Search

We propose in this article to build up a collaboration between a deep neural network and a human in the loop to swiftly obtain accurate segmentation maps of remote sensing images. In a nutshell, the agent iteratively interacts with the network to correct its initially flawed predictions. Concretely, these interactions are annotations representing the semantic labels. Our methodological contribution is twofold. First, we propose two interactive learning schemes to integrate user inputs into deep neural networks. The first one concatenates the annotations with the other network's inputs. The second one uses the annotations as a sparse ground-truth to retrain the network. Second, we propose an active learning strategy to guide the user towards the most relevant areas to annotate. To this purpose, we compare different state-of-the-art acquisition functions to evaluate the neural network uncertainty such as ConfidNet, entropy or ODIN. Through experiments on three remote sensing datasets, we show the effectiveness of the proposed methods. Notably, we show that active learning based on uncertainty estimation enables to quickly lead the user towards mistakes and that it is thus relevant to guide the user interventions.

Many applications of Visual SLAM, such as augmented reality, virtual reality, robotics or autonomous driving, require versatile, robust and precise solutions, most often with real-time capability. In this work, we describe OV$^{2}$SLAM, a fully online algorithm, handling both monocular and stereo camera setups, various map scales and frame-rates ranging from a few Hertz up to several hundreds. It combines numerous recent contributions in visual localization within an efficient multi-threaded architecture. Extensive comparisons with competing algorithms shows the state-of-the-art accuracy and real-time performance of the resulting algorithm. For the benefit of the community, we release the source code: \url{https://github.com/ov2slam/ov2slam}., Comment: Accepted for publication in IEEE Robotics and Automation Letters (RA-L). Code is available at : \url{https://github.com/ov2slam/ov2slam}

Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). It consists of continually adapting a neural network to a target image using an interactive learning process with sparse user annotations as ground-truth. We show through experiments on three datasets using synthesized annotations the benefits of the approach, reaching an IoU improvement up to 4.7% for ten sampled clicks. Finally, we exhibit that our approach can be particularly rewarding when it is faced to additional issues such as domain adaptation., Comment: 8 pages, 4 Figures, ECML-PKDD Workshop MACLEAN

We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results., Comment: 9 pages, 7 figures, 4 tables

This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations. Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations. Importantly, user annotations modify the inputs of the network - not its weights - enabling a fast and smooth process. Through experiments on two public aerial datasets, we show that user annotations are extremely rewarding: each click corrects roughly 5000 pixels. We analyze the impact of different aspects of our framework such as the representation of the annotations, the volume of training data or the network architecture. Code is available at https://github.com/delair-ai/DISIR., Comment: 8 pages, 12 figures. Published in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

A novel method performing 3D PTV from double frame multi-camera images is introduced. Particle velocities are estimated by following three steps. Firstly, separate particle reconstructions with a sparsity-based algorithm are performed on a fine grid. Secondly, they are expanded on a coarser grid on which 3D correlation is performed, yielding a predictor displacement field that allows to efficiently match particles at the two time instants. As these particles are still located on a voxel grid, the third, final step achieves particle position refinement to their actual subvoxel position by a global optimization process, also accounting for their intensities. As it strongly leverages on principles from tomographic reconstruction, the technique is termed Double-Frame Tomo-PTV (DF-TPTV). Synthetic tests on a complex turbulent flow show that the method achieves high particle and vector detection efficiency, up to seeding densities of around 0.08 particles per pixel (ppp), while its root-mean-square error of velocity estimation is lower to that of state-of-the-art similar methods. Results from an experimental campaign on a transitional round air jet at Reynolds number 4600 are also presented. During the tests, seeding density varies from 0.06 to 0.03 ppp on average. Associated to an outlier rejection scheme based on temporal statistics, DF-TPTV vector fields truthfully correspond to the instantaneous jet dynamics. Quantitative performance assessment is provided by introducing statistics performed by bin averaging, upon assuming statistical axisymmetry of the jet. Mean and fluctuating axial velocity components in the jet near-field are compared with reference results obtained from planar PIV at higher seeding density., Comment: 15 pages. Submitted to Experiments in Fluids. P. Cornic and B. Leclaire are co-first authors

Super-resolution (SR) techniques make use of subpixel shifts between frames in an image sequence to yield higher-resolution images. We propose an original observation model devoted to the case of non isometric inter-frame motion as required, for instance, in the context of airborne imaging sensors. First, we describe how the main observation models used in the SR literature deal with motion, and we explain why they are not suited for non isometric motion. Then, we propose an extension of the observation model by Elad and Feuer adapted to affine motion. This model is based on a decomposition of affine transforms into successive shear transforms, each one efficiently implemented by row-by-row or column-by-column 1-D affine transforms. We demonstrate on synthetic and real sequences that our observation model incorporated in a SR reconstruction technique leads to better results in the case of variable scale motions and it provides equivalent results in the case of isometric motions.

Current optical interferometers are affected by unknown turbulent phases on each telescope. In the field of radio-interferometry, the self-calibration technique is a powerful tool to process interferometric data with missing phase information. This paper intends to revisit the application of self-calibration to Optical Long Baseline Interferometry (OLBI). We cast rigorously the OLBI data processing problem into the self-calibration framework and demonstrate the efficiency of the method on real astronomical OLBI dataset.

This paper is an H band interferometric examination of Arcturus, a star frequently used as a spatial and spectral calibrator. Using the IOTA 3 telescope interferometer, we performed spectro-interferometric observation (R~35) of Arcturus. Atmospheric models and prescriptions were fitted to the data to derive the brightness distribution of the photosphere. Image reconstruction was also obtained using two software algorithms: Wisard and Mira. An achromatic power law proved to be a good model of the brightness distribution, with a limb darkening compatible with the one derived from atmospheric model simulations using our Marcs model. A Rosseland diameter of 21.05+/-0.21 was derived, corresponding to an effective temperature of T_eff=4295+/-26 K. No companion was detected from the closure phases, with an upper limit on the brightness ratio of 8e-4 at 1AU. Dynamic range at such distance from the photosphere was established at 1.5e-4 (1sigma rms). An upper limit of 1.7e-3 was also derived for the level of brightness asymmetries present on the photosphere., Comment: 12 pages, 12 figures, accepted in A&A