Lutz Goldmann

• PhD
• Swiss Federal Institute of Technology in Lausanne

In this paper, we present a novel framework for quality control in cinematic VR (360-video) based on Voronoi patches and saliency which can be used in post-production workflows. Our approach first extracts patches in stereoscopic omnidirectional images (ODI) using the spherical Voronoi diagram. The subdivision of the ODI into patches allows an accu...

Many 2D-to-3D conversion techniques rely on image-based rendering methods in order to synthesize 3D views from monoscopic images. This leads to holes in the generated views due to previously occluded objects becoming visible for which no texture information is available. Approaches attempting to alleviate the effects of these artifacts are referred...

Increasing popularity of 3D videos calls for new methods to ease the conversion process of existing monocular video to stereoscopic or multi-view video. A popular way to convert video is given by depth image-based rendering methods, in which a depth map that is associated with an image frame is used to generate a virtual view. Because of the lack o...

As 3D image and video content has gained significant popularity, subjective 3D quality assessment has become an important issue for the creation, processing, and distribution of high quality 3D content. Reliable subjective quality assessment of 3D content is often difficult due to the subjects’ limited 3D experience, the interaction of multiple qua...

This paper presents an integrated system for face detection and tracking in video sequences. The system consists of two modules, namely face detection and face tracking. The automatic face detection is based on a non-holistic object detection approach that utilizes the appearance and the topology of facial components to robustly detect faces in ima...

3D quality of experience (QoE) in nature is a mul-tidimensional problem and involves many factors that contribute to the global quality rating such as image quality, depth perception and visual discom-fort. One important aspect for the development and evaluation of 3D processing techniques is the selection of appropriate 3D content. To this aim it...

In this paper, the authors analyze their graph-based approach for 2D and 3D object duplicate detection in still images. A graph model is used to represent the 3D spatial information of the object based on the features extracted from training images to avoid explicit and complex 3D object modeling. Therefore, improved performance can be achieved in...

Among various subjective quality evaluation methodologies, paired comparison has the advantage of improved simplicity of the subjects' evaluation task due to simplified rating scales and direct comparison of two stimuli. Thus, it may lead to more reliable results when individual quality levels are difficult to define, quality differences between st...

While D display technologies are already widely available for cinema and home or corporate use, only a few portable devices currently feature D display capabilities. Moreover, the large majority of D display solutions rely on binocular perception. In this paper, we study the alternative methods for restitution of 3D images on conventional 2D displa...

Today, several alternatives for compression of digital pictures and video sequences exist to choose from. Beside internationally recognized standard solutions, open access options like the VP8 image and video compression have recently appeared and are gaining popularity. In this paper, we present the methodology and the results of the rate-distorti...

With the rapid growth of digital photography, sharing of photos with friends and family has become very popular. When people share their photos, they usually organize them in albums according to events or places. To tell the story of some important events in one's life, it is desirable to have an efficient summarization tool which can help people t...

The success of 3D video, as one of the emerging multimedia formats, will largely depend on the improved quality of experience that it provides to viewers when compared to conventional 2D video. Therefore reliable methods for D video quality assessment are crucial in order to optimize D video systems and services. The goal of this paper is to review...

In this paper, we extend a graph-based approach for omnidirectional object duplicate detection in still images. Objects are detected from several points of view with different distances. The goal of this work is to determine how many training images have to be taken and from which points of view in order to achieve a certain efficiency. Moreover, t...

With the rapid growth of digital photography, sharing of photos with friends and family has become very popular. When people share their photos, they usually organize them in albums according to events or places. To tell the story of some important events in one's life, it is desirable to have an efficient summarization tool which can help people t...

Among various subjective quality evaluation methodologies, paired comparison has the advantage of improved simplicity of the subjects’ evaluation task due to simplified rating scales and direct comparison of two stimuli. Thus, it may lead to more reliable results when individual quality levels are difficult to define, quality differences between st...

With the technological evolution of digital acquisition and content analysis, millions of images and video sequences are captured every day and used in a large variety of applications. As keyword-based indexing is very time consuming and inefficient due to linguistic and semantic ambiguities, content-based image and video retrieval systems have bee...

In this paper, we analyze the influence of temporal asynchrony on the subjective quality of stereoscopic video. Based on our recently created 3D video database, different levels of asynchrony were simulated and a comprehensive subjective test was conducted to determine the associated degradations in quality of experience. Furthermore, we developed...

While objective and subjective quality assessment of 2D im-ages and video has been an active research topic in the re-cent years, emerging 3D technologies require new quality metrics and methodologies taking into account the funda-mental differences in the human visual perception and typi-cal distortions of stereoscopic content. Therefore, this pap...

