In recent years, Maritime Domain Awareness (MDA) has become important for national defense in Japan. Target detection using hyperspectral data is useful for MDA. In this study, we found that Correlation Matched Filter (CMF) has a better detection accuracy than Spectral Matched Filter (SMF), both of which are derived from Reed-Xiaoli Detector. CMF doesn't need to calculate the average value of the background spectrum, which is also advantageous in real-time processing. In addition, we could also show that it is possible to improve the detection accuracy by band selection in CMF. This increases the detection accuracy of foreign matter on the ocean.
Morphological patterns of tissues are important index for pathologists to tell the difference between cancer and non-cancer cells. However, diagnoses with human eyes and experience have limitations. For example, ovarian cancers are categorized into 4 types in the morphological forms. This classification does not thoroughly correspond to the malignancy. Even worse, there are cases that medicines are not effective when patients have the same type of ovarian cancer. That is why, the new method to diagnose the cancer cells are demanded. In this paper, we measured and analyzed the hyperspectral data of colon cancer nuclei and ovarian cancer nuclei and proved that hyperspectral camera has potential to distinguish the cancer in the early stage and to find the novel classification which corresponds to the cancer malignancy. Machine learning methods enabled us to distinguish four stages of colon canceration with 98.9% accuracy. In addition, two groups of ovarian cancer specimens created based on the hyperspectral data showed a significant difference on their cumulative survival curves.
Target detection using hyperspectral images is useful for Maritime Domain Awareness (MDA). For future application to MDA, in the previous study, targets on the sea was photographed with a hyperspectral camera mounted on a helicopter to demonstrate a target detection using a Reed-Xiaoli detector (RXD). Although the demonstration turned out to be successful, for there were many erroneous detections due to white waves, improvement of the detection accuracy was desired. In this study, pixels classified as white waves by random forest, which is a supervised machine learning method, were removed from pixels which were regarded as anomaly by RXD.As a result, 76% white waves were successfully removed. This study show that white wave removal is possible by machine learning. This will improve the detection accuracy of foreign matter on the ocean.
Hyperspectral Images are now used in the field of agriculture, cosmetics, and space exploring. Behind this fact, there is a result of efforts to contrive miniaturization and decrease in costs. This paper describes low-cost and small Hyperspectral Camera (HSC) under development and a method of utilizing it. Real Time Detection System for MDA is that government agencies put those cameras in small satellites and use them for MDA (Maritime Domain Awareness). We assume early detection of unidentified floating objects to find out disguised fishing ships and submarines.
We developed a new, easy, and objective method to detect gastric cancer using hyperspectral imaging (HSI) technology combining spectroscopy and imaging A total of 16 gastroduodenal tumors removed by endoscopic resection or surgery from 14 patients at Yamaguchi University Hospital, Japan, were recorded using a hyperspectral camera (HSC) equipped with HSI technology Corrected spectral reflectance was obtained from 10 samples of normal mucosa and 10 samples of tumors for each case The 16 cases were divided into eight training cases (160 training samples) and eight test cases (160 test samples) We established a diagnostic algorithm with training samples and evaluated it with test samples Diagnostic capability of the algorithm for each tumor was validated, and enhancement of tumors by image processing using the HSC was evaluated The diagnostic algorithm used the 726-nm wavelength, with a cutoff point established from training samples The sensitivity, specificity, and accuracy rates of the algorithm’s diagnostic capability in the test samples were 78.8% (63/80), 92.5% (74/80), and 85.6% (137/160), respectively Tumors in HSC images of 13 (81.3%) cases were well enhanced by image processing Differences in spectral reflectance between tumors and normal mucosa suggested that tumors can be clearly distinguished from background mucosa with HSI technology.
Hokkaido Satellite Project was kicked off at April in 2003 by the volunteer group that consists of students, researchers and
engineers in order to demonstrate the space business models using nanosatellites of 15kg/50kg in Japan. The Hokkaido satellite
named "TAIKI" is characterized by a hyperspectral sensor with a VNIR (visible and near infrared range) and a laser
communication instrument for data downlink communication. At the beginning of 2008 we started to develop a space qualified
hyperspectral sensor HSC3000 based on the optical design of HSC1700. Last year we developed the hyperspectral camera
HSC-3000 BBM funded by New Energy Development Organization (NEDO) as the position of the breadboard model of
HSC3000. HSC-3000 BBM is specified by the spectral range from 400nm to 1000nm, 81 spectral bands, image size of 640 x 480
pixels, radiometric resolution of 10 bits and data transfer rate of 200 f/s. By averaging outputs of several adjacent pixels to
increase S/N, HSC3000 of the spaceborne is targeted at the specification of 30 m spatial resolution, 61 spectral bands, 10 nm
spectral resolution and S/N300.
Spin-off technology of the hyperspectral imager is also introduced. We have succeeded to develop a hyperspectral camera as the
spin-off product named HSC1700 which installs both the hyperspectral sensor unit and a scanning mechanism inside. The
HSC1700 is specified by the spectral range from 400nm to 800nm, 81 spectral bands, image size of 640 x 480 pixels, radiometric
resolution of 8 bits and data transfer rate of 30 f/s.