Hyperspectral remote sensing is becoming an active research field in the last decades thanks to the availability of efficient machine learning algorithms and also to the ever-increasing computation power. However, the...
详细信息
ISBN:
(纸本)9781509061822
Hyperspectral remote sensing is becoming an active research field in the last decades thanks to the availability of efficient machine learning algorithms and also to the ever-increasing computation power. However, there exist application domains (e.g., embedded applications) in which the deployment of this kind of systems becomes unfeasible due to the high requirements related to the size, power consumption or processing speed. A way to overcome this trouble consists on using any method able to scale-down the dimensionality of the problem and/or to reduce the complexity of the machine learning models. In this paper, we propose the use of a multiobjective genetic algorithm to minimize both the dimension of the input space and the size of the machine learning model. In particular, we have developed a hyperspectral image classifier based on an Extreme Learning Machine (ELM) for which the number of system inputs (dimensionality) and the number of hidden neurons are minimized without decreasing its performance. The system is evaluated by using a known benchmark dataset.
In the paper we present a method for increasing the quality of views synthesized with typical Depth-image-Based Rendering (DIBR) view synthesis algorithms. In the proposed idea the resolution of input real views and c...
详细信息
ISBN:
(纸本)9781509063451
In the paper we present a method for increasing the quality of views synthesized with typical Depth-image-Based Rendering (DIBR) view synthesis algorithms. In the proposed idea the resolution of input real views and corresponding depth maps is doubled before the view synthesis. After the synthesis, the resolution of a synthesized view is downsampled back to the original resolution. This approach is transparent for the view synthesis algorithms, thus can be used with any DIBR method. In the paper, tests for two synthesis algorithms (the state-of-the-art MPEG reference software and our view synthesis method) are presented. For both algorithms, the proposed upsampling improves objective and subjective quality of synthesized views.
Extracranial robotic radiotherapy employs external markers and a correlation model to trace the tumor motion caused by the respiration. The real-time tracking of tumor motion however requires a prediction model to com...
详细信息
ISBN:
(纸本)9781509028092
Extracranial robotic radiotherapy employs external markers and a correlation model to trace the tumor motion caused by the respiration. The real-time tracking of tumor motion however requires a prediction model to compensate the latencies induced by the software (image data acquisition and processing) and hardware (mechanical and kinematic) limitations of the treatment system. A new prediction algorithm based on local receptive fields extreme learning machines (pLRF-ELM) is proposed for respiratory motion prediction. All the existing respiratory motion prediction methods model the non-stationary respiratory motion traces directly to predict the future values. Unlike these existing methods, the pLRF-ELM performs prediction by modeling the higher-level features obtained by mapping the raw respiratory motion into the random feature space of ELM instead of directly modeling the raw respiratory motion. The developed method is evaluated using the dataset acquired from 31 patients for two horizons in-line with the latencies of treatment systems like CyberKnife. Results showed that pLRF-ELM is superior to that of existing prediction methods. Results further highlight that the abstracted higher-level features are suitable to approximate the nonlinear and non-stationary characteristics of respiratory motion for accurate prediction.
This paper investigates the traffic flow characteristics of mixed stream of autonomous and human-driven vehicles. The proposed model aims at understanding the fundamental properties of mixed flow of human-driven (N) a...
