Emile Hendriks

• dr
• Managing Director at Delft University of Technology

In this paper, we propose a novel method to estimate the confidence of a registration that does not require any ground truth, is independent from the registration algorithm and the resulting confidence is correlated with the amount of registration error. We first apply a local search to match patterns between the registered image pairs. Local searc...

In most stereo-matching algorithms, stereo similarity measures are used to determine which image patches in a left-right image pair correspond to each other. Different similarity measures may behave very differently on different kinds of image structures, for instance, some may be more robust to noise whilst others are more susceptible to small tex...

Depth sensors such as Kinect fail to find the depth of transparent objects which makes 3D reconstruction of such objects a challenge. The refinement algorithms for Kinect depth maps either do not address transparency or they only provide sparse depth on such objects which is inadequate for dense 3D reconstruction. In order to solve this problem, we...

Stereo confidence measures are one of the most popular research topics in stereo vision. These measures give an indication about the certainty of the matching. The main aim of using confidence measures is to filter the erroneous disparity estimations at the end of the matching process. However, they can also be incorporated at the initial step of t...

Scanline optimization (SO) is one of the fundamental refinement approaches in stereo matching. SO is incorporated to smooth final disparity estimations by using energy minimization over local patches. The main drawback of SO approaches is their constant energy penalties. The constant penalties may smooth the wrong disparity estimations as well as t...

We propose a snowing model to iteratively smoothe the various image noises while preserving the important image structures such as edges and lines. Considering the gray image as a digital terrain model, we develop an adaptive weighted least squares support vector machine (LS-SVM) to iteratively estimate the optimal gray surface underlying the noisy...

The Microsoft Kinect depth sensor provides depth maps of indoor environments with unknown depth gaps because of infrared (IR) reflectance properties of the objects inside the scene and occlusion. In this paper, we propose a grid-based hierarchical learning algorithm for predicting the depth values of the gaps inside the Kinect's depth map. The scen...

Proper sensor placement is crucial for maximizing the usability of large-scale sensor networks. Specially, the total sensible area covered by a sensor network can be maximized if we optimally arrange all sensors. To address this coverage optimization problem, this paper studies a typical sensor network—camera network. In this network, both location...

The Microsoft Kinect enables real time 3D reconstruction of an indoor environment with low computational power by producing depth measurements with high resolution. Yet, the measured depth images are not in perfect quality because of the reflectance properties of the objects inside the scene. In this paper, we propose a novel depth prediction algor...

State-of-the-art stereo matching algorithms estimate disparities using local block-matching, and subsequently refine the disparity estimates by introducing smoothness constraints and performing global energy minimization. Such algorithms are hampered by the inability of local block-matching algorithms to deal with repetitive patterns. This paper pr...

Simultaneously tracking poses of multiple people is a difficult problem because of inter-person occlusions and self occlusions. This paper presents an approach that circumvents this problem by performing tracking based on observations from multiple wide-baseline cameras. The proposed global occlusion estimation approach can deal with severe inter-p...

For multi atlas-based segmentation approaches, a segmentation fusion scheme which considers local performance measures may be more accurate than a method which uses a global performance measure. We improve upon an existing segmentation fusion method called SIMPLE and extend it to be localized and suitable for multi-labeled segmentations. We demonst...

Fluorescence loss in photobleaching (FLIP) is a method to study compartment connectivity in living cells. A FLIP sequence is obtained by alternatively bleaching a spot in a cell and acquiring an image of the complete cell. Connectivity is estimated by comparing fluorescence signal attenuation in different cell parts. The measurements of the fluores...

In this paper, we propose a novel area-based algorithm for stereo correspondence estimation. The new dense correspondence estimation algorithm, which we call HACM (Hierarchical Adaptive Curve Matching), is suitable for stereo analysis of both static and dynamic scenes. The core of this method is the derivation of a pixel-based dense adaptive curve...

In this paper, we investigate to what extent modern computer vision and machine learning techniques can assist social psychology research by automatically recognizing facial expressions. To this end, we develop a system that automatically recognizes the action units defined in the facial action coding system (FACS). The system uses a sophisticated...

This paper discusses a number of image analysis challenges emerging from longitudinal small animal molecular imaging studies. Three steps towards a quantitative 3D analysis of follow-up small animal imaging are presented: whole-body articulated registration, change visualization in follow-up data and fusion of optical and 3D structural imaging data...

