Multiple instance hybrid estimator for hyperspectral target characterization and sub-pixel target detection

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.

Data-augmented matched subspace detector for hyperspectral subpixel target detection

“…The HyMap dataset is a benchmark dataset for hyperspectral subpixel target detection [19,20,21,22]. The MUUFL dataset provides two HSIs over the same scene, thus serving the purpose of model validation [23,24]. The proposed methods are compared against MSD, MSDinter and four classical target detection methods, namely CEM [6], AMF [3], signed ACE (sACE) [25] and OSP [4].…”

“…Therefore, using AUC would be a more informative criterion for evaluating the detection performance, which is also adopted in [23]. A target detection method is more effective if it has a larger AUC.…”

Multi-Feature Manifold Discriminant Analysis for Hyperspectral Image Classification

“…Hyperspectral imagery (HSI) provides hundreds of narrow and continuous adjacent bands through dense spectral sampling from visible to short-wave infrared regions [1][2][3][4][5][6][7][8]. A fine-spectralresolution HSI provides useful information for classifying different types of ground objects, and it has a variety of applications in many fields such as mineral exploration, environmental monitoring, precision agriculture, and target recognition [9][10][11][12][13].…”

Sparse Unmixing for Hyperspectral Image with Nonlocal Low-Rank Prior

“…It has been actively discussed by researchers and widely applied in many fields, such as agricultural production, geological survey, urban planning, and environmental monitoring [2,3]. However, because of the limitations of optical instrument's performance and imperfect spectral acquisition techniques, the spatial resolution of hyperspectral images is low, which results in a pixel that may contain more than one type of ground object signature, called a mixed pixel [4,5]. Because of the existence of many mixed pixels, the accuracy of hyperspectral image processing has been greatly affected.…”