for involving binary tests on the full set of pairwise regions with different shapes, scales and distances. This leads to a more meaningful description than existing methods which normally apply a limited set of pooling configurations. Then, an extended Adaboost is proposed for efficient bit selection by emphasizing high variance and low correlation, achieving a highly compact representation. Secondly, the RMGD is computed from multiple image properties where binary strings are extracted. We cast multi-grouped features integration as rankSVM or sparse SVM learning problem, so that different features can compensate strongly for each other, which is the key to discriminativeness and robustness. The performance of RMGD was evaluated on a number of publicly available benchmarks, where the RMGD outperforms the state-of-the-art binary descriptors significantly.