Geoinformation Science Research Team

MUltiband Satellite Imagery for object Classification (MUSIC) for HotArea dataset

We created MUltiband Satellite Imagery for object Classification (MUSIC) for HotArea (HA) dataset. The HA is a system to automatically detect hotspots (e.g., fires and volcanoes) in the world in mid-resolution satellite data and displays the results on a web-based GIS system. Currently Hotarea utilizes Landsat 8 and Sentinel-2 data in global scale and in some selected regions, respectively.

MUltiband Satellite Imagery for object Classification (MUSIC) to detect Golf Course

We have created MUltiband Satellite Imagery for object Classification (MUSIC) to detect Golf Course (GC). There are more than 30,000 golf courses all over the world. They are good targets for research of automatic object detection due to their specific shape, world-wide distribution and common size. MUSIC for GC is the dataset to support the global survey of golf courses based on satellite imagery.

We have created Hyper Spectral Salient Object Detection Dataset (HS-SOD)

Recurrent feedback CNN for Water Region Estimation from Multitemporal Satellite Images
Vinayaraj Poliyaprama, Nevrez Imamoglub, and Ryousuke Nakamura

<Abstract>
Water region estimation is considered as one of the fundamental classication tasks in remote sensing. Several previous research works focused on traditional practices such as spectral analysis, and statistical approaches for water region estimation. However, producing a consistent global scale water estimation results are stillconsidered as relatively challenging task. On the other hand, in computer vision applications Convolutional Neural Network (CNN) emerged as greater tool for classication tasks. Recently, Recurrent Convolutional Neural
Network(R-CNN) proposed for improved classication results. Therefore, inspired from R-CNN, this research proposes a Recurrent feedback Encoder-Decoder without max-pooling for global scale water region estimation using temporal Landsat-8 images. The proposed R-CNN uses three Landsat-8 images which consist of current observation (t0) to predict water region and two previous observation of the same location (t-1, t -2), and these three temporal observation of the same location were employed for training with the ground truth labelled data (water/non-water) from the current observation. Proposed R-CNN model uses temporal input data and results in multi-temporal output for water region estimation. Experiments show promising results especially while using concatenated recurrent feedback features. The model signicantly outperforms baseline model and UNet (without recurrent and feedback structure). Detailed comparison study on temporal Landsat-8 images that highly aected by sunglint, cloud and other atmospheric conditions shows that the proposed model has a potential to produce reliable water region estimation where UNet, baseline model R-CNN single model fail.

Global structure of thermal tides in the upper cloud layer of Venus revealed by LIR onboard Akatsuki
T.Kouyama, M.Taguchi, T.Fukuhara, T.Imamura, T.Horinouchi, T.M.Sato, S.Murakami, G.L.Hashimoto, Y.J. Lee, M. Futaguchi, T. Yamada, M.Akiba, T.Satoh, M.Nakamura

<Abstract>
Longwave Infrared Camera (LIR) on board Akatsukifirst revealed the global structure of thethermal tides in the upper cloud layer of Venus. The data were acquired over three Venusian years, andthe analysis was done over the areas from the equator to the midlatitudes in both hemispheres and over thewhole local time. Thermal tides at two vertical levels were analyzed by comparing data at two differentemission angles. Dynamical wave modes consisting of tides were identified; the diurnal tide consistedmainly of Rossby‐wave and gravity‐wave modes, while the semidiurnal tide predominantly consisted of agravity‐wave mode. The revealed vertical structures were roughly consistent with the above wave modes, butsome discrepancy remained if the waves were supposed to be monochromatic. In turn, the heating profilethat excites the tidal waves can be constrained to match this discrepancy, which would greatly advance theunderstanding of the Venusian atmosphere