Search

Change detection on images of very different time instants from remote sensing databases and up-to-date satellite born or UAV born imaging is an emerging technology platform today. Since outdoor sceneries, principally observation of natural reserves, agricultural meadows and forest areas, are changing in illumination, coloring, textures and shadows time-by-time, and the resolution and geometrical properties of the imaging conditions may be also diverse, robust and semantic level algorithms should be developed for the comparison of images of the same or similar places in very different times. Earlier, a new method, fusion Markov Random Field (fMRF) method has been introduced which applied unsupervised or partly supervised clustering on a fused image series by using cross-layer similarity measure, followed by a multi-layer Markov Random Field segmentation. This paper shows the effective parametrization of the fusion MRF segmentation method for the analysis of agricultural areas of fine details and difficult subclasses.

Unmixing based change detection (UBCD) provides subpixel level information on the nature of the changes that occur in a temporal image series, in addition to providing a multi-output change detection map. These advantages have recently carried UBCD to prominence among change detection approaches for hyperspectral images. However, most, if not all, works on UBCD operate with the assumption that the endmembers do not vary in character temporally or locally. This assumption often fails to uphold, as intrinsic variability of endmembers is a significant concern for most real datasets, in addition to endmember variability occurring in temporal images due to changes in lighting or acquisition conditions. This paper proposes unmixing with the recently proposed extended linear mixture model (ELMM) to address spectral variability for UBCD and highlights its advantage with respect to UBCD with the linear mixture model (LMM) through experiments on synthetic and real datasets.

The work demonstrates the possibility of aircraft detection using Sentinel-1 synthetic aperture radar image series with 10 m resolution using change detection method. Sentinel-1 data can be used for detection of large aircraft as additional “indicators”, effective in combination with high resolution observations. The results of processing are demonstrated using a series of 15 SAR images acquired within the period from January to November 2017. Presented examples show that the results of aircraft detection in many cases clearly correspond to the number of targets that can be detected in the images manually. The probability of correct detection, estimated in real observation conditions for the most of images exceeded 0,8 and the final probability for all series was 0,76.

International audience; The quantization error (QE) from Self-Organizing Map (SOM) output after learning is exploited and its principal functional properties are explored. SOM learning (unsupervised winner-take-all) is applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images. It is proven that the QE from the SOM output after learning provides a reliable indicator of potentially critical changes in images across time. The QE increases linearly with the variability in spatial contrast contents of images across time when contrast intensity is kept constant. The hitherto unsuspected capacity of this metric to capture even the smallest changes in large bodies of image time series after using ultra-fast SOM learning is illustrated on examples from SOM learning studies on computer generated images, MRI image time series, and satellite image time series. Linear trend analysis of the changes in QE as a function of the time an image of a given series was taken gives proof of the statistical reliability of this metric as an indicator of local change. It is shown that the QE is correlated with significant clinical, demographic, and environmental data from the same reference time period during which test image series were recorded. The findings show that the QE from SOM, which is easily implemented and requires computation times no longer than a few minutes for a given image series of 20 to 25, is useful for a fast analysis of whole series of image data when the goal is to provide an instant statistical decision relative to change/no change between images.

International audience; This paper presents a likelihood ratio test based method of change detectionand classification for synthetic aperture radar (SAR) time series, namelyNORmalized Cut on chAnge criterion MAtrix (NORCAMA). This methodinvolves three steps: 1) multi-temporal pre-denoising step over the wholeimage series to reduce the effect of the speckle noise; 2) likelihood ratiotest based change criteria between two images using both the original noisyimages and the denoised images; 3) change classification by a normalized cutbased clustering-and-recognizing method on change criterion matrix (CCM).The experiments on both synthetic and real SAR image series show theeffective performance of the proposed framework.

In this paper, the processing of temporal PolSAR image series is addressed through a region-based and multi-scale data representation, the Binary Partition Tree (BPT). This structure contains useful information related to the data structure at different detail levels that may be employed for different applications. The construction of this structure ans its exploitation is addressed in this work in the context of the speckle filtering and data segmentation applications. A new region model and processing strategy are defined to tackle with the temporal dimension of the data. Finally, to illustrate the capabilities of the proposed technique, results are shown with a real RADARSAT-2 dataset.

The paper introduces a novel methodology to find changes in remote sensing image series. Some remotely sensed areas are scanned frequently to spot relevant changes, and several repositories contain multi-temporal image samples for the same area. The proposed method finds changes in images scanned by a long time-interval difference in very different lighting and surface conditions. The presented method is basically an exploitation of Harris saliency function and its derivatives for finding featuring points among image samples. To fit together the definition of keypoints and their active contour around them, we have introduced the Harris corner detection as an outline detector instead of the simple edge functions. We also demonstrate a new local descriptor by generating local active contours. Saliency points support the boundary hull definition of objects, constructing by graph based connectivity detection and neighborhood description. This graph based shape descriptor works on the saliency points of the difference and in-layer features. We prove the method in finding structural changes on remote sensing images.

International audience; This paper presents a new method for unsupervised sub-pixel change detection using image series. The method is based on the definition of a probabilistic criterion capable of assessing the level of coherence of an image series relatively to a reference classification with a finer resolution. In opposition to approaches based on an a priori model of the data, the model developed here is based on the rejection of a non-structured model --- called a-contrario model --- by the observation of structured data. This coherence measure is the core of a stochastic algorithm which selects automatically the image subdomain representing the most likely changes. A theoretical analysis of this model is led to predict its performances, in particular regarding the contrast level of the image as well as the number of change pixels in the image. Numerical simulations are also presented, that confirm the high robustness of the method and its capacity to detect changes impacting more than 25% of a considered pixel under average conditions. An application to land-cover change detection is then provided using time series of satellite images.