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)

Canopy Averaged Chlorophyll Content Prediction of Pear Trees using Convolutional Auto-Encoder on Hyperspectral Data

Subir Paul, Vinayaraj Poliyapram, Nevrez İmamoğlu, Kuniaki Uto, Ryosuke Nakamura, D. Nagesh Kumar

<Abstract>
Chlorophyll content is one of the essential parameters to assess the growth process of the fruit trees. This present study developed a model for estimation of canopy averaged chlorophyll content (CACC) of pear trees using the convolutional auto-encoder (CAE) features of hyperspectral data. This study also demonstrated the inspection of anomaly among the trees by employing multi-dimensional scaling (MDS) on the CAE features and detected outlier trees prior to fit nonlinear regression models. These outlier trees were excluded from the further experiments which helped in improving the prediction performance of CACC. Gaussian process regression (GPR) and support vector regression (SVR) techniques were investigated as nonlinear regression models and used for prediction of CACC. The CAE features were proven to be providing better prediction of CACC when compared with the direct use of hyperspectral bands or vegetation indices as predictors. The CACC prediction performance was improved with the exclusion of the outlier trees during training of the regression models. It was evident from the experiments that GPR could predict the CACC with better accuracy compared to SVR. In addition, the reliability of the tree canopy masks, which were utilized for averaging the features' values for a particular tree, was also evaluated.

CORN: An Alternative Way to Utilize Time-Series Data of SAR Images in Newly Built Construction Detection
Raveerat Jaturapitpornchai, Poompat Rattanasuwan, Masashi Matsuoka and Ryosuke Nakamura

<Abstract>
The limitations in obtaining sufficient datasets for training deep learning networks is preventing many applications from achieving accurate results, especially when detecting new constructions using time-series satellite imagery, since this requires at least two images of the same scene and it must contain new constructions in it. To tackle this problem, we introduce Chronological Order Reverse Network (CORN)--an architecture for detecting newly built constructions in time-series SAR images that does not require a large quantity of training data. The network uses two U-net adaptations to learn the changes between images from both Time 1-Time 2 and Time 2-Time 1 formats, which allows it to learn double the amount of changes in different perspectives. We trained the network with 2028 pairs of 256 × 256 pixel SAR images from ALOSPALSAR, totaling 4056 pairs for the network to learn from, since it learns from both Time 1-Time 2 and Time 2-Time 1. As a result, the network can detect new constructions more accurately, especially at the building boundary, compared to the original U-net trained by the same amount of training data. The experiment also shows that the model trained with CORN can be used with images from Sentinel-1. The source code is available at https://github.com/Raveerat-titech/CORN.

A Point-Wise LiDAR and Image Multimodal Fusion Network (PMNet) for Aerial Point Cloud 3D Semantic Segmentation
Vinayaraj Poliyapram, Weimin Wang and Ryosuke Nakamura

<Abstract>
3D semantic segmentation of point cloud aims at assigning semantic labels to each point by utilizing and respecting the 3D representation of the data. Detailed 3D semantic segmentation of urban areas can assist policymakers, insurance companies, governmental agencies for applications such as urban growth assessment, disaster management, and traffic supervision. The recent proliferation of remote sensing techniques has led to producing high resolution multimodal geospatial data. Nonetheless, currently, only limited technologies are available to fuse the multimodal dataset effectively. Therefore, this paper proposes a novel deep learning-based end-to-end Point-wise LiDAR and Image Multimodal Fusion Network (PMNet) for 3D segmentation of aerial point cloud by fusing aerial image features. PMNet respects basic characteristics of point cloud such as unordered, irregular format and permutation invariance. Notably, multi-view 3D scanned data can also be trained using PMNet since it considers aerial point cloud as a fully 3D representation. The proposed method was applied on two datasets (1) collected from the urban area of Osaka, Japan and (2) from the University of Houston campus, USA and its neighborhood. The quantitative and qualitative evaluation shows that PMNet outperforms other models which use non-fusion and multimodal fusion (observational-level fusion and feature-level fusion) strategies. In addition, the paper demonstrates the improved performance of the proposed model (PMNet) by over-sampling/augmenting the medium and minor classes in order to address the class-imbalance issues.