Search

Unmanned aerial vehicles (UAVs) have become a very popular way of acquiring video within contexts such as remote data acquisition or surveillance. Unfortunately, their viewpoint is often unstable, which tends to impact the automatic processing of their video flux negatively. To counteract the effects of an inconsistent viewpoint, two video processing strategies are classically adopted, namely registration and stabilization, which tend to be affected by distinct issues, namely jitter and drifting. Following our prior work, we suggest that the motion estimators used in both situations can be modeled to take into account their inherent errors. By acknowledging that drifting and jittery errors are of a different nature, we propose a combination that is able to limit their influence and build a hybrid solution for jitter-free video registration. In this work, however, our modeling was restricted to 2D-rigid transforms, which are rather limited in the case of airborne videos. In the present paper, we extend and refine the theoretical ground of our previous work. This addition allows us to show how to practically adapt our previous work to perspective transforms, which our study shows to be much more accurate for this problem. A lightweight implementation enables us to automatically register stationary UAV videos in real time. Our evaluation includes traffic surveillance recordings of up to 2 h and shows the potential of the proposed approach when paired with background subtraction tasks.

The computed tomography imaging spectrometer (CTIS) is a snapshot hyperspectral imaging system. Its output is a 2D image of multiplexed spatiospectral projections of the hyperspectral cube of the scene. Traditionally, the 3D cube is reconstructed from this image before further analysis. In this paper, we show that it is possible to learn information directly from the CTIS raw output, by training a neural network to perform binary classification on such images. The use case we study is an agricultural one, as snapshot imagery is used substantially in this field: the detection of apple scab lesions on leaves. To train the network appropriately and to study several degrees of scab infection, we simulated CTIS images of scabbed leaves. This was made possible with a novel CTIS simulator, where special care was taken to preserve realistic pixel intensities compared to true images. To the best of our knowledge, this is the first application of compressed learning on a simulated CTIS system.

The land cover reconstruction from monochromatic historical aerial images is a challenging task that has recently attracted an increasing interest from the scientific community with the proliferation of large-scale epidemiological studies involving retrospective analysis of spatial patterns. However, the efforts made by the computer vision community in remote-sensing applications are mostly focused on prospective approaches through the analysis of high-resolution multi-spectral data acquired by the advanced spatial programs. Hence, four contributions are proposed in this paper. They aim at providing a comparison basis for the future development of computer vision algorithms applied to the automation of the land cover reconstruction from monochromatic historical aerial images. First, a new multi-scale multi-date dataset composed of 4.9 million non-overlapping annotated patches of the France territory between 1970 and 1990 has been created with the help of geography experts. This dataset has been named HistAerial. Second, an extensive comparison study of the state-of-the-art texture features extraction and classification algorithms, including deep convolutional neural networks (DCNNs), has been performed. It is presented in the form of an evaluation. Third, a novel low-dimensional local texture filter named rotated-corner local binary pattern (R-CRLBP) is presented as a simplification of the binary gradient contours filter through the use of an orthogonal combination representation. Finally, a novel combination of low-dimensional texture descriptors, including the R-CRLBP filter, is introduced as a light combination of local binary patterns (LCoLBPs). The LCoLBP filter achieved state-of-the-art results on the HistAerial dataset while conserving a relatively low-dimensional feature vector space compared with the DCNN approaches (17 times shorter).

In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS Participation--Tree Species Classification Using Random Forests and Botanical Features. CLEF 2012), to highlight the impact of the choices made for segmentation aspects. All the tests are based on a database of 232 images of tree leaves depicted on natural background from smartphones acquisitions. We also propose to study the improvements, in terms of performance, using preprocessing tools, such as the interaction between the user and the application through an input stroke, as well as the use of color distance maps. The results presented in this paper shows that the method developed by Cerutti et al. (denoted Guided Active Contour), obtains the best score for almost all observation criteria. Finally, we detail our online benchmark composed of 14 unsupervised methods and 6 supervised ones.