We evaluate the performance of different key-point detectors and region descriptors when used for automatic classification of small sea targets in infrared video. In our earlier research performed on this subject as well as in other literature, many different region descriptors have been proposed. However, it is unclear which methods are most appli...

Human perception of sign language can serve as inspiration for the improvement of automatic recognition systems. Experiments with human signers show that sign language signs contain redundancy over time. In this article, experiments are conducted to investigate whether comparable redundancies also exist for an automatic sign language recognition sy...

Object detection is a critical step in automated surveillance. A common approach to building object detectors involves statistical learning techniques using as input large annotated data sets. However, due to inevitable limitations of a typical training data set, this supervised approach is unsuitable for building a generic surveillance system appl...

This paper studies how to improve the field of view (FOV) coverage of a camera network. We focus on a special but practical scenario where the cameras are randomly scattered in a wide area and each camera may adjust its orientation but cannot move in any direction. We propose a particle swarm optimization (PSO) algorithm which can efficiently find...

Derivation of diagnostically relevant parameters from first-pass myocardial perfusion magnetic resonance images involves the tedious and time-consuming manual segmentation of the myocardium in a large number of images. To reduce the manual interaction and expedite the perfusion analysis, we propose an automatic registration and segmentation method...

In this paper, we describe a system that performs online transformation estimation between pre-calibrated stereo cameras. This allows the stereo cameras to be moved around and automatically re-calibrated without the use of a calibration object. This also allows the set-up to recover from accidental nudges that invalidate the extrinsic (external to...

The classification of sequences requires the combination of information from different time points. In this paper the detection of facial expressions is considered. Experiments on the detection of certain facial muscle activations in videos show that it is not always required to model the sequences fully, but that the presence of specific frames (t...

The paper presents an extension of active appearance models (AAMs) that is better capable of dealing with the large variation in face appearance that is encountered in large multi-person face data sets. Instead of the traditional PCA-based texture model, our extended AAM employs a mixture of probabilistic PCA to describe texture variation, leading...

Automated landmark detection may facilitate the examination and automatic analysis of three-dimensional (3D) echocardiograms. By detecting 3D anatomical landmark points, the standard anatomical views can be extracted automatically, for better standardized visualization. Furthermore, the landmarks can serve as an initialization for other analysis me...

In this paper we present a combined probability estimation approach to detect and track multiple people for pose estimation at the same time. It can deal with partial and total occlusion between persons by adding torso appearance to the tracker. Moreover, the upper body of each individual is further segmented into head, torso, upper arm and lower a...

In sign language studies, it is generally assumed that a sign can be divided into several phases in time (preparation, stroke, and retraction) and that the stroke contains all of the necessary information. However, this has not been tested empirically. In order to learn where the information truly resides, we present an experiment that investigate...

Under the support vector machine framework, the support value analysis-based image fusion has been studied, where the salient features of the original images are represented by their support values. The support value transform (SVT)-based image fusion approach have demonstrated some advantages over the existing methods in multisource image fusion....

Object detection is an essential component in automated vision-based surveillance systems. In general, object detectors are constructed using training examples obtained from large annotated data sets. The inevitable limitations of typical training data sets make such supervised methods unsuitable for building generic surveillance systems applicable...

We present the results of an experiment on lexical recognition of human sign language signs in which the available perceptual information about handshape and hand orientation was manipulated. Stimuli were videos of signs from Sign Language of the Netherlands (SLN). The videos were processed to create four conditions: (1) one in which neither handsh...

To recover an everywhere-in-focus image, the multi-scale analysis image fusion is a classical method. Within these multi-resolution decompositions, the salient feature components image sequences with the largest magnitude are selected at each pixel location and finally, the fused image can be recovered from the decomposed components image sequences...

In this paper, we present an approach to capture markerless human motion and recognize human poses. Different body parts such as the torso and the hands are segmented from the whole body and tracked over time. A 2D model is used for the torso detection and tracking, while a skin color model is utilized for the hands tracking. Moreover, 3D location...

In this paper we present a framework for the rendering of scenes for 3DTV applications. The goal of our work is to investigate ways to generate virtual views of a scene captured using a relatively small number of real cameras. The approach adopted uses per-pixel operations and therefore is suitable for fast parallel implementation. A depth map is i...

Pollen is a major cause of allergy and monitoring pollen in the air is relevant for diagnostic purposes, development of pollen forecasts, and for biomedical and biological researches. Since counting airborne pollen is a time-consuming task and requires specialized personnel, an automated pollen counting system is desirable. In this article, we pres...

