In spite of extensive research in the last decade, activity recognition still faces many challenges for real-world applications. On one hand, when attempting to recognize various activities, different sensors play dif...
详细信息
ISBN:
(纸本)9781631900242
In spite of extensive research in the last decade, activity recognition still faces many challenges for real-world applications. On one hand, when attempting to recognize various activities, different sensors play different on different activity classes. This heterogeneity raises the necessity of learning the optimal combination of sensor modalities for each activity. On the other hand, users may consistently or occasionally annotate activities. To boost recognition accuracy, we need to incorporate the user input and incrementally adjust the model. To tackle these challenges, we propose an adaptive activity recognition with dynamic heterogeneous sensorfusion framework. We dynamically fuse various modalities to characterize different activities. The model is consistently updated upon arrival of newly labeled data. To evaluate the effectiveness of the proposed framework, we incorporate it into popular feature transformation algorithms, e.g., Linear Discriminant Analysis, Marginal Fisher's Analysis, and Maximum Mutual Information in the proposed framework. Finally, we carry out experiments on a real-world dataset collected over two weeks. The result demonstrates the practical implication of our framework and its advantage over existing approaches.
Digital Musical Instruments (DMIs) are musical instruments typically composed of a control surface where user interaction is measured by sensors whose values are mapped to sound synthesis algorithms. These instruments...
详细信息
Digital Musical Instruments (DMIs) are musical instruments typically composed of a control surface where user interaction is measured by sensors whose values are mapped to sound synthesis algorithms. These instruments have gained interest among skilled musicians and performers in the last decades leading to artistic practices including musical performance, interactive installations and dance. The creation of DMIs typically involves several areas, among them: arts, design and engineering. The balance between these areas is an essential task in DMI design so that the resulting instruments are aesthetically appealing, robust, and allow responsive, accurate and repeatable sensing. In this paper, we review the use of sensors in the DMI community as manifested in the proceedings of the International conference on New Interfaces for Musical Expression (NIME 2009-2013). Focusing on the sensor technologies and signal conditioning techniques used by the NIME community. Although it has been claimed that specifications for artistic tools are harder than those for military applications, this study raises a paradox showing that in most of the cases, DMIs are based on a few basic sensors types and unsophisticated engineering solutions, not taking advantage of more advanced sensing, instrumentation and signal processing techniques that could dramatically improve their response. We aim to raise awareness of limitations of any engineering solution and to assert the benefits of advanced electronics instrumentation design in DMIs. For this, we propose the use of specialized sensors such as strain gages, advanced conditioning circuits and signal processing tools such as sensorfusion. We believe that careful electronic instrumentation design may lead to more responsive instruments.
Location-based applications require knowing the user position constantly in order to find out and provide information about user's context. They use GPS signals to locate users, but unfortunately GPS location syst...
详细信息
ISBN:
(纸本)9783319036113
Location-based applications require knowing the user position constantly in order to find out and provide information about user's context. They use GPS signals to locate users, but unfortunately GPS location systems do not work in indoor environments. Therefore, there is a need of new methods that calculate the location of users in indoor environments using smartphone sensors. There are studies that propose indoor positioning systems but, as far as we know, they neither run on Android devices, nor can work in real environments. The goal of this chapter is to address that problem by presenting two methods that estimate the user position through a smartphone. The first method is based on euclidean distance and use Received Signal Strength (RSS) from WLAN Acces Points present in buildings. The second method uses sensorfusion to combine raw data of accelerometer and magnetometer inertial sensors. An Android prototype that implements both methods has been created and used to test both methods. The conclusions of the test are that RSS technique works efficiently in smartphones and achieves to estimate the position of users well enough to be used in real applications. On the contrary, the test results show that sensorfusion technique can be discarded due to bias errors and low frequency readings from accelerometers sensor.
Recent remote sensing applications require sensors that provide both high spatial and spectral resolution, but this is often not possible for economic and constructive reasons. The "fusion" of images at diff...
详细信息
ISBN:
(纸本)9781628413076
Recent remote sensing applications require sensors that provide both high spatial and spectral resolution, but this is often not possible for economic and constructive reasons. The "fusion" of images at different spatial and spectral resolution is a method widely used to solve this problem. Pan-sharpening techniques have been applied in this work to simulate PRISMA images. The work presented here is indeed part of the Italian Space Agency project "ASI-AGI", which includes the study of a new platform, PRISMA, consisting of an hyperspectral sensor with a spatial resolution of 30 m and a panchromatic sensor with a spatial resolution of 5 m, for monitoring and understanding the Earth's surface. Firstly, PRISMA images have been simulated using images from MIVIS and Quickbird sensors. Then several existing fusion methods have been tested in order to identify the most suitable for the platform PRISMA in terms of spatial and spectral information preservation. Both standard and wavelet algorithms have been used: among the former there are Principal Component Analysis and Gram-Schmidt transform, and among the latter are Discrete Wavelet Transform and the "a trous" wavelet transform. Also the Color Normalized Spectral Sharpening method has been used. Numerous quality metrics have been used to evaluate spatial and spectral distortions introduced by pan-sharpening algorithms. Various strategies can be adopted to provide a final rank of alternative algorithms assessed by means of a battery of quality indexes. All implemented statistics have been standardized and then three different methodologies have been used to achieve a final score and thus a classification of pan-sharpening algorithms. Currently a new protocol is under development to evaluate the preservation of spatial and spectral information in fusion methods. This new protocol should overcome the limitations of existing alternative approaches and be robust to changes in the input dataset and user-defined parameters.
Thank to the widespread diffusion of RGBD sensing devices based on active technologies, in recent years, many research and industrial applications have taken advantage of reliable cues computed from dense depth data. ...
