Xiaoyi Jiang | University of Münster (original) (raw)
Papers by Xiaoyi Jiang
Frontiers in Marine Science, Jul 28, 2023
Introduction: In the last decade, the outbreak of large-scale green tides caused by Ulva prolifer... more Introduction: In the last decade, the outbreak of large-scale green tides caused by Ulva prolifera has continuously occurred in the Yellow Sea. Satellite remote sensing techniques have been widely used to monitor the distribution area and duration of green tides due to their advantages of their large-area synchronous observation. Ulva prolifera in the Yellow Sea is mainly distributed in bands or large patches during its flourishing stage. Previous studies have rarely reported the quantitative analysis of a single Ulva prolifera patch and its changes in the short term. Methods: Considering the high temporal resolution of the Geostationary Ocean Color Imager (GOCI) sensor and the patchy distribution of Ulva prolifera floating on the sea surface, we developed a feasible method for monitoringUlva prolifera by performing clustering analysis with density-based spatial clustering of applications with noise (DBSCAN) to capture the diurnal variation characteristics of a single Ulva prolifera patch. Results: This new approach was used to extract informationfrom a single Ulva prolifera patch in the Yellow Sea in 2012 and 2017. The results showed that during the time of GOCI imaging, the tidal current was the main factor driving the drift of Ulva prolifera, and the drifting direction of Ulva prolifera was consistent with the direction of the local tidal current, with a coefficient of determination of 0.94. Discussion: By changing the normalized difference vegetation index (NDVI) threshold, further more accurate atmospheric correction (AC) of GOCI data during the twilight periods was indirectly achieved. By comparing the areal change in the single patch before and after AC, we speculated that the daily change in signal intensity received by the GOCI sensor may be the main reason for the diurnal variation in the Ulva proliferacoverage area. The results showed the details of the diurnal variation in Ulvaprolifera patches in the dynamic marine environment, and the main reason that may cause this variation was speculated.
Springer eBooks, 2022
Graph kernels have been studied for a long time and applied among others for graph classification... more Graph kernels have been studied for a long time and applied among others for graph classification. In this paper we bring two novel aspects into the graph processing community. Currently, the backbone for kernel-based classification is solely the support vector machine. We introduce the interpolation kernel machine for this purpose. In addition, for both support vector machine and interpolation kernel machine, many kernels used in practice do not satisfy the formal requirements (e.g. positive definiteness). We thus introduce extensions of the standard version to indefinite kernel methods. We argue and experimentally demonstrate why these two aspects should be considered for graph classification. One of our conclusions will be that the interpolation kernel machine is a good alternative of support vector machine. Consequently, we will propose an extended experimental protocol. With this work we contribute to increasing the methodological plurality in the graph processing community.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Interpolating classifiers interpolate all the training data and thus have zero training error. Re... more Interpolating classifiers interpolate all the training data and thus have zero training error. Recent research shows their fundamental importance for high-performance ensemble techniques and other advantages. Interpolation kernel machines belong to the class of interpolating classifiers and do generalize well. They have been demonstrated to be a good alternative to support vector machines. In this work we further improve their performance. We propose not to use their inherent multiclass classification capacity, but instead apply them for solving binary classification instances based on a mutliclass-to-binary reduction. We experimentally study this ensemble approach in combination with six reducing multiple-to-binary methods. The experimental results show that the oneversus-one scheme consistently demonstrates superior performance.
