This paper discusses an efficient and effective approach to simultaneously identifying and tracki... more This paper discusses an efficient and effective approach to simultaneously identifying and tracking two free moving and gesturing hands, together with the provision of accurate segmentation masks of the hands regions. It is aimed at a novel application in telepresence video conferencing system. The skin colour model in YUV colour space is created and adapted to characterise the likely appearance of hands. The initialisation is performed on the first two frames of a video stream, and the probabilistic skin colour map and motion mask information are used, resulting in an accurate segmentation of the two initial hands. The ensued tracking uses a set of Kalman filters to predict the centroid, orientation, and sizes of candidate hand objects, from which refinements of hands locations are made. The issue of inter-hands overlap and update of the skin colour model are also properly addressed.
Abstract In this paper. a novel area-hased dense stereo correspondence estimation algorithm is pr... more Abstract In this paper. a novel area-hased dense stereo correspondence estimation algorithm is proposed. The new algorithm. which we call Hierarchical Adaptive Curve Matching or HACM in short. is suitable for stereo imaging of both static and dynamic ...
BACKGROUND In the era of the digital economy, the demand for medical and public health services h... more BACKGROUND In the era of the digital economy, the demand for medical and public health services has soared in recent years, asking for developing innovative healthcare service models. This trend has accelerated the urgency to implement effective and efficient data exchange and service interoperability, which enable coordinated care services among tiered healthcare institutions, improve the quality of oversight of regulators, and provide vast and comprehensive data collection to support clinical medicine and health economics research, thus improving the overall service quality and patient satisfaction. However, the isolated data islands among heterogeneous IT systems have been a significant problem, seriously restricting data sharing and service interoperability capabilities. In this context, HL7 FHIR was formally introduced in 2014 and has since continued evolving. Because of its many advantages, such as a simple data model, flexible exchanging model, and adequate open source tools, this standard has attracted worldwide attention in the healthcare industry and has been adopted and promoted by health systems in the UK, USA, and Canada. OBJECTIVE By investigating and analyzing the latest literature on FHIR from the perspectives of motivations, techniques, and applications, we proposed a general FHIR Practice Guideline (FHIR PG) to facilitate stakeholders in the healthcare ecosystem to both understand the FHIR standard and build interoperable services with ease. METHODS We identified 487 papers from the Web of Science and IEEE databases and selected 85 papers published between January 1, 2020, and July 1, 2022, as the source of investigation. First, we chose to classify these papers into three categories: data standardization, data management, and data interoperation, for each of which we discussed the motivations, techniques, and applications. Then, we proposed a general FHIR PG for the entire FHIR practice process through careful analysis and collation. RESULTS The general FHIR PG clarified the unique roles of all the stakeholders involved, including the Implementation Guides (IGs) standard committee, healthcare IT system vendor, and application developer. And it integrated the data standardization flow, data exchange model, and service implementation approach into a complete practice process. As a result, the general FHIR PG facilitates stakeholders to practice the FHIR standard and design interoperable healthcare services. CONCLUSIONS This paper proposed a general FHIR PG by discussing the process of data standardization, data management, and data interoperation from the latest literature. The general FHIR PG can help a stakeholder in the healthcare ecosystem to identify its unique roles, manage the scope of responsibilities, and plan the work content, thereby facilitating the implementation and promotion of the FHIR standard.
Abstract In this paper we present an effective real-time video surveillance system suitable for a... more Abstract In this paper we present an effective real-time video surveillance system suitable for a wide range of outdoor application scenarios. By carefully addressing unique challenges of outdoor scenes such as frequent illumination change and complex object motion etc., this ...
In this chapter we have discussed the recent trend in developing an advanced videoconferencing sy... more In this chapter we have discussed the recent trend in developing an advanced videoconferencing system that moves towards being a seamless integration of a real and virtual world environment with high-quality 3-D telepresence, while focusing on outlining the scope of research work and software system architecture for the VIRTUE project. The entire VIRTUE system design is flexible and conceived largely on the basis of exploiting state-of-the-art technologies in the computer vision, and image and video processing fields guided by the results of human factor studies, rather than physically placing multiple displays, cameras and human subjects. Specifically, we have chosen to demonstrate a core component for 3-D scene analysis, an efficient technique for robust disparity estimation from stereos of still and dynamic scenes, and its application in 3-D visualisation and videoconferencing applications when employing an image-based rendering approach for reconstructing new (and temporarily coherent) virtual views.