详细信息
ISBN:
(纸本)9781450329255
Thank to the widespread diffusion of RGBD sensing devices based on active technologies, in recent years, many research and industrial applications have taken advantage of reliable cues computed from dense depth data. However, although these sensors can be very effective in many circumstances, they are not always well suited for outdoor environments and can also interfere with each other when sensing the same area. On the other hand, traditional systems based on passive stereo vision technology, due to their computational/energy requirements, reliability, size, cost etc, have been, so far, mostly confined to research projects. Nevertheless, recent advances in computation architectures and algorithms enable to overcome most of these issues and, in this paper, we describe the architecture and the processing pipeline of an effective RGBD sensor based on stereo vision suited for real time applications. This sensor allows us to infer, in indoor and outdoor environments, dense and accurate depth maps computed according to state-of-art algorithms and with minimal energy requirements that fit with typical constraints of smart camera systems.
Image stabilization is relevant for various industrial and medical applications. In particular, we consider the use of image stabilization in robotic beating heart surgery. A robot, which is remotely controlled by the...
详细信息
ISBN:
(纸本)9781479916344
Image stabilization is relevant for various industrial and medical applications. In particular, we consider the use of image stabilization in robotic beating heart surgery. A robot, which is remotely controlled by the surgeon, can automatically compensate for the motion of the beating heart. To give the surgeon the illusion of operating on a stationary heart, a stabilized image of the beating heart is shown to the surgeon. Image stabilization cancels the unwanted motion of the heart, but retains changes to color and texture, for example cuts on the heart surface. In this paper, stabilization is first considered as a 2D image transformation problem. Subsequently, it is extended to stabilization of a 3D point cloud or surface. The proposed algorithms are evaluated in both ex-vivo and in-vivo experiments. In the evaluation, the stabilization quality achievable with several common interpolation functions is compared.
The proceedings contain 12 papers. The topics discussed include: Bayesian tracking and multi-core beamforming for estimation of correlated brain sources;particle filtering for network-based positioning terrestrial rad...
ISBN:
(纸本)9781849198639
The proceedings contain 12 papers. The topics discussed include: Bayesian tracking and multi-core beamforming for estimation of correlated brain sources;particle filtering for network-based positioning terrestrial radio networks;tracking simulated UAV swarms using particle filters;rectangular extended object tracking with box particle filter using dynamic constraints;probabilistic step and turn detection in indoor localization;fusing kinect sensor and inertial sensors with multi-rate kalman filter;piecewise constant sequential importance sampling for fast particle filtering;hybrid gauss-hermite filter;regional variance in target number: analysis and application for multi-Bernoulli point processes;combined evidential data association;and PHD filtering in presence of highly structured sea clutter process and tracks with extent.
In this paper, we propose to use information theory to automatically select the best sensors in a Ultra Wide Band (UWB) Radar sensor Networks (RSN) to detect target in foliage environment. Information theoretic algori...
详细信息
ISBN:
(纸本)9783319077826;9783319077819
In this paper, we propose to use information theory to automatically select the best sensors in a Ultra Wide Band (UWB) Radar sensor Networks (RSN) to detect target in foliage environment. Information theoretic algorithms such as entropy and mutual information are proven methods that can be applied to data collected by various sensors for target detection. However, the complexity of the environment brings uncertainty in fusion center and the big data collected by sensors can have huge processing load. In this paper, we propose to use another information theoretical criterion known as Chernoff information that can provide the best error exponent of detection in Bayesian approach. We also used Chernoff Stein Lemma for fusing the data to optimize the performance. The performance of the algorithm was evaluated, based on real world data. Results show that our opportunistic sensing (OS) algorithm does efficient utilization of sensing assets and provide same performance while it is compared with the existing method without OS.
Parallel and Distributed Processing Techniques and applications is a compendium of articles and papers that were presented at PDPTA '13, an international conference that serves researchers, scholars, professionals...
ISBN:
(纸本)9781601322586
Parallel and Distributed Processing Techniques and applications is a compendium of articles and papers that were presented at PDPTA '13, an international conference that serves researchers, scholars, professionals, students, and academicians. Hamid R. Arabnia, Hiroshi Ishii, Minoru Ito, Hiroaki Nishikawa, Fernando G. Tinetti, George A. Gravvanis, George Jandieri, and Ashu M. G. Solo (Editors) Selected topics include parallel and distributed algorithms and applications, mathematical modeling and problem solving, and grid + cloud computing and supporting tools + applications, etc. Selected Sessions and Topics for example: Resource Allocation, Scheduling, Energy-Aware Computing + Load-Balancing + Fault-Tolerant Systems Parallel and Distributed algorithms and applications Mathematical Modeling and Problem Solving - MPS Grid + Cloud Computing and Supporting Tools + applications Systems Software + Programming Models + Threads + Caching + File Systems + Testing and Monitoring Methods Performance Evaluation, Estimation, and Related Issues Communication Systems + Networks and Interconnection Networks + Peer-To-Peer Networks Ad-Hoc Networks + sensor Networks and applications Cluster Computing + Multi-Core, GPU, FPGA Processing and applications Data-Driven Networking Systems with High Tolerance for Disaster, Fault and Congestion Position and Regular - Communication Systems, Cloud Computing, Reconfigurable Systems, Parallel and Distributed Computing, Scheduling, architectures, and applications Cloud Computing, Optimization, sensor Networks, Scheduling, and applications
Real-time orientation estimation based on mobile, low-power hardware platforms requires customized processor cores or dedicated hardware accelerators to achieve the throughput requirements demanded by applications lik...
详细信息
暂无评论