Object detection is a critical step in automated surveillance. A common approach to constructing object detectors consists of annotating large datasets and using them to train the detectors. However, due to inevitable limitations of a typical training data set, such supervised approach is unsuitable for building generic surveillance systems applica...

Research on automatic sign language recognition (ASLR) has mostly been conducted from a machine learning perspective. We propose to implement results from human sign recognition studies in ASLR. In a previous study it was found that handshape is important for human sign recognition. The current paper describes the implementation of this conclusion:...

Current automatic sign language recognition (ASLR) seldom uses perceptual knowledge about the recognition of sign language. Using such knowledge can improve ASLR because it can give an indication which elements or phases of a sign are important for its meaning. Also, the current generation of data-driven ASLR methods has shortcomings which may not...

To recognize speech, handwriting or sign language, many hybrid approaches have been proposed that combine Dynamic Time Warping (DTW) or Hidden Markov Models (HMM) with discriminative classifiers. However, all methods rely directly on the likelihood models of DTW/HMM. We hypothesize that time warping and classification should be separated because of...

We present a method to automatically construct a sign language classifier for a previously unseen sign. The only required input of a new sign is one example, performed by a sign language tutor. The method works by comparing the measurements of the new sign to signs that have been trained on a large number of persons. The parameters of the respectiv...

In this study we compare human and machine acceptability judgments for extreme variations in sign productions. We gathered acceptability judgments of 26 signers and scores of three different automatic gesture recognition (AGR) algorithms that could potentially be used for automatic acceptability judgments, in which case the correlation between huma...

We have developed a prototype for a learning environment for deaf and hard of hearing children. This demonstration consists of hands-on experience with the prototype. In total, there are three exercises: 1) an introduction of all pictures and corresponding signs, 2) multiple choice sign-to-picture and 3) performing the sign that corresponds to the...

One of the decisive steps in automated surveillance and monitoring is object detection. A standard approach to constructing object detectors consists of annotating large data sets and using them to train a detector. Nevertheless, due to unavoidable constraints of a typical training data set, supervised approaches are inappropriate for building gene...

Object detection is a critical step in automating the monitoring and surveillance tasks. To maximize its reliability, robust algorithms are needed to separate real objects from moving shadows. In this paper we propose a framework for detecting moving shadows caused by moving objects in video, which first learns autonomously and on-line the characte...

This work investigates knowledge driven segmentation of cardiac MR perfusion sequences. We build upon previous work on multi-band AAMs to integrate into the segmentation both spatial priors about myocardial shape as well as temporal priors about characteristic perfusion patterns. Different temporal and spatial features are developed without a stric...

To quantify osteoarthritis (OA) by automatic measurement of the joint space width (JSW) in the finger joints in hand radiographs, and validate this against semi-quantitative scoring. Forty subjects with primary OA at multiple sites were selected, 20 of which had no joint space narrowing (JSN) in the hand, and 20 had moderate to severe JSN. Conventi...

Object detection is a crucial step in automating monitoring and surveillance. A classical approach to object detection employs supervised learning methods, which are effective in well-defined narrow application scopes. In this paper we propose a framework for detecting moving objects in video, which first learns autonomously and on-line the charact...

A 3D visual hand gesture recognition method is proposed that detects correctly performed signs from stereo camera input. Hand tracking is based on skin detection with an adaptive chrominance model to get high accuracy. Informative high level motion properties are extracted to simplify the classification task. Each example is mapped onto a fixed ref...

This paper addresses the problem of deriving measures that express the degree of the reliability of motion vectors estimated by a block-matching motion estimation method. We express the block matching motion estimation scheme in the probabilistic framework as a maximum-likelihood estimation scheme. Subsequently, we derive the confidence measures in...

In this paper, we present a person independent 3D system for judging the correctness of a sign. The system is camera-based, using computer vision techniques to track the hand and extract features. 3D co-ordinates of the hands and other features are calculated from stereo images. The features are then modeled statistically and automatic feature sele...

Contrast-enhanced CT Angiography has become an accepted diagnostic tool for detecting Pulmonary Embolism (PE). The CT obstruction index proposed by Qanadli, which is based on the number of obstructed arterial segments, enables the quantification of PE severity. Because the required manual identification of twenty arterial segments is time consuming...

In case of the absence of a calibration procedure, or when there exists a color difference between direct and ambient light, standard chrominance models are not completely brightness invariant. Therefore, they cannot provide the best space for robust color modeling. Instead of using a fixed chrominance model, our method estimates the actual depende...