The ability to recognize physical activity, such as sedentary, driving, riding, daily activities ... more The ability to recognize physical activity, such as sedentary, driving, riding, daily activities and effective training, is useful for health conscious users to catalogue their daily activities and to develop good exercise routines. Conventional activity recognition algorithms require complex calculations, which are not suitable for wearable devices developed on low-cost, low-power hardware platforms. In this paper, inspired by the text mining related work, we design a novel activity recognition algorithm, which is named “Motionword”. In the wearable device proper, a lightweight recognition algorithm is adopted to compute in real-time predefined atomic events, and count the frequency that these events occur, resulting in a data summary, and then the data summary is transmitted to the platform. On the platform, intelligent method is used to identify and categorize the user's main activity into 5 classes. The test results on a dataset composed of 110 user∗day real world data, contributed by 10 users, show that the recognition accuracy is 95.52%. The Motionword algorithm is capable of achieving accurate activity recognition results without additional hardware cost or power consumption.
Walking is the most easily achievable way to reduce obesity and to keep fit. Step counting device... more Walking is the most easily achievable way to reduce obesity and to keep fit. Step counting devices are helpful for users to develop regular walking habits, but they may mistake some abnormal situations (SHAKING, SWING, JITTER, PENDULUM, etc.) for walking and thus result in step counting errors. Such errors will inflate the number of steps, and lead to biased inter-user comparisons or competitions. To fix the problem, we developed an effective algorithm to detect abnormal step counting, which extract 13 non-directional features from acceleration data, and feed them into OneClass Support Vector Machine (OCSVM) to check wether it is abnormal. The detection algorithm has been tested on a dataset composed of 500 minutes real world data, which is captured by 10 users. It is shown that the proposed algorithm is capable of detecting most of the abnormal situations while not mistaking normal activity (walking/running) for abnormal. While the false alarm rate is 5.08%, the algorithm detects 90.72% of abnormal situations. The AUC (Area Under the Curve) of the proposed algorithm reaches 0.9252, which shows that the algorithm is very effective for abnormal situation detection. Keywords-abnormal step-counting detection; OCSVM; Nondirectional Feature Extraction;
ABSTRACT This paper presents a new method for remote and interactive browsing of long video seque... more ABSTRACT This paper presents a new method for remote and interactive browsing of long video sequences. The solution is based on interactive navigation in a scalable mega image resulting from a JPEG2000 coded keyframe-based video summary. The presented system is compliant with the new JPEG2000 part 9 "JPIP – JPEG2000 Interactivity, API and Protocol," which lends itself to working under varying channel conditions such as wireless networks. The flexibility offered by JPEG2000 allows the application to highlight interactively keyframes corresponding to the desired content first within a low quality and low-resolution version of the full video summary. It then offers a fine grain scalability for a user to navigate and zoom in to particular scenes or events represented by the keyframes. This possibility to visualise keyframes of interest and playback the corresponding video shots within the context of the whole sequence enables the user to understand the temporal relations between semantically similar events, i.e. a new way to analyse long video sequences.
Network-centric smart video surveillance has witnessed a surge of interest from both diverse busi... more Network-centric smart video surveillance has witnessed a surge of interest from both diverse business sectors and research communities over the last decade. BT's recent transformation from a dominant fixed line Telco in the UK to a leading networked ICT service provider worldwide has spurred our researches in this and allied field so as to provide value-added services and solutions, addressing
The HL7 FHIR is an emerging international standard designed to facilitate the interoperability am... more The HL7 FHIR is an emerging international standard designed to facilitate the interoperability among IT systems of healthcare providers' and other stakeholders'. The implementation of interoperability relies on three key elements: unified data standards, API specifications and the coordinated scheduling. In this paper, we addressed the interoperability between a health community of primary care facilities and county hospitals in China, which usually adopted diversified legacy health IT systems from different vendors over the years. We designed a series of open service FHIR API specifications targeting seven prior applications commonly encountered in such a community, as well as developed an integration service platform (ISPf) to serve these APIs. The seven scenarios included outpatient appointment process, two-way referrals, access to regional LIS, access to regional PACS, retrieval of medical service history, payment request and access to PHR. Each care institution needs to access the ISPf as per open service API specifications. The ISPf provides API authorization, calling and secure management services among healthcare providers. Our work demonstrated an open, flexible, effective and standards complied approach to promoting health IT systems' interoperability to enable tiered and coordinated healthcare services to the great benefit of under-served citizens.
