No abstract

No abstract

This article addresses the problem of estimating scene visibility in time series of satellite images. It focuses on satellites with few spectral bands and high revisit frequency. Our approach exploits the redundancy of information acquired during these revisits. It is based on an unsupervised algorithm that tracks local ground textures across time and detects ruptures caused mainly by opaque clouds and in some cases by haze, cirrus and shadows. Experiments have been carried out on 18 PlanetScope image times series of various locations. These time series come with handmade ground truth labels that are published together with this paper. We compare our results with the Unusable Data Masks (UDM) that Planet provides together with the images, and demonstrate the effectiveness of the proposed method: success rates of 97.78% and 89.36% are reached for the visible and occluded regions classification. This article is related to the following publication: [

This paper proposes a cloud detection algorithm for Earth observation images obtained by pushbroom satellite imagers. The pushbroom technology induces an inter-band acquisition delay leading to a parallax effect for the clouds. We propose a method exploiting this characteristic thanks to the analysis of the inter-band disparity. Several other features discriminating clouds are also defined and all are merged to build a robust a contrario statistical decision. Experiments applied on scenes acquired by various pushbroom satellites such as Sentinel-2, RapidEye and WorldView-2 show the effectiveness of the proposed method. In particular, we demonstrate a balanced accuracy rate close to 98% for cloud and non cloud classification for Sentinel-2 images.

Abstract. Assessing ground visibility is a crucial step in automatic satellite image analysis. Nevertheless, several recent Earth observation satellite constellations lack specially designed spectral bands and use a frame camera, precluding spectrum-based and parallax-based cloud detection methods. An alternative approach is to detect the parts of each image where the ground is visible. This can be done by comparing locally pairs of registered images in a temporal series: matching regions are necessarily cloud free. Indeed, the ground has persistent patterns that can be observed repetitively in the time series while the appearance of clouds changes at each date. To detect reliably the “visible” ground, we propose here an a contrario local image matching method coupled with an efficient greedy algorithm.

The conception and improvement of algorithms for subpixel stereovision requires very precise test databases. The state of the art on the sets of images used extensively by the scientific community shows that they are often incomplete and imprecise compared to the dataset goals. We will present a method based on image synthesis to produce stereoscopic pairs with ground truths such as disparity and occlusion maps reaching an accuracy of about 10 −6 pixels. The a priori noise estimate is also taken into account. This process allows us to deliver a new image database consisting of 66 stereo pairs together with their ground truths.Keywords: ground truths; disparity map; stereovision; synthetic images Source CodeWe provide the code of a program that computes the 3D coordinates of the points associated with each ground truth in order to view them with appropriate software. We also provide a modified code of the algorithm from Lisani et al. [15]. It allows to process images in floating point format such as TIF or EXR. Supplementary MaterialThe database is available at this address 1 . The use of these images for scientists is permitted provided that this article is mentioned as well as the designers of the scenes.

This article studies the effectiveness of optical flow methods applied to short baseline image pairs under different noise levels. New metrics have been developed to analyze the results because the usual metrics are inadequate in a subpixel context. We have used the implementation of some standard optical flow methods adapted to the stereo problem. Our experiments show that the Brox et al. method produces the least errors, with a 60% success rate and a relative precision at 1/100th of a pixel. On the other hand, our comparison shows that a discontinuity preserving method, derived from Brox et al., also provides competitive results at the same time that it yields disparities with more details and correct contours. Source Code Source codes of Lucas-Kanade 1D, Robust Optical Flow 1D and Robust Discontinuity Preserving 1D algorithms are provided in the web page of the article 1 .

No abstract