In this paper, we consider the use of object duplicate detection for the propagation of geotags from a small set of images with location names (IPTC) to a large set of non-tagged images. The motivation behind this idea is that images of individual locations usually contain specific objects such as monuments, buildings or signs. Therefore, object du...

This paper describes the details and the results of the subjective quality evaluation performed at EPFL, as a contribution to the effort of the Joint Collaborative Team on Video Coding (JCT-VC) for the definition of the next-generation video coding standard. The performance of 27 coding technologies have been evaluated with respect to two H.264/MPE...

Video transcoding is an important step to enable interoperability between different networks, terminals, applications, and services for video communication. This paper studies the influence of typical video transcoding artifacts due to frame rate reduction and drift error on the subjective quality. Given a realistic dataset for a DVB-T to DVB-H tra...

Content-based video retrieval has become a very active research area in the last decade due to the increasing number of video content shared on social networks such as YouTube and DailyMotion. While most of the content-based video retrieval approaches employ low-level visual features for global analysis of the video, this paper proposes an object-b...

While objective and subjective quality assessment of 2D images and video have been an active research topic in the recent years, emerging 3D technologies require new quality metrics and methodologies taking into account the fundamental differences in the human visual perception and typical distortions of stereoscopic content. Therefore, this paper...

Im vergangenen Jahrzehnt sind der Computer und das Internets zu einem wichtigen Bestandteil unseres täglichen Lebens geworden. Wir verwenden diese Technologien um zu kommunizieren, zu arbeiten, einzukaufen, und für unsere Unterhaltung. Die Zukunft sieht eine stärkere Einbettung dieser Technologien in unsere tägliche Umgebung (Heim, Büro und öffentl...

With the rapid growth of digital photography, sharing of photos with friends and family has become very popular. When people share their photos, they usually organize them in albums according to events or places. To tell the story of some important events in one's life, it is desirable to have an efficient summarization tool which can help people t...

Over the last few years, social network systems have greatly increased users’ involvement in online content creation and annotation. Since such systems usually need to deal with a large amount of multimedia data, it becomes desirable to realize an interactive service that minimizes tedious and time consuming manual annotation. In this paper, we pro...

The study presented in this paper aims at quantifying the empirical limits of JPEG optimization, when the compressed stream is standard compliant and only the quantization tables are optimized. Image-dependent quantization tables, which minimize the bitrate of the compressed image while maintaining transparent visual quality, are identified by mean...

In this paper, we analyze our graph-based approach for 2D and 3D object duplicate detection in still images. A graph model is used to represent the 3D spatial information of the object based on the features extracted from training images so that an explicit and complex 3D object modeling is avoided. Therefore, improved performance can be achieved i...

In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the si...

The success of 3DTV, as one of the emerging multimedia formats, will largely depend on the quality of experience it provides to the viewer in relation to traditional media. Therefore reliable methods for quality assessment are crucial in order to optimize 3D systems and services. The goal of this paper is to review recent developments in 3D quality...

With the increasing amount of multimedia data, efficient tools for search and retrieval are needed. Since people are naturally one of the most interesting objects within these documents, a system for multimodal person search and retrieval has been developed. It combines the audiovisual analysis of persons with the query by example paradigm and rele...

In this paper a procedure for subjective evaluation of the new JPEG XR codec for compression of still pictures is described in details. The new algorithm has been compared to the existing JPEG and JPEG 2000 standards when considering compression of high resolution 24 bpp pictures, by mean of a campaign of subjective quality assessment tests which f...

For object analysis in videos such as in video surveillance systems, the preliminary segmentation step is very important. Many segmentation methods using static camera have been proposed in the last decade, but they all suffer in occurrance of object reflection especially on the ground, i.e. reflected regions are also segmented as foregrounds. We p...

During the last decade computers and the internet have become an important aspect in our everyday life. We use this technology to communicate, study, work, shop, and entertain ourselves. The vision of the future is to embed this computing technology into our home, transportation and working environments. The ultimate goal is to develop intelligent...

In this paper, we consider the evaluation of graph-based object duplicate detection. Several applications require accurate and efficient object duplicate detection methods, such as automatic video and image tag propagation, video surveillance, and high level image or video search. In this paper, a graph-based approach for 3D object duplicate detect...

Spatial region (image) segmentation is a fundamental step for many computer vision applications. Although many methods have been proposed, less work has been done in developing suitable evaluation methodologies for comparing different approaches. The main problem of general purpose segmentation evaluation is the dilemma between objectivity and gene...