This paper discusses an efficient and effective approach to simultaneously identifying and tracki... more This paper discusses an efficient and effective approach to simultaneously identifying and tracking two free moving and gesturing hands, together with the provision of accurate segmentation masks of the hands regions. It is aimed at a novel application in telepresence video conferencing system. The skin colour model in YUV colour space is created and adapted to characterise the likely appearance of hands. The initialisation is performed on the first two frames of a video stream, and the probabilistic skin colour map and motion mask information are used, resulting in an accurate segmentation of the two initial hands. The ensued tracking uses a set of Kalman filters to predict the centroid, orientation, and sizes of candidate hand objects, from which refinements of hands locations are made. The issue of inter-hands overlap and update of the skin colour model are also properly addressed.
Abstract In this paper. a novel area-hased dense stereo correspondence estimation algorithm is pr... more Abstract In this paper. a novel area-hased dense stereo correspondence estimation algorithm is proposed. The new algorithm. which we call Hierarchical Adaptive Curve Matching or HACM in short. is suitable for stereo imaging of both static and dynamic ...
BACKGROUND In the era of the digital economy, the demand for medical and public health services h... more BACKGROUND In the era of the digital economy, the demand for medical and public health services has soared in recent years, asking for developing innovative healthcare service models. This trend has accelerated the urgency to implement effective and efficient data exchange and service interoperability, which enable coordinated care services among tiered healthcare institutions, improve the quality of oversight of regulators, and provide vast and comprehensive data collection to support clinical medicine and health economics research, thus improving the overall service quality and patient satisfaction. However, the isolated data islands among heterogeneous IT systems have been a significant problem, seriously restricting data sharing and service interoperability capabilities. In this context, HL7 FHIR was formally introduced in 2014 and has since continued evolving. Because of its many advantages, such as a simple data model, flexible exchanging model, and adequate open source tools, this standard has attracted worldwide attention in the healthcare industry and has been adopted and promoted by health systems in the UK, USA, and Canada. OBJECTIVE By investigating and analyzing the latest literature on FHIR from the perspectives of motivations, techniques, and applications, we proposed a general FHIR Practice Guideline (FHIR PG) to facilitate stakeholders in the healthcare ecosystem to both understand the FHIR standard and build interoperable services with ease. METHODS We identified 487 papers from the Web of Science and IEEE databases and selected 85 papers published between January 1, 2020, and July 1, 2022, as the source of investigation. First, we chose to classify these papers into three categories: data standardization, data management, and data interoperation, for each of which we discussed the motivations, techniques, and applications. Then, we proposed a general FHIR PG for the entire FHIR practice process through careful analysis and collation. RESULTS The general FHIR PG clarified the unique roles of all the stakeholders involved, including the Implementation Guides (IGs) standard committee, healthcare IT system vendor, and application developer. And it integrated the data standardization flow, data exchange model, and service implementation approach into a complete practice process. As a result, the general FHIR PG facilitates stakeholders to practice the FHIR standard and design interoperable healthcare services. CONCLUSIONS This paper proposed a general FHIR PG by discussing the process of data standardization, data management, and data interoperation from the latest literature. The general FHIR PG can help a stakeholder in the healthcare ecosystem to identify its unique roles, manage the scope of responsibilities, and plan the work content, thereby facilitating the implementation and promotion of the FHIR standard.
Abstract In this paper we present an effective real-time video surveillance system suitable for a... more Abstract In this paper we present an effective real-time video surveillance system suitable for a wide range of outdoor application scenarios. By carefully addressing unique challenges of outdoor scenes such as frequent illumination change and complex object motion etc., this ...
In this chapter we have discussed the recent trend in developing an advanced videoconferencing sy... more In this chapter we have discussed the recent trend in developing an advanced videoconferencing system that moves towards being a seamless integration of a real and virtual world environment with high-quality 3-D telepresence, while focusing on outlining the scope of research work and software system architecture for the VIRTUE project. The entire VIRTUE system design is flexible and conceived largely on the basis of exploiting state-of-the-art technologies in the computer vision, and image and video processing fields guided by the results of human factor studies, rather than physically placing multiple displays, cameras and human subjects. Specifically, we have chosen to demonstrate a core component for 3-D scene analysis, an efficient technique for robust disparity estimation from stereos of still and dynamic scenes, and its application in 3-D visualisation and videoconferencing applications when employing an image-based rendering approach for reconstructing new (and temporarily coherent) virtual views.
