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.
In this paper, we address the problem of inpainting in 3D digital models with large holes. The missing region inference problem is solved with a dictionary learning-based method that harnesses a geometric prior derived from a single self-similar structure and online depth databases. The underlying surface is recovered by adaptively propagating local 3D surface smoothness from around the boundary of...
Touchless hand gesture recognition systems are becoming important in automotive user interfaces as they improve safety and comfort. Various computer vision algorithms have employed color and depth cameras for hand gesture recognition, but robust classification of gestures from different subjects performed under widely varying lighting conditions is still challenging. We propose an algorithm for drivers'...
This paper tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other state-of-the-art solutions we factorize 2D observations in camera parameters, base poses and mixing coefficients. Existing methods require sufficient camera motion during the sequence to achieve a correct 3D reconstruction. To obtain convincing 3D reconstructions...
The color appearance of an object can vary widely as a function of camera sensitivity and ambient illumination. In this paper, we discuss a methodology for seamless interfacing across imaging sensors and under varying illumination conditions for two very relevant problems in aerial imaging, namely, change detection and mosaicing. The proposed approach works by estimating surface reflectance which...
Action recognition is a fundamental problem in computer vision. However, all the current approaches pose the problem in a multi-class setting, where each actor is modeled as performing a single action at a time. In this work we pose the action recognition as a multi-label problem, i.e., an actor can be performing any plausible subset of actions. Determining which subsets of labels can co-occur is...
Recent technical advances in Unmanned Aerial Vehicles (UAV) made a realm of applications possible. In this paper we focus on the application of following a walking pedestrian in real-time, using optimised pedestrian detection and object tracking. For this we use an on-board embedded system, offering an optimal ratio of computational power and weight. We extend the commonly used ground plane estimation...
A solution to long distance outdoor face recognition is presented in this work. The proposed method, called the Two-Stage Alignment/Enhancement Filtering (TAEF) system, consists of three main components: a cross-distance face alignment technique, a cross-environment face enhancement technique, and a two-stage filtering system. Given a probe image, the procedure of face alignment, enhancement and matching...
Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on external examples with proper data augmentations. It is then fine-tuned with multi-scale self examples from each input, where...
The subject of this paper is the visual object tracking in infrared (IR) videos. Our contribution is twofold. First, the performance behaviour of the state-of-the-art trackers is investigated via a comparative study using IR-visible band video conjugates, i.e., video pairs captured observing the same scene simultaneously, to identify the IR specific challenges. Second, we propose a novel ensemble...
Following previous series on Looking at People (LAP) challenges [6, 5, 4], ChaLearn ran two competitions to be presented at CVPR 2015: action/interaction spotting and cultural event recognition in RGB data. We ran a second round on human activity recognition on RGB data sequences. In terms of cultural event recognition, tens of categories have to be recognized. This involves scene understanding and...
Most state-of-the-art solutions for localizing facial feature landmarks build on the recent success of the cascaded regression framework [7, 15, 34], which progressively predicts the shape update based on the previous shape estimate and its feature calculation.
Traditionally, land-cover mapping from remote sensing images is performed by classifying each atomic region in the image in isolation and by enforcing simple smoothing priors via random fields models as two independent steps. In this paper, we propose to model the segmentation problem by a discriminatively trained Conditional Random Field (CRF). To this end, we employ Structured Support Vector Machines...
In this paper, we study the problem of reproducing the light from a single image of an object covered with random specular microfacets on the surface. We show that such reflectors can be interpreted as a randomized mapping from the lighting to the image. Such specular objects have very different optical properties from both diffuse surfaces and smooth specular objects like metals, so we design a special...
Object class detection has been a synonym for 2D bounding box localization for the longest time, fueled by the success of powerful statistical learning techniques, combined with robust image representations. Only recently, there has been a growing interest in revisiting the promise of computer vision from the early days: to precisely delineate the contents of a visual scene, object by object, in 3D...
Skin appearance modeling using high resolution photography has led to advances in recognition, rendering and analysis. Computational appearance provides an exciting new opportunity for integrating macroscopic imaging and microscopic biology. Recent studies indicate that skin appearance is dependent on the unseen distribution of microbes on the skin surface, i.e. the skin microbiome. While modern sequencing...
This paper proposes to enhance low resolution dynamic depth videos containing freely non-rigidly moving objects with a new dynamic multi-frame super-resolution algorithm. Existent methods are either limited to rigid objects, or restricted to global lateral motions discarding radial displacements. We address these shortcomings by accounting for non-rigid displacements in 3D. In addition to 2D optical...
We present a fast and accurate 3D hand tracking method which relies on RGB-D data. The method follows a model based approach using a hierarchical particle filter variant to track the model's state. The filter estimates the probability density function of the state's posterior. As such, it has increased robustness to observation noise and compares favourably to existing methods that can be trapped...
Visual sensing, such as vision based localization, navigation, tracking, are crucial for intelligent robots, which have shown great advantage in many robotic applications. However, the market is still in lack of a powerful visual sensing platform to deal with most of the visual processing tasks. In this paper we introduce a powerful and efficient platform, Guidance, which is composed of one processor...
The pupillary response has been used to measure mental workload because of its sensitivity to stimuli and high resolution. The goal of this study was to diagnose the cognitive effort involved with a task that was presented visually. A multinomial processing tree (MPT) was used as an analytical tool in order to disentangle and predict separate cognitive processes, with the resulting output being a...
We describe a method to model perspective distortion as a one-parameter family of warping functions. This can be used to mitigate its effects on face recognition, or synthesis to manipulate the perceived characteristics of a face. The warps are learned from a novel dataset and, by comparing one-parameter families of images, instead of images themselves, we show the effects on face recognition, which...
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.