The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple scales. However, the performance gain of such ad hoc architectures is usually limited to pay off the computational cost. In this work, we address the small object detection...
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a...
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal. While these learning-based methods are significantly more effective in capturing high-level features than prior techniques, they can only handle very low-resolution inputs...
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. Using a novel, multi-scale training method the same YOLOv2 model can run...
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate...
Most of the conventional face hallucination methods assume the input image is sufficiently large and aligned, and all require the input image to be noise-free. Their performance degrades drastically if the input image is tiny, unaligned, and contaminated by noise. In this paper, we introduce a novel transformative discriminative autoencoder to 8X super-resolve unaligned noisy and tiny (16X16) low-resolution...
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent...
Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. [37] showed one interesting way to synthesize novel images by performing gradient ascent in the latent space of a generator network to maximize the activations of one or multiple neurons in a separate classifier network. In this paper we extend this method by introducing an...
Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning. While most recognition approaches aim to be scale-invariant, the cues for recognizing a 3px tall face are fundamentally...
Deep convolutional neural networks (CNN) have recently been shown to generate promising results for aesthetics assessment. However, the performance of these deep CNN methods is often compromised by the constraint that the neural network only takes the fixed-size input. To accommodate this requirement, input images need to be transformed via cropping, warping, or padding, which often alter image composition,...
Magnetic Resonance Imaging (MRI) offers high-resolution in vivo imaging and rich functional and anatomical multimodality tissue contrast. In practice, however, there are challenges associated with considerations of scanning costs, patient comfort, and scanning time that constrain how much data can be acquired in clinical or research studies. In this paper, we explore the possibility of generating...
Semantic segmentation for remote sensing images is a critical process in the workflow of object-based image analysis. Recently, convolutional neural networks(CNNs) are powerful visual models that yield hierarchies of features. In this paper, we propose a deep convolutional encoder-decoder model for remote sensing images segmentation. Specifically, we rely on the encoder network to extract the high-level...
The present paper introduces an extension of attribute profiles (APs) by extracting their local features. The so-called local feature-based attribute profiles (LFAPs) are expected to provide a better characterization of each APs' filtered pixel (i.e. APs' sample) within its neighborhood, hence better deal with local texture information from the image's content. In this work, LFAP is constructed by...
Speckle removal from single-channel and multi-dimensional SAR remains a difficult problem. In this paper, we are investigating the use of a Convolutional Neural Network (CNN), previously applied to the Super-Resolution problem, for speckle removal. Because speckle noise statistics is signal dependent, we are training the neural network on the residual image formed by the ratio of the observed intensity...
The classification procedure to identify remote sensing signatures from a particular geographical region can be achieved using an accurate identification model that is based on multispectral data and uses pixel statistics for the class description. This methodology is referred to as the Multispectral Identification Model. This paper presents this particular methodology applied to large remote sensing...
An improved super-resolution image reconstruction algorithm based on dictionary-learning is studied for the time-consuming algorithms in the existing dictionary training process. In this paper, the reconstruction of image super resolution is realized from the compressed sensing theory. The image patches are conveyed by sparse linear representations with an over-complete dictionary. In the process...
Using monthly as well as annual statistics, we investigate the potentials of synergetic utilization of multispectral and C-band SAR data for the classification of a study site in the central Brazilian state of Mato Grosso. We aim at the classification of five tropical land cover classes (primary forests, secondary vegetation, pasture, agricultural, water), and highlight the potentials of standalone...
We aim to jointly estimate height and semantically label monocular aerial images. These two tasks are traditionally addressed separately in remote sensing, despite their strong correlation. Therefore, a model learning both height and classes jointly seems advantageous and so, we propose a multitask Convolutional Neural Network (CNN) architecture with two losses: one performing semantic labeling, and...
One significant advantage of the deep convolutional neural networks (DCNN) is their representational ability for local complex structures. Inspired by this observation, a DCNN based residual learning model is proposed to learn a nonlinear mapping function between the high-resolution (HR) and low-resolution (LR) image patches. The DCNN is trained based on image patches, which are only sampled from...
Increasing population, rapid urbanization, quest for biofuels, pollution, diseases, and adverse climate changes are some of the major drivers behind the changing surface of our planet. Timely monitoring and assessment of these changes, along with dissemination of accurate information, is important for policy makers, city planners, and humanitarian relief workers. Advances in remote sensing technologies...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.