Face analysis is a very active research field, due to its large variety of applications and the different challenges (illumination, pose, expressions or occlusions) the methods need to cope with. Facial occlusions are one of the biggest challenges since they are difficult to model and have a large influence on the performance of subsequent analysis...

This paper addresses one of the main challenges of face recognition (FR): facial occlusions. Currently, the human brain is the most robust known FR approach towards partially occluded faces. Nevertheless, it is still not clear if humans recognize faces using a holistic or a component-based strategy, or even a combination of both. In this paper, thr...

Abstract In this paper we describe the K-Space participation in TRECVid 2006. K-Space participated in two tasks, highlevel feature extraction and search. We present our approaches for each of these activities and provide a brief

This paper describes an advanced user-interface that detects and identifies people from video data, tracks their body and body part movements, and recognizes a set of gesture-based user commands. In this way an exemplar implementation for interacting with an intelligent cash machine is presented. The system combines person identification and gestur...

Content based multimedia retrieval systems have been pro- posed to allow for automatic and ecient indexing and retrieval of the increasing amount of audiovisual data (image, video and audio clips). The search for specic persons within this data is an important subtopic due to its large range of applications. This article describes an original syste...

This paper presents a novel approach for automatic and robust object detection. It utilizes a component-based approach that combines techniques from both statistical and structural pattern recognition domain. While the component detection relies on Haar-like features and an AdaBoost trained classifier cascade, the topology verification is based on...

Speaker change detection (SCD) is a preliminary step for many audio applications such as speaker segmentation and recognition. Thus, its robustness is crucial to achieve a good performance in the later steps. Especially, misses (false negatives) affect the results. For some applications, domain-specific characteristics can be used to improve the re...

In this paper we describe K-Space participation in TRECVid 2007. K-Space participated in two tasks, high- level feature extraction and interactive search. We present our approaches for each of these activities and provide a brief analysis of our results. Our high-level feature submission utilized multi-modal low-level features which included visual...

In this work, our aim is to develop an automated system which provides data useful for football game analysis. Information from multiple cameras is used to perform player detection, classification and tracking. A background segmentation approach, which operates with the invariant Gaussian colour model and uses temporal information, is used to achie...

This paper describes an original system for content based image retrieval. It is based on MPEG-7 descriptors and a novel approach for long term relevance feedback using a Bayesian classifier. Each image is represented by a special model that is adapted over multiple feedback rounds and even multiple sessions or users. The experiments show its outst...

This paper presents a novel approach for automatic and robust object detection. It utilizes a component-based approach that combines techniques from both statistical and structural pattern recognition domain. While the component detection relies on Haar-like features and an AdaBoost trained classifier cascade, the topology verification is based on...

A new segmentation approach usable for fixed or motion compensated camera is described. Instead of the often used RGB color space we operate with the invariant Gaussian color model proposed by Geusebroek and temporal information which eliminates unsteady regions surrounded by the moving objects. The Gaussian color model has never been used in video...

Traditional surveillance systems are usually based on visual information only. With the emerging multimedia analysis techniques, interests are changing towards systems that incorporate multiple sensors and different modalities, which leads to new ways of analyzing this multimedia data and more sophisticated applications. This paper shortly reviews...

In this paper we describe K-Space’s participation in TRECVid 2008 in the interactive search task. For 2008 the K-Space group performed one of the largest interactive video information retrieval experiments conducted in a laboratory setting. We had three institutions participating in a multi-site multi-system experiment. In total 36 users participat...

In the case of a static or motion compensated camera, static background segmentation methods can be applied to segment the interesting foreground objects from the background. Although a lot of methods have been proposed, a general assessment of the state of the art is not available. An important issue is to compare various state of the art methods...

This paper presents a novel approach to human body posture recognition based on the MPEG-7 contour-based shape descriptor and the widely used projection histogram. A combination of them was used to recognize the main posture and the view of a human based on the binary object mask obtained by the segmentation process. The recognition is treated as a...

This paper presents an original system for recognizing persons based on their appearance. Thus, it is especially suitable to surveillance scenarios, where biometric information might not be available. Dierent visual low level features in combination with dierent su- pervised learning methods are examined in order to built a robust system. Furthermo...

Abstract This paper presents a multimodal system incorporating smart room technologies (SRT) for confer- ence room applications. Although, the audio-visual anal- ysis requires only rather basic equipment, the system works reliably and supports various applications such as recognizing persons using dierent modalities, local- izating visible speakers...

Thanks to advances in digital acquisition, processing, and storage technologies, millions of images are captured every day and shared in online social services such as Facebook 1 , Flickr 2 , and Picasa 3 . Furthermore, images provide an inter-esting way to identify or to find desired objects and locations. Image based search and retrieval is becom...