Multiple Instance Hybrid Estimator for Hyperspectral Target Characterization and Sub-pixel Target Detection

TL;DR

This paper introduces a novel multiple instance hybrid estimator that effectively characterizes targets and detects sub-pixel targets in hyperspectral data despite imprecise labels and mixed pixel signatures.

Contribution

It presents a new approach combining a data mixing model with multiple instance learning to improve target signature estimation and sub-pixel detection in hyperspectral imagery.

Findings

Effective at learning discriminative target signatures

Achieves superior performance over state-of-the-art algorithms

Validated on simulated and real hyperspectral data

Abstract

The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented. In many hyperspectral target detection problems, acquiring accurately labeled training data is difficult. Furthermore, each pixel containing target is likely to be a mixture of both target and non-target signatures (i.e., sub-pixel targets), making extracting a pure prototype signature for the target class from the data extremely difficult. The proposed approach addresses these problems by introducing a data mixing model and optimizing the response of the hybrid sub-pixel detector within a multiple instance learning framework. The proposed approach iterates between estimating a set of discriminative target and non-target signatures and solving a sparse unmixing problem. After learning target signatures, a signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments show the proposed algorithm is effective at learning discriminative target signatures and achieves superior performance over state-of-the-art comparison algorithms.