Target-to-Anomaly Conversion for Hyperspectral Anomaly Detection

Abstract

and telling us what having access to this work means to you and why it's important to you. Thank you. NOMENCLATURE ACE Adaptive cosine estimator. AD Anomaly detector. ADBS Anomaly detection in background. ADP Anomaly detection probability. BDP Background detection probability. BKG Background. BS Background suppressibility. CDA Component decomposition analysis.

Hyperspectral Anomaly Detection with Auto-Encoder and Independent Target

“…(11,9) in [42], δ OSPDS−AD L7 + Ŝ6 (r Ŝ6 ) in [19], δ OSP−GoDec L 7 +S 6 (r L 7 +S 6 ) in [15], and δ CDASC IC 6 (r IC 6 ) in [20], respectively. In Table 7, the detectability is evaluated using EAS with AUC ADP = 0.6135 and AUC JAD = 1.6008, followed by AUC ADP = 0.6135 and AUC JAD = 1.6008 [44], while the BKG suppressibility of AUC BDP = 0.9790 that is only slightly lower than AUC BDP = 0.9818 and AUC BDP = 0.9804, generated using OSPDS-AD and OSP-GoDec respectively. Although the background suppression is not optimal, based on the overall evaluated performance, it is reasonable to say that AEIT was the best anomaly detector than other compared methods based on accuracy and efficiency.…”

“…Technically speaking, three airplanes, in Figure 7, could not be considered as anomalies due to the visible size of candidate targets [43][44][45]. Figure 7 shows the detection maps of AEIT, and Table 5 depicts the corresponding quantified detection results for the San Diego Airport scene.…”

Band Sampling of Hyperspectral Anomaly Detection in Effective Anomaly Space

“…The effectiveness of EAS in AD has been also shown in [14] that EAS can remove second-order statistics-characterized BKG and noise while removing non-Gaussian noise by SC. To avoid duplication, we refer all details to [3] and [14].…”

“…5. It was collected in August 1995 from a flight altitude of 10 000 ft with a ground sampling distance of approximately 1.56 m. This scene has been studied extensively by many reports such as [1], [2], and [3]. It has a total of 169 bands used for the experiments with low-signal/high-noise bands: bands 1-3 and bands 202-210 and water vapor absorption bands: bands 101-112 and bands 137-153 removed.…”

Anomaly Detection of Hyperspectral Images Based on Transformer With Spatial–Spectral Dual-Window Mask

“…Digital Object Identifier 10.1109/JSTARS.2022.3232762 data analysis applications [1], [2], such as anomaly detection [3], [4], image classification [5], [6], and target detection [7], [8]. Among these applications, anomaly detection utilizes continuous spectral information and spatial information of land covers to detect anomalies with significant different spectral signatures from their surrounding environment [9].…”