<Abstract> Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us to obtain redundant spectral information of the observed scenes from the reflected light source from objects. A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved. In this work, we proposed a salient object detection model on hyperspectral images by applying manifold ranking (MR) on self-supervised Convolutional Neural Network (CNN) features (high-level features) from unsupervised image segmentation task. Self-supervision of CNN continues until clustering loss or saliency maps converges to a defined error between each iteration. Finally, saliency estimations is done as the saliency map at last iteration when the self-supervision procedure terminates with convergence. Experimental evaluations demonstrated that proposed saliency detection algorithm on hyperspectral images is outperforming state-of-the-arts hyperspectral saliency models including the original MR based saliency model.
<Abstract> Land cover classification and investigation of temporal changes are considered to be common applications of remote sensing. Water/non-water region estimation is one of the most fundamental classification tasks, analyzing the occurrence of water on the Earth's surface. However, common remote sensing practices such as thresholding, spectral analysis, and statistical approaches are not sufficient to produce a globally adaptable water classification. The aim of this study is to develop a formula with automatically derived tuning parameters using perceptron neural networks for water/non-water region estimation, which we call the Perceptron-Derived Water Formula (PDWF), using Landsat-8 images. Water/non-water region estimates derived from PDWF were compared with three different approaches--Modified Normalized Difference Water Index (MNDWI), Automatic Water Extraction Index (AWEI), and Deep Convolutional Neural Network--using various case studies. Our proposed method outperforms all three approaches, showing a significant improvement in water/non-water region estimation. PDWF performance is consistently better even in cases of challenging conditions such as low reflectance due to hill shadows, building-shadows, and dark soils. Moreover, our study implemented a sunglint correction to adapt water/non-water region estimation over sunglint-affected pixels. View Full-Text
This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end manner. However, in many applications such as building change detection on satellite images, few positive samples are available for the training. Moreover, scene image pairs contain many trivial events, such as in illumination changes or background motions. These many trivial events and the class imbalance problem lead to false alarms for rare event detection. In order to overcome these difficulties, we propose a novel method to learn disentangled representations from only low-cost negative samples. The proposed method disentangles different aspects in a pair of observations: variant and invariant factors that represent trivial events and image contents, respectively. The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.