The ability to recognize physical activity, such as sedentary, driving, riding, daily activities ... more The ability to recognize physical activity, such as sedentary, driving, riding, daily activities and effective training, is useful for health conscious users to catalogue their daily activities and to develop good exercise routines. Conventional activity recognition algorithms require complex calculations, which are not suitable for wearable devices developed on low-cost, low-power hardware platforms. In this paper, inspired by the text mining related work, we design a novel activity recognition algorithm, which is named “Motionword”. In the wearable device proper, a lightweight recognition algorithm is adopted to compute in real-time predefined atomic events, and count the frequency that these events occur, resulting in a data summary, and then the data summary is transmitted to the platform. On the platform, intelligent method is used to identify and categorize the user's main activity into 5 classes. The test results on a dataset composed of 110 user∗day real world data, contributed by 10 users, show that the recognition accuracy is 95.52%. The Motionword algorithm is capable of achieving accurate activity recognition results without additional hardware cost or power consumption.
Walking is the most easily achievable way to reduce obesity and to keep fit. Step counting device... more Walking is the most easily achievable way to reduce obesity and to keep fit. Step counting devices are helpful for users to develop regular walking habits, but they may mistake some abnormal situations (SHAKING, SWING, JITTER, PENDULUM, etc.) for walking and thus result in step counting errors. Such errors will inflate the number of steps, and lead to biased inter-user comparisons or competitions. To fix the problem, we developed an effective algorithm to detect abnormal step counting, which extract 13 non-directional features from acceleration data, and feed them into OneClass Support Vector Machine (OCSVM) to check wether it is abnormal. The detection algorithm has been tested on a dataset composed of 500 minutes real world data, which is captured by 10 users. It is shown that the proposed algorithm is capable of detecting most of the abnormal situations while not mistaking normal activity (walking/running) for abnormal. While the false alarm rate is 5.08%, the algorithm detects 90.72% of abnormal situations. The AUC (Area Under the Curve) of the proposed algorithm reaches 0.9252, which shows that the algorithm is very effective for abnormal situation detection. Keywords-abnormal step-counting detection; OCSVM; Nondirectional Feature Extraction;
ABSTRACT This paper presents a new method for remote and interactive browsing of long video seque... more ABSTRACT This paper presents a new method for remote and interactive browsing of long video sequences. The solution is based on interactive navigation in a scalable mega image resulting from a JPEG2000 coded keyframe-based video summary. The presented system is compliant with the new JPEG2000 part 9 "JPIP – JPEG2000 Interactivity, API and Protocol," which lends itself to working under varying channel conditions such as wireless networks. The flexibility offered by JPEG2000 allows the application to highlight interactively keyframes corresponding to the desired content first within a low quality and low-resolution version of the full video summary. It then offers a fine grain scalability for a user to navigate and zoom in to particular scenes or events represented by the keyframes. This possibility to visualise keyframes of interest and playback the corresponding video shots within the context of the whole sequence enables the user to understand the temporal relations between semantically similar events, i.e. a new way to analyse long video sequences.
Network-centric smart video surveillance has witnessed a surge of interest from both diverse busi... more Network-centric smart video surveillance has witnessed a surge of interest from both diverse business sectors and research communities over the last decade. BT's recent transformation from a dominant fixed line Telco in the UK to a leading networked ICT service provider worldwide has spurred our researches in this and allied field so as to provide value-added services and solutions, addressing
The HL7 FHIR is an emerging international standard designed to facilitate the interoperability am... more The HL7 FHIR is an emerging international standard designed to facilitate the interoperability among IT systems of healthcare providers' and other stakeholders'. The implementation of interoperability relies on three key elements: unified data standards, API specifications and the coordinated scheduling. In this paper, we addressed the interoperability between a health community of primary care facilities and county hospitals in China, which usually adopted diversified legacy health IT systems from different vendors over the years. We designed a series of open service FHIR API specifications targeting seven prior applications commonly encountered in such a community, as well as developed an integration service platform (ISPf) to serve these APIs. The seven scenarios included outpatient appointment process, two-way referrals, access to regional LIS, access to regional PACS, retrieval of medical service history, payment request and access to PHR. Each care institution needs to access the ISPf as per open service API specifications. The ISPf provides API authorization, calling and secure management services among healthcare providers. Our work demonstrated an open, flexible, effective and standards complied approach to promoting health IT systems' interoperability to enable tiered and coordinated healthcare services to the great benefit of under-served citizens.
Uploads
Papers by Li-Qun Xu