Abstract
This work proposes a new morphological random walker (MRW) method for hyperspectral anomaly detection. The proposed method introduces a morphology-based objective function into a random walker (RW) algorithm, sufficiently exploiting spatial morphological property and spatial similarity of HSIs for detection. The MRW method comprises two major stages. Firstly, we employ the extended morphological profiles (EMPs) and different operations to extract the spatial morphological property of HSIs. Second, according to the morphological property, we construct a morphology-based objective function. This function is incorporated into the RW-based optimization model, encoding the spatial similarity of HSIs in a weighted graph. Two factors determine the class of test pixels, including the spatial morphological information learned by EMPs, and the spatial correlation among adjoining pixels modeled by the weighted graph. Since the two factors are well considered in the MRW method, the proposed method illustrates outstanding detection performances for several widely used real HSIs.
Highlights
Hyperspectral images (HSIs) can identify spectrum differences of different ground objects [1]–[4]
To exploit spectral-spatial information in anomalies effectively, this paper introduces a morphological random walker (MRW) technique, jointly capturing the spatial morphological property and spatial similarity information in HSIs for hyperspectral anomaly detection
In this work, a novel MRW detector is presented for hyperspectral anomaly detection
Summary
Hyperspectral images (HSIs) can identify spectrum differences of different ground objects [1]–[4]. In the case of scene classification, numerous spectral-spatial feature extraction methods [1], [44] have been proposed to enhance the classification performance via capturing morphological property in images, such as attribute profiles (AP) [45], [46], extinction profiles (EP) [47], [48], morphological profiles (MP)based methods [49], [50], and its extended versions (EMP) [51], [53]. The main contribution of this paper is to propose an effective anomaly detection method, jointly capturing both the morphology property of anomaly objects and the spatial similarity among adjoining pixels simultaneously. The detection result is obtained by jointly exploiting the spatial morphological information learned by EMPs and the spatial correlation among adjoining pixels modeled by the weighted graph. 2nm where P1 represents the initial detection map (e.g., in Fig. 2(g)), effectively reflecting the spatial morphology property in HSIs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