Pattern Recognition, Mar 1, 2022
Stroke extraction and matching are critical for structural interpretation based applications of h... more Stroke extraction and matching are critical for structural interpretation based applications of handwritten Chinese characters, such as Chinese character education and calligraphy analysis. Stroke extraction from offline handwritten Chinese characters is difficult because of the missing of temporal information, the multi-stroke structures and the distortion of handwritten shapes. In this paper, we propose a comprehensive scheme for solving the stroke extraction problem for handwritten Chinese characters. The method consists of three main steps: (1) fully convolutional network (FCN) based skeletonization; (2) query pixel guided stroke extraction; (3) model-based stroke matching. Specifically, based on a recently proposed architecture of FCN, both the stroke skeletons and cross regions are firstly extracted from the character image by the proposed SkeNet and CrossNet, respectively. Stroke extraction is solved by simulating the human perception that once given a certain pixel from non-cross region of a stroke, the whole stroke containing the pixel can be traced. To realize this idea, we formulate stroke extraction as a problem of pairing and connecting skeleton-wise stroke segments which are adjacent to the same cross region, where the pairing consistency between stroke segments is measured using a PathNet . To reduce the ambiguity of stroke extraction, the extracted candidate strokes are matched with a character model consisting of standard strokes by tree search to identify the correct strokes. For verifying the effectiveness of the proposed method, we train and test our models on character images with stroke segmentation annotations generated from the online handwriting datasets CASIA-OLHWDB and ICDAR13-Online, as well as a dataset of R egularly-W ritten online handwritten characters (RW-OLHWDB). The experimental results demonstrate the effectiveness of the proposed method and provide several benchmarks. Particularly, the precisions of stroke extraction for ICDAR13-Online and RW-OLHWDB are 89.0% and 94.9%, respectively.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Interpolating classifiers interpolate all the training data and thus have zero training error. Re... more Interpolating classifiers interpolate all the training data and thus have zero training error. Recent research shows their fundamental importance for high-performance ensemble techniques. Interpolation kernel machines belong to the class of interpolating classifiers and do generalize well. They have been demonstrated to be a good alternative to support vector machine for graph classification. In this work we further improve their performance by considering multiple kernel learning. We establish a general scheme for achieving this goal. The current experimental work is done using quadratic kernel combination. Our experimental results demonstrate the performance boosting potential of our approach against the use of individual graph kernels.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Computing a consensus object from a set of given objects is a core problem in machine learning an... more Computing a consensus object from a set of given objects is a core problem in machine learning and pattern recognition. A popular approach is the formulation of generalized median as an optimization problem. The concept of generalized median has been studied for numerous problem domains with a broad range of applications. Currently, the research is widely scattered in the literature and no comprehensive survey is available. This brief survey contributes to closing this gap and systematically discusses the relevant issues of generalized median computation. In particular, we present a taxonomy of computation frameworks and methods. We also outline a number of future research directions.
Big Data and Cognitive Computing
In recent years, there have been significant advances in deep learning and road marking recogniti... more In recent years, there have been significant advances in deep learning and road marking recognition due to machine learning and artificial intelligence. Despite significant progress, it often relies heavily on unrepresentative datasets and limited situations. Drivers and advanced driver assistance systems rely on road markings to help them better understand their environment on the street. Road markings are signs and texts painted on the road surface, including directional arrows, pedestrian crossings, speed limit signs, zebra crossings, and other equivalent signs and texts. Pavement markings are also known as road markings. Our experiments briefly discuss convolutional neural network (CNN)-based object detection algorithms, specifically for Yolo V2, Yolo V3, Yolo V4, and Yolo V4-tiny. In our experiments, we built the Taiwan Road Marking Sign Dataset (TRMSD) and made it a public dataset so other researchers could use it. Further, we train the model to distinguish left and right obje...
Electronics
Drowsiness is a major risk factor for road safety, contributing to serious injury, death, and eco... more Drowsiness is a major risk factor for road safety, contributing to serious injury, death, and economic loss on the road. Driving performance decreases because of increased drowsiness. In several different applications, such as facial movement analysis and driver safety, blink detection is an essential requirement that is used. The extremely rapid blink rate, on the other hand, makes automatic blink detection an extremely challenging task. This research paper presents a technique for identifying eye blinks in a video series recorded by a car dashboard camera in real time. The suggested technique determines the facial landmark positions for each video frame and then extracts the vertical distance between the eyelids from the facial landmark positions. The algorithm that has been proposed estimates the facial landmark positions, extracts a single scalar quantity by making use of Eye Aspect Ratio (EAR), and identifies the eye closeness in each frame. In the end, blinks are recognized by...
Applied Sciences, 2020
In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achie... more In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achieves outstanding performance. The detection of a traffic sign, as it has a dual function in monitoring and directing the driver, is a big concern for driver support systems. A core feature of autonomous vehicle systems is the identification of the traffic sign. This article focuses on the prohibitive sign. The objective is to detect in real-time and reduce processing time considerably. In this study, we implement the spatial pyramid pooling (SPP) principle to boost Yolo V3’s backbone network for the extraction of functionality. Our work uses SPP for more comprehensive learning of multiscale object features. Then, perform a comparative investigation of Yolo V3 and Yolo V3 SPP across various scales to recognize the prohibitory sign. Comparisons with Yolo V3 SPP models reveal that their mean average precision (mAP) is higher than Yolo V3. Furthermore, the test accuracy findings indicate that...