We present an algorithm for Dynamic Time Warp-ing (DTW) on multi-dimensional time series (MD-DTW). The algorithm utilises all dimensions to find the best synchronisation. It is compared to ordi-nary DTW, where a single dimension is used for aligning the series. Both one-dimensional and multi-dimensional DTW are also tested when derivatives instead...

Quantification of airborne pollen is an important tool in scientific research and patient care in allergy. The currently available method relies on microscopic examination of pollen slides, performed by qualified researchers. Although highly reliable, the method is labor intensive and requires extensive training of the researchers involved. In an a...

Estimating the number of persons in a public place provides useful information for video-based surveillance and monitoring applications. In the case of oblique camera setup, counting is either achieved by detecting individuals or by statistically establishing relations between values of simple image features (e.g. amount of moving pixels, edge dens...

Many real-time image processing applications are con- fronted with performance limitations when implemented in software. The skin segmentation algorithm utilized in hand gesture recognition as developed by the ICT department of Delft University of Technology presents an example of such an application. This paper presents the design of an FPGA based...

This paper describes a non-intrusive method to estimate the gaze direction of a person by using stereo cameras. First, facial features are tracked with an adapted particle filtering algorithm using factorized likelihoods to estimate the 3D head pose. Next the 3D gaze vector is calculated by estimating the eyeball center and the cornea center of bot...

We present new techniques for passive ranging with a dual-band IR search and track (IRST) sensor aboard a ship. Three distance estimation methods are described: the atmospheric propagation model, the apparent surface of the target, and target motion analysis (TMA). These methods are tested on the sensor output of real data during cold water trials...

This paper describes the recognition of isolated Dutch sign language signs. Data is gathered with one digital camera. Head and hands are tracked, and the values are categorised to produce a linguistically inspired feature vector. With this feature vector, classification is performed. We build left-to-right Markov chain models without skips or loops...

This chapter presents an extensive overview of passive camera calibration techniques. Starting with a detailed introduction and mathematical description of the imaging process of an off-the-shelf camera, it reviews all existing passive calibration approaches with increasing complexity. All algorithms are presented in detail so that they are directl...

Usually, object detection is performed directly on (normalized) gray values or gray primitives like gradients or Haar-like features. In that case the learning of relationships between gray primitives, that describe the structure of the object, is the complete responsibility of the classifier. We propose to apply more knowledge about the image struc...

This paper describes a method for automatic contour detection in long-axis cardiac MRI using an adaptive virtual exploring robot. The robot is a simulated trained virtual autonomous tri-cycle that is initially positioned in a binary representation of the left ventricle (LV) and finds the contours during navigation through the ventricle. The method...

Our aim is to insert depth information into an existing 2D video sequence to provide content for 3D-TV applications, which we try to achieve through segmentation of the objects in the given 2D video sequence. To this effect, we present a method for temporal stabilization of video object segmentation algorithms for 3D-TV applications. First, two qua...

Analysis of CT datasets is commonly time consuming because of the required manual interaction. We present a novel and fast automatic initialization algorithm to detect the carotid arteries providing a fully automated approach of the segmentation and centerline detection. First, the volume of interest (VOI) is estimated using a shoulder landmark. Th...

We present a method for improving the temporal stability of video object segmentation algorithms for 3D-TV applications. First, two quantitative measures to evaluate temporal stability without ground-truth are presented. Then, a pseudo-3D curve evolution method, which spatio-temporally stabilizes the estimated object segments is introduced. Tempora...

Since the introduction of particle filtering for object tracking, a lot of improvements have been suggested. However, the definition of the observation likelihood function, needed for determining the particle weights, has received little attention. Because particle weights determine how the particles are re-sampled, the likelihood function has a st...

We explore the energy dissipation of the Linear Processor Array (LPA) as a function of the number of available resources (Processor Units P) within the array. This number P is an important parameter, as it reflects performance, relates parallel processing to energy dissipation, and influences the scaling of the various parts of the LPA architecture...

In this paper, we describe the view representation and reconstruction module for an image-based telepresence system, based on a viewpoint-adaptation scheme and the image-based rendering technique. For real-time three-dimensional synthesis, a parallel version of our multistep view reconstruction algorithm is realized on dedicated hardware based on T...

This chapter presents an extensive overview of passive camera calibration techniques. Starting with a detailed introduction and mathematical description of the imaging process of an off-the-shelf camera, it reviews all existing passive calibration approaches with increasing complexity. All algorithms are presented in detail so that they are directl...

