Ralph Braspenning - Academia.edu (original) (raw)

Papers by Ralph Braspenning

Complexity scalable algorithms are capable of trading resource usage for output quality in a near... more Complexity scalable algorithms are capable of trading resource usage for output quality in a near-optimal way. We present a complexity scalable motion estimation algorithm based on the 3-D recursive search block matcher. We introduce data prioritizing as a new approach to scalability. With this approach, we achieve a near-constant complexity and a continuous quality-resource distribution. While maintaining acceptable quality, it

The picture quality of prototype 3D TVs based on lenticular displays is currently not at the leve... more The picture quality of prototype 3D TVs based on lenticular displays is currently not at the level of regular 2D displays. The frequency reproduction properties of such a 3D display are analyzed and an experiment is presented to validate the conclusions. Furthermore, we show options, like crosstalk reduction, based on the new knowledge to improve the pic-ture quality.

Recent efforts in defining ambient intelligence applications based on user-centric concepts, the ... more Recent efforts in defining ambient intelligence applications based on user-centric concepts, the advent of technology in different sensing modalities as well as the expanding interest in multimodal information fusion and situation-aware and dynamic vision processing algorithms have created a common motivation across different research disciplines to utilize context as a key enabler of application-oriented vision systems design. Improved robustness, efficient use of sensing and computing resources, dynamic task assignment to different operating modules as well as adaptation to event and user behavior models are among the benefits a vision processing system can gain through the utilization of contextual information. The Workshop on Use of Context in Vision Processing (UCVP) aims to address the opportunities in incorporating contextual information in algorithm design for single or multi-camera vision systems, as well as systems in which vision is complemented with other sensing modalit...

We present a motion estimation algorithm designed to fully exploit the flexibility offered by pro... more We present a motion estimation algorithm designed to fully exploit the flexibility offered by programmable platforms. This algorithm adapts its resolution to the image content using the highest spatial accuracy only for those parts of the image where it is required, i.e. near the borders of moving objects.

Many approaches to facial expression recognition focus on assessing the six basic emotions (anger... more Many approaches to facial expression recognition focus on assessing the six basic emotions (anger, disgust, happiness, fear, sadness, and surprise). Real-life situations proved to produce many more subtle facial expressions. A reliable way of analyzing the facial behavior is the Facial Action Coding System (FACS) developed by Ekman and Friesen, which decomposes the face into 46 action units (AU) and is usually performed by a human observer. Each AU is related to the contraction of one or more specific facial muscles. In this study we present an approach towards automatic AU recognition enabling recognition of an extensive palette of facial expressions. As distinctive features we used motion flow estimators between every two consecutive frames, calculated in special regions of interest (ROI). Even though a lot has been published on the facial expression recognition theme, it is still difficult to draw a conclusion regarding the best methodology as there is no common basis for compari...

Visual Communications and Image Processing 2007, 2007

Philips provides autostereoscopic three-dimensional display systems that will bring the next leap... more Philips provides autostereoscopic three-dimensional display systems that will bring the next leap in visual experience, adding true depth to video systems. We identified three challenges specifically for 3D image processing: 1) bandwidth and complexity of 3D images, 2) conversion of 2D to 3D content, and 3) object-based image/depth processing. We discuss these challenges and our solutions via several examples. In

Visual Communications and Image Processing 2004, 2004

ABSTRACT We present a method for true-motion estimation assisted by feature point correspondences... more ABSTRACT We present a method for true-motion estimation assisted by feature point correspondences. First the difference between true-motion estimation and motion estimation for coding applications is explained, and an earlier published efficient true-motion estimation algorithm, called 3DRS, is summarized. Then the convergence property of this algorithm is discussed. We present a method for improving the convergence, by using feature point correspondences and show that a significant quality increase can be obtained for sequences containing high velocities.

Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001

ABSTRACT Since programmable platforms have a fixed number of resources, the number of algorithms ... more ABSTRACT Since programmable platforms have a fixed number of resources, the number of algorithms that can run in parallel is limited. We propose to overcome this by introducing scalable algorithms that are capable of trading resource usage for output quality. We show the feasibility of this approach by means of an implementation example, namely scalable sharpness enhancement for video signals

2008 8th IEEE International Conference on Automatic Face & Gesture Recognition, 2008

In this paper, we extensively investigate local features based facial expression recognition with... more In this paper, we extensively investigate local features based facial expression recognition with face registration errors, which has never been addressed before. Our contributions are three fold. Firstly, we propose and experimentally study the Histogram of Oriented Gradients (HOG) descriptors for facial representation. Secondly, we present facial representations based on Local Binary Patterns (LBP) and Local Ternary Patterns (LTP) extracted from overlapping local regions. Thirdly, we quantitatively study the impact of face registration errors on facial expression recognition using different facial representations. Overall LBP with overlapping gives the best performance (92.9% recognition rate on the Cohn-Kanade database), while maintaining a compact feature vector and best robustness against face registration errors.

Handbook of Ambient Intelligence and Smart Environments, 2010

Facial expressions, resulting from movements of the facial muscles, are the face changes in respo... more Facial expressions, resulting from movements of the facial muscles, are the face changes in response to a person's internal emotional states, intentions, or social communications. There is a considerable history associated with the study on facial expressions. Darwin (1872) was the first to describe in details the specific facial expressions associated with emotions in animals and humans, who argued that all mammals show emotions reliably in their faces. Since that, facial expression analysis has been a area of great research interest for behavioral scientists . Psychological studies suggest that facial expressions, as the main mode for non-verbal communication, play a vital role in human face-to-face communication. For illustration, we show some examples of facial expressions in .

Visual Communications and Image Processing 2002, 2002

ABSTRACT Complexity scalable algorithms are capable of trading resource usage for output quality ... more ABSTRACT Complexity scalable algorithms are capable of trading resource usage for output quality in a near-optimal way. We present a complexity scalable motion estimation algorithm based on the 3-D recursive search block matcher. We introduce data prioritizing as a new approach to scalability. With this approach, we achieve a near-constant complexity and a continuous quality-resource distribution. While maintaining acceptable quality, it is possible to vary the resource usage from below 1 match-error calculation per block on the average to more than 5 match-error calculations per block on the average.

2008 Second ACM/IEEE International Conference on Distributed Smart Cameras, 2008

In this paper we investigate improvements to the efficiency of human body detection using histogr... more In this paper we investigate improvements to the efficiency of human body detection using histograms of oriented gradients (HOG). We do this without compromising the performance significantly. This is especially relevant for embedded implementations in smart camera systems, where the onboard processing power and memory is limited. We focus on applications for indoor environments such as offices and living rooms. We present different experiments to reduce both the computational complexity as well as the memory requirements for the trained model. Since the HOG feature length is large, the total memory size needed for storing the model can become more than 50MB. We use a feature selection based on Bayesian theory to reduce the feature length. Additionally we compare the performance of the full-body detector with an upper-body only detector. For computational complexity reduction we employ a ROI-based approach.