The analysis of behavioural traits of Caenorhabditis elegans is an important method for understan... more The analysis of behavioural traits of Caenorhabditis elegans is an important method for understanding neuromuscular functions and diseases. Since C. elegans is a small and translucent animal which conducts a variety of complex movement patterns many different imaging and tracking protocols are used for different behavioural traits. Thus a unified multi-purpose imaging and tracking system for multiple behavioural assays would be favourable to improve statistical strength and comparability. Here we present a novel worm tracking toolbox based on the FIM (Frustrated total internal reflection (FTIR) based Imaging Method) system incorporating a variety of different behavioural assays into a single imaging and tracking setup.First, we apply the FTIR-based imaging method to C. elegans, thus we are able to improve the overall image quality compared to state of the art recording techniques. This method is easy to use and can be utilised to image animals during crawling on agar and trashing in...
Sensors, 2019
We review some emerging trends in transduction, connectivity and data analytics for Point-of-Care... more We review some emerging trends in transduction, connectivity and data analytics for Point-of-Care Testing (POCT) of infectious and non-communicable diseases. The patient need for POCT is described along with developments in portable diagnostics, specifically in respect of Lab-on-chip and microfluidic systems. We describe some novel electrochemical and photonic systems and the use of mobile phones in terms of hardware components and device connectivity for POCT. Developments in data analytics that are applicable for POCT are described with an overview of data structures and recent AI/Machine learning trends. The most important methodologies of machine learning, including deep learning methods, are summarised. The potential value of trends within POCT systems for clinical diagnostics within Lower Middle Income Countries (LMICs) and the Least Developed Countries (LDCs) are highlighted.
Digital Restoration of Medieval Tapestries
Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in pa... more Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in particular of the Bern Historical Museum. Many of them are well preserved, but much of their color is highly faded. Thus their today's appearance is very different from the original one. This paper deals with the digital restoration of the appearance of such tapestries. Two methods are developed and examined, one using the back side of the tapestry, the other one using color clustering. Our main criteria are a convincing approximation of the expected appearance and - due to the large size of many of the tapestries - a high degree of automation.
3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano, 2006.
Introducing Stereo Effects into Cel Animations
2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008
FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
Journal of Visualized Experiments, 2014
Localization of pedestrian lights on mobile devices
Proceedings: APSIPA ASC …, 2009
IEEE transactions on image processing, 2022
The random walker method for image segmentation is a popular tool for semi-automatic image segmen... more The random walker method for image segmentation is a popular tool for semi-automatic image segmentation, especially in the biomedical field. However, its linear asymptotic run time and memory requirements make application to 3D datasets of increasing sizes impractical. We propose a hierarchical framework that, to the best of our knowledge, is the first attempt to overcome these restrictions for the random walker algorithm and achieves sublinear run time and constant memory complexity. The goal of this framework is -rather than improving the segmentation quality compared to the baseline method -to make interactive segmentation on out-of-core datasets possible. The method is evaluated quantitatively on synthetic data and the CT-ORG dataset where the expected improvements in algorithm run time while maintaining high segmentation quality are confirmed. The incremental (i.e., interaction update) run time is demonstrated to be in seconds on a standard PC even for volumes of hundreds of gigabytes in size. In a small case study the applicability to large real world from current biomedical research is demonstrated. An implementation of the presented method is publicly available in version 5.2 of the widely used volume rendering and processing software Voreen 1 .
Introducing Stereo Effects into Cel Animations
2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008
... 124131, IEEE Computer Society. [7] S. Knorr, E. Imre, B. ¨Ozkalayci, AA Alatan, and T. Sikor... more ... 124131, IEEE Computer Society. [7] S. Knorr, E. Imre, B. ¨Ozkalayci, AA Alatan, and T. Sikora, A modular scheme for 2d/3d conversion of tv broadcast, in 3DPVT '06, Washington, DC, USA, 2006, pp. 703710, IEEE Computer Society. ...
Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in pa... more Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in particular of the Bern Historical Museum. Many of them are well preserved, but much of their color is highly faded. Thus their today's appearance is very different from the original one. This paper deals with the digital restoration of the appearance of such tapestries. Two methods are developed and examined, one using the back side of the tapestry, the other one using color clustering. Our main criteria are a convincing approximation of the expected appearance and - due to the large size of many of the tapestries - a high degree of automation.