The manual verification of a radiotherapy treatment, where a portal image is matched onto a planning image, is very time consuming and subject to inter- and intraobserver variability. Therefore, a fully automatic matching procedure (image registration) is required. Existing automatic matching algorithms are confounded, however, by irrelevant inform...

This paper describes a robust eye tracking algorithm designed for complex indoor situations. A well known method often used for eye detection is to use a structured infrared lighting scheme which exploits the bright and dark pupil effect. Although methods based on this principle are very robust, they usually fail as a cause of rapid head movement o...

In this paper we propose a semi-automatic method for general object-based segmentation of image sequences. A label field is initialized by the user in the first frame of the sequence and then it is automatically tracked for the rest of the frames based on the color and motion properties of the various objects in the scene. We propose a novel statis...

This work[9] aims at determining dense motion and disparity fields given a stereoscopic sequence of images for the construction of stereo interpolated images. Ateach time instant the two dense motion fields, for the left and the right sequences, and the disparity field of the next stereoscopic pair are jointly estimated. The disparity field of the...

This work aims at determining dense motion and disparity fields given a stereoscopic sequence of images for the construction of stereo interpolatedimages.Ateach time instant the two dense motion fields, for the left and the right sequences, and the disparity field of the next stereoscopic pair are jointly estimated. The disparity field of the curre...

We propose a real-time multi-step view reconstruction algorithm and we tune its implementation to a virtual teleconference application. Theoretical motivations and practical implementation issues of the algorithm are detailed. The proposed algorithm can be used to reconstruct novel views at arbitrary poses (position and orientation) in a way that i...

We propose a real-time multi-step view reconstruction algorithm and we tune its implementation to a virtual teleconference application. Theoretical motivations and practical implementation issues of the algorithm are detailed. The proposed algorithm can be used to reconstruct novel views at arbitrary poses (position and orientation) in a way that i...

Selection of the best set of scales is problematic when developing signal driven approaches for pixel-based image segmentation. Often, different possibly conflicting criteria need to be fulfilled in order to obtain the best tradeoff between uncertainty (variance) and location accuracy. The optimal set of scales depends on several factors: the noise...

We design a new scheme for the accurate localization of markers in images of calibration plates. This forms the basis of so-called fixed or strong camera calibration methods. We focus on the most widely used plates with circular markers arranged in a regular grid. Our algorithm is fully automatic and very robust. We assess its results by using synt...

This paper addresses the problem of deriving measures that express the degree of the reliability of motion vectors estimated by a block matching motion estimation method. We express the block matching motion estimation scheme in the probabilistic framework and derive the confidence measures in terms of the a-posteriori probabilities of the estimate...

Not Available

An integrated media system is a computer-based environment that supports the creation, sharing, distribution and effective communication of multimodal information across the boundaries of space and time. The EU Information Societies Technology (IST) project — VIRTUE (Virtual Team User Environment) is working steadily towards the realisation of most...

This paper addresses the problem of spatio-temporal segmentation of video sequences. An initial intensity segmentation method (watershed segmentation) provides a number of initial segments which are subsequently labeled, with a known number of labels, according to motion information. The label field is modeled as a Markov random field where the sta...

Virtual view synthesis is essential for 3D teleconference systems like VIRTUE, which utilizes the motion parallax cue. In this paper we propose a multi-step view synthesis algorithm to efficiently reconstruct an arbitrary view in real time and utilize all the information we have from stereo cameras. We show that the newly proposed algorithm can be...

In this paper we propose a middle view stereo representation (MVSR) to efficiently utilize the bandwidth and ease the implementation of a view-adaptive teleconference system. We show that the MVSR can be used to reconstruct a high quality view from an arbitrary pose, using occlusion information. Its modular property makes real-time implementation f...

Traditional definitions of edges and corners are limited in the sense that they restrict their application. In this paper we generalize the concepts of edges and corners to 1D features and 2D features, respectively. The phase congruency theory is chosen as a mathematical system to model the generalized concepts. The basics of the phase congruency t...

We propose a generic algorithm for the geometrically correct reconstruction of 3-D scenes on stereo displays with viewpoint adaptation. This forms the basis of multiviewpoint systems, which are currently the most promising candidates for real-time implementations of 3-D visual communication systems. The reconstruction algorithm needs 3-D tracking o...

For the purpose of automating a clinical diagnostic apparatus to quantify the deformability of human red blood cells, we present an automated image analysis procedure for on-line detection of the cell shape based upon the method of parametric deformable templates.