Visual Communications and Image Processing 2003, 2003

ABSTRACT For various applications, such as data compression, structure from motion, medical imagi... more ABSTRACT For various applications, such as data compression, structure from motion, medical imaging and video enhancement, there is a need for an algorithm that divides video sequences into independently moving objects. Because our focus is on video enhancement and structure from motion for consumer electronics, we strive for a low complexity solution. For still images, several approaches exist based on colour, but these lack in both speed and segmentation quality. For instance, colour-based watershed algorithms produce a so-called oversegmentation with many segments covering each single physical object. Other colour segmentation approaches exist which somehow limit the number of segments to reduce this oversegmentation problem. However, this often results in inaccurate edges or even missed objects. Most likely, colour is an inherently insufficient cue for real world object segmentation, because real world objects can display complex combinations of colours. For video sequences, however, an additional cue is available, namely the motion of objects. When different objects in a scene have different motion, the motion cue alone is often enough to reliably distinguish objects from one another and the background. However, because of the lack of sufficient resolution of efficient motion estimators, like the 3DRS block matcher, the resulting segmentation is not at pixel resolution, but at block resolution. Existing pixel resolution motion estimators are more sensitive to noise, suffer more from aperture problems or have less correspondence to the true motion of objects when compared to block-based approaches or are too computationally expensive. From its tendency to oversegmentation it is apparent that colour segmentation is particularly effective near edges of homogeneously coloured areas. On the other hand, block-based true motion estimation is particularly effective in heterogeneous areas, because heterogeneous areas improve the chance a block is unique and thus decrease the chance of the wrong position producing a good match. Consequently, a number of methods exist which combine motion and colour segmentation. These methods use colour segmentation as a base for the motion segmentation and estimation or perform an independent colour segmentation in parallel which is in some way combined with the motion segmentation. The presented method uses both techniques to complement each other by first segmenting on motion cues and then refining the segmentation with colour. To our knowledge few methods exist which adopt this approach. One example is \cite{meshrefine}. This method uses an irregular mesh, which hinders its efficient implementation in consumer electronics devices. Furthermore, the method produces a foreground/background segmentation, while our applications call for the segmentation of multiple objects. NEW METHOD As mentioned above we start with motion segmentation and refine the edges of this segmentation with a pixel resolution colour segmentation method afterwards. There are several reasons for this approach: + Motion segmentation does not produce the oversegmentation which colour segmentation methods normally produce, because objects are more likely to have colour discontinuities than motion discontinuities. In this way, the colour segmentation only has to be done at the edges of segments, confining the colour segmentation to a smaller part of the image. In such a part, it is more likely that the colour of an object is homogeneous. + This approach restricts the computationally expensive pixel resolution colour segmentation to a subset of the image. Together with the very efficient 3DRS motion estimation algorithm, this helps to reduce the computational complexity. + The motion cue alone is often enough to reliably distinguish objects from one another and the background. To obtain the motion vector fields, a variant of the 3DRS block-based motion estimator which analyses three frames of input was used. The 3DRS motion estimator is known for its ability to estimate motion vectors which closely resemble the true motion. BLOCK-BASED MOTION SEGMENTATION As mentioned above we start with a block-resolution segmentation based on motion vectors. The presented method is inspired by the well-known KKK-means segmentation method \cite{K-means}. Several other methods (e.g. \cite{kmeansc}) adapt KKK-means for connectedness by adding a weighted shape-error. This adds the additional difficulty of finding the correct weights for the shape-parameters. Also, these methods often bias one particular pre-defined shape. The presented method, which we call KKK-regions, encourages connectedness because only blocks at the edges of segments may be assigned to another segment. This constrains the segmentation method to such a degree that it allows the method to use least squares for the robust fitting of affine motion models for each segment. Contrary to \cite{parmkm}, the segmentation step still operates on vectors instead of…

Proceedings of the Workshop on Use of Context in Vision Processing - UCVP '09, 2009

IEEE Transactions on Consumer Electronics, 2003

Future consumer terminals will be more and more based on programmable platforms instead of only d... more Future consumer terminals will be more and more based on programmable platforms instead of only dedicated hardware. Novel scalable video algorithm (SVA) software modules trade off resource usage against quality of the output signal. SVAs together with a strategy manager and a quality-of-service resource manager (QoS-RM) aim for flexible, robust, and cost-effective media processing in software on programmable architectures. We

Recent developments in the field of facial expression recognition advocate the use of feature vec... more Recent developments in the field of facial expression recognition advocate the use of feature vectors based on Local Binary Patterns (LBP). Research on the algorithmic side addresses robustness issues when dealing with non-ideal illumination conditions. In this paper, we address the challenges related to mapping these algorithms on smart camera platforms. Algorithmic partitioning taking into account the camera architecture is investigated with a primary focus of keeping the power consumption low. Experimental results show that compute-intensive feature extraction tasks can be mapped on a massively-parallel processor with reasonable processor utilization. Although the final feature classification phase could also benefit from parallel processing, mapping on a generalpurpose sequential processor would suffice.

It is often very hard to interpret molecular structure data obtained as a result of experimental ... more It is often very hard to interpret molecular structure data obtained as a result of experimental measurement or theoretical calculations. Typical examples of such data sources are X-ray diffraction techniques, NMR techniques or quantum mechanic calculations. The obtained 3D data as electron density maps or atom positions are complex objects and they require sophisticated methods of visualization. In the first part of this article we will discus several data interpretation problems for which the stereoscopic visualization is strongly ...

Telepresence has gone a long way since first seminal works on shared task and person spaces [1]. ... more Telepresence has gone a long way since first seminal works on shared task and person spaces [1]. After a number of technologies, such as broadband internet, high quality HD lowdelay video compression, or web applications, have become mature enough, several products have been able to irrupt into the market establishing a solid step forward towards practical true Telepresence solutions. Despite these advances, there is still work to do in what concerns naturality and usability. For instance, current systems are limited to 2D ...