Unsupervised Change Detection in Multitemporal SAR Images Using MRF Models

An unsupervised change-detection method that considers the spatial contextual information in a log-ratio difference image generated from multitemporal SAR images is proposed. A Markov random filed (MRF) model is particularly employed to exploit statistical spatial correlation of intensity levels among neighboring pixels. Under the assumption of the independency of pixels and mixed Gaussian distribution in the log-ratio difference image, a stochastic and iterative EM-MPM change-detection algorithm based on an MRF model is developed. The EM-MPM algorithm is based on a maximiser of posterior marginals (MPM) algorithm for image segmentation and an expectation-maximum (EM) algorithm for parameter estimation in a completely automatic way. The experiment results obtained on multitemporal ERS-2 SAR images show the effectiveness of the proposed method.

Technique Based on Image Pyramid and Bayes Rule for Noise Reduction in Unsupervised Change Detection

In this paper,a technique based on image pyramid and Bayes rule for reducing noise effects in unsupervised change detection is proposed.By using Gaussian pyramid to process two multitemporal images respectively,two image pyramids are constructed.The difference pyramid images are obtained by point-by-point subtraction between the same level images of the two image pyramids.By resizing all difference pyramid images to the size of the original multitemporal image and then making product operator among them,a map being similar to the difference image is obtained.The difference image is generated by point-by-point subtraction between the two multitemporal images directly.At last,the Bayes rule is used to distinguish the changed pixels.Both synthetic and real data sets are used to evaluate the performance of the proposed technique.Experimental results show that the map from the proposed technique is more robust to noise than the difference image.

Use of Sentinel-1 imagery for flood management in a reservoir-regulated river basin

Flood hazard monitoring and mapping is of great importance because it represents a significant contribution to risk management. The present study investigated the flood event that occurred downstream from the transboundary Strymon River basin, more specifically at Serres basin-a reservoir-regulated basin, in the beginning of 2015. The focus of this study was to better understand the spatio-temporal dynamic of the flood and the causes that initiated the hazard. Within the Serres basin, the Strymon transboundary river outflows to Lake Kerkini, which regulates water flow downstream for irrigation purposes and flood protection. For this research, a dataset of Sentinel-1 SAR GRD images was collected and processed covering the period of October 2014-October 2015 to investigate the water level changes in Lake Kerkini. Based on SAR images, binary water/non-water products and multitemporal RGB amplitude images were generated and interpreted. Sentinel-1 products have proved to be an effective tool on flood hazard dynamic extension mapping and estimation of water extent bodies retained by small reservoirs. In agreement with hydro-meteorological data and the high-resolution DEM, it was conceived that the flood event occurred due to the water volume flowing from upstream in the reservoir and the large amount of water draining from the tributaries into nearby sub-basins. Moreover, inefficient water management of the overwhelming water flow through the dam could further strengthen the flood event. The proposed approach, which is entirely based on open access remotely sensed data and processing tools, could be implemented in the same area for past flood events to produce archive retrospective data, as well as in other similar reservoir-regulated river basins in terms of water management and flood risk management.