Frontiers in Marine Science, Jul 28, 2023
Introduction: In the last decade, the outbreak of large-scale green tides caused by Ulva prolifer... more Introduction: In the last decade, the outbreak of large-scale green tides caused by Ulva prolifera has continuously occurred in the Yellow Sea. Satellite remote sensing techniques have been widely used to monitor the distribution area and duration of green tides due to their advantages of their large-area synchronous observation. Ulva prolifera in the Yellow Sea is mainly distributed in bands or large patches during its flourishing stage. Previous studies have rarely reported the quantitative analysis of a single Ulva prolifera patch and its changes in the short term. Methods: Considering the high temporal resolution of the Geostationary Ocean Color Imager (GOCI) sensor and the patchy distribution of Ulva prolifera floating on the sea surface, we developed a feasible method for monitoringUlva prolifera by performing clustering analysis with density-based spatial clustering of applications with noise (DBSCAN) to capture the diurnal variation characteristics of a single Ulva prolifera patch. Results: This new approach was used to extract informationfrom a single Ulva prolifera patch in the Yellow Sea in 2012 and 2017. The results showed that during the time of GOCI imaging, the tidal current was the main factor driving the drift of Ulva prolifera, and the drifting direction of Ulva prolifera was consistent with the direction of the local tidal current, with a coefficient of determination of 0.94. Discussion: By changing the normalized difference vegetation index (NDVI) threshold, further more accurate atmospheric correction (AC) of GOCI data during the twilight periods was indirectly achieved. By comparing the areal change in the single patch before and after AC, we speculated that the daily change in signal intensity received by the GOCI sensor may be the main reason for the diurnal variation in the Ulva proliferacoverage area. The results showed the details of the diurnal variation in Ulvaprolifera patches in the dynamic marine environment, and the main reason that may cause this variation was speculated.
Springer eBooks, 2022
Graph kernels have been studied for a long time and applied among others for graph classification... more Graph kernels have been studied for a long time and applied among others for graph classification. In this paper we bring two novel aspects into the graph processing community. Currently, the backbone for kernel-based classification is solely the support vector machine. We introduce the interpolation kernel machine for this purpose. In addition, for both support vector machine and interpolation kernel machine, many kernels used in practice do not satisfy the formal requirements (e.g. positive definiteness). We thus introduce extensions of the standard version to indefinite kernel methods. We argue and experimentally demonstrate why these two aspects should be considered for graph classification. One of our conclusions will be that the interpolation kernel machine is a good alternative of support vector machine. Consequently, we will propose an extended experimental protocol. With this work we contribute to increasing the methodological plurality in the graph processing community.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Interpolating classifiers interpolate all the training data and thus have zero training error. Re... more Interpolating classifiers interpolate all the training data and thus have zero training error. Recent research shows their fundamental importance for high-performance ensemble techniques and other advantages. Interpolation kernel machines belong to the class of interpolating classifiers and do generalize well. They have been demonstrated to be a good alternative to support vector machines. In this work we further improve their performance. We propose not to use their inherent multiclass classification capacity, but instead apply them for solving binary classification instances based on a mutliclass-to-binary reduction. We experimentally study this ensemble approach in combination with six reducing multiple-to-binary methods. The experimental results show that the oneversus-one scheme consistently demonstrates superior performance.
Pattern Recognition, Mar 1, 2022
Stroke extraction and matching are critical for structural interpretation based applications of h... more Stroke extraction and matching are critical for structural interpretation based applications of handwritten Chinese characters, such as Chinese character education and calligraphy analysis. Stroke extraction from offline handwritten Chinese characters is difficult because of the missing of temporal information, the multi-stroke structures and the distortion of handwritten shapes. In this paper, we propose a comprehensive scheme for solving the stroke extraction problem for handwritten Chinese characters. The method consists of three main steps: (1) fully convolutional network (FCN) based skeletonization; (2) query pixel guided stroke extraction; (3) model-based stroke matching. Specifically, based on a recently proposed architecture of FCN, both the stroke skeletons and cross regions are firstly extracted from the character image by the proposed SkeNet and CrossNet, respectively. Stroke extraction is solved by simulating the human perception that once given a certain pixel from non-cross region of a stroke, the whole stroke containing the pixel can be traced. To realize this idea, we formulate stroke extraction as a problem of pairing and connecting skeleton-wise stroke segments which are adjacent to the same cross region, where the pairing consistency between stroke segments is measured using a PathNet . To reduce the ambiguity of stroke extraction, the extracted candidate strokes are matched with a character model consisting of standard strokes by tree search to identify the correct strokes. For verifying the effectiveness of the proposed method, we train and test our models on character images with stroke segmentation annotations generated from the online handwriting datasets CASIA-OLHWDB and ICDAR13-Online, as well as a dataset of R egularly-W ritten online handwritten characters (RW-OLHWDB). The experimental results demonstrate the effectiveness of the proposed method and provide several benchmarks. Particularly, the precisions of stroke extraction for ICDAR13-Online and RW-OLHWDB are 89.0% and 94.9%, respectively.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Interpolating classifiers interpolate all the training data and thus have zero training error. Re... more Interpolating classifiers interpolate all the training data and thus have zero training error. Recent research shows their fundamental importance for high-performance ensemble techniques. Interpolation kernel machines belong to the class of interpolating classifiers and do generalize well. They have been demonstrated to be a good alternative to support vector machine for graph classification. In this work we further improve their performance by considering multiple kernel learning. We establish a general scheme for achieving this goal. The current experimental work is done using quadratic kernel combination. Our experimental results demonstrate the performance boosting potential of our approach against the use of individual graph kernels.
Zenodo (CERN European Organization for Nuclear Research), Aug 7, 2023
Computing a consensus object from a set of given objects is a core problem in machine learning an... more Computing a consensus object from a set of given objects is a core problem in machine learning and pattern recognition. A popular approach is the formulation of generalized median as an optimization problem. The concept of generalized median has been studied for numerous problem domains with a broad range of applications. Currently, the research is widely scattered in the literature and no comprehensive survey is available. This brief survey contributes to closing this gap and systematically discusses the relevant issues of generalized median computation. In particular, we present a taxonomy of computation frameworks and methods. We also outline a number of future research directions.
Big Data and Cognitive Computing
In recent years, there have been significant advances in deep learning and road marking recogniti... more In recent years, there have been significant advances in deep learning and road marking recognition due to machine learning and artificial intelligence. Despite significant progress, it often relies heavily on unrepresentative datasets and limited situations. Drivers and advanced driver assistance systems rely on road markings to help them better understand their environment on the street. Road markings are signs and texts painted on the road surface, including directional arrows, pedestrian crossings, speed limit signs, zebra crossings, and other equivalent signs and texts. Pavement markings are also known as road markings. Our experiments briefly discuss convolutional neural network (CNN)-based object detection algorithms, specifically for Yolo V2, Yolo V3, Yolo V4, and Yolo V4-tiny. In our experiments, we built the Taiwan Road Marking Sign Dataset (TRMSD) and made it a public dataset so other researchers could use it. Further, we train the model to distinguish left and right obje...
Electronics
Drowsiness is a major risk factor for road safety, contributing to serious injury, death, and eco... more Drowsiness is a major risk factor for road safety, contributing to serious injury, death, and economic loss on the road. Driving performance decreases because of increased drowsiness. In several different applications, such as facial movement analysis and driver safety, blink detection is an essential requirement that is used. The extremely rapid blink rate, on the other hand, makes automatic blink detection an extremely challenging task. This research paper presents a technique for identifying eye blinks in a video series recorded by a car dashboard camera in real time. The suggested technique determines the facial landmark positions for each video frame and then extracts the vertical distance between the eyelids from the facial landmark positions. The algorithm that has been proposed estimates the facial landmark positions, extracts a single scalar quantity by making use of Eye Aspect Ratio (EAR), and identifies the eye closeness in each frame. In the end, blinks are recognized by...
Applied Sciences, 2020
In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achie... more In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achieves outstanding performance. The detection of a traffic sign, as it has a dual function in monitoring and directing the driver, is a big concern for driver support systems. A core feature of autonomous vehicle systems is the identification of the traffic sign. This article focuses on the prohibitive sign. The objective is to detect in real-time and reduce processing time considerably. In this study, we implement the spatial pyramid pooling (SPP) principle to boost Yolo V3’s backbone network for the extraction of functionality. Our work uses SPP for more comprehensive learning of multiscale object features. Then, perform a comparative investigation of Yolo V3 and Yolo V3 SPP across various scales to recognize the prohibitory sign. Comparisons with Yolo V3 SPP models reveal that their mean average precision (mAP) is higher than Yolo V3. Furthermore, the test accuracy findings indicate that...
The analysis of behavioural traits of Caenorhabditis elegans is an important method for understan... more The analysis of behavioural traits of Caenorhabditis elegans is an important method for understanding neuromuscular functions and diseases. Since C. elegans is a small and translucent animal which conducts a variety of complex movement patterns many different imaging and tracking protocols are used for different behavioural traits. Thus a unified multi-purpose imaging and tracking system for multiple behavioural assays would be favourable to improve statistical strength and comparability. Here we present a novel worm tracking toolbox based on the FIM (Frustrated total internal reflection (FTIR) based Imaging Method) system incorporating a variety of different behavioural assays into a single imaging and tracking setup.First, we apply the FTIR-based imaging method to C. elegans, thus we are able to improve the overall image quality compared to state of the art recording techniques. This method is easy to use and can be utilised to image animals during crawling on agar and trashing in...
Sensors, 2019
We review some emerging trends in transduction, connectivity and data analytics for Point-of-Care... more We review some emerging trends in transduction, connectivity and data analytics for Point-of-Care Testing (POCT) of infectious and non-communicable diseases. The patient need for POCT is described along with developments in portable diagnostics, specifically in respect of Lab-on-chip and microfluidic systems. We describe some novel electrochemical and photonic systems and the use of mobile phones in terms of hardware components and device connectivity for POCT. Developments in data analytics that are applicable for POCT are described with an overview of data structures and recent AI/Machine learning trends. The most important methodologies of machine learning, including deep learning methods, are summarised. The potential value of trends within POCT systems for clinical diagnostics within Lower Middle Income Countries (LMICs) and the Least Developed Countries (LDCs) are highlighted.
Digital Restoration of Medieval Tapestries
Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in pa... more Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in particular of the Bern Historical Museum. Many of them are well preserved, but much of their color is highly faded. Thus their today's appearance is very different from the original one. This paper deals with the digital restoration of the appearance of such tapestries. Two methods are developed and examined, one using the back side of the tapestry, the other one using color clustering. Our main criteria are a convincing approximation of the expected appearance and - due to the large size of many of the tapestries - a high degree of automation.
3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano, 2006.
Introducing Stereo Effects into Cel Animations
2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008
FIM Imaging and FIMtrack: Two New Tools Allowing High-throughput and Cost Effective Locomotion Analysis
Journal of Visualized Experiments, 2014
Localization of pedestrian lights on mobile devices
Proceedings: APSIPA ASC …, 2009
IEEE transactions on image processing, 2022
The random walker method for image segmentation is a popular tool for semi-automatic image segmen... more The random walker method for image segmentation is a popular tool for semi-automatic image segmentation, especially in the biomedical field. However, its linear asymptotic run time and memory requirements make application to 3D datasets of increasing sizes impractical. We propose a hierarchical framework that, to the best of our knowledge, is the first attempt to overcome these restrictions for the random walker algorithm and achieves sublinear run time and constant memory complexity. The goal of this framework is -rather than improving the segmentation quality compared to the baseline method -to make interactive segmentation on out-of-core datasets possible. The method is evaluated quantitatively on synthetic data and the CT-ORG dataset where the expected improvements in algorithm run time while maintaining high segmentation quality are confirmed. The incremental (i.e., interaction update) run time is demonstrated to be in seconds on a standard PC even for volumes of hundreds of gigabytes in size. In a small case study the applicability to large real world from current biomedical research is demonstrated. An implementation of the presented method is publicly available in version 5.2 of the widely used volume rendering and processing software Voreen 1 .
Introducing Stereo Effects into Cel Animations
2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008
... 124131, IEEE Computer Society. [7] S. Knorr, E. Imre, B. ¨Ozkalayci, AA Alatan, and T. Sikor... more ... 124131, IEEE Computer Society. [7] S. Knorr, E. Imre, B. ¨Ozkalayci, AA Alatan, and T. Sikora, A modular scheme for 2d/3d conversion of tv broadcast, in 3DPVT '06, Washington, DC, USA, 2006, pp. 703710, IEEE Computer Society. ...
Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in pa... more Medieval Burgundian tapestries belong to the most valuable treasures of historical museums, in particular of the Bern Historical Museum. Many of them are well preserved, but much of their color is highly faded. Thus their today's appearance is very different from the original one. This paper deals with the digital restoration of the appearance of such tapestries. Two methods are developed and examined, one using the back side of the tapestry, the other one using color clustering. Our main criteria are a convincing approximation of the expected appearance and - due to the large size of many of the tapestries - a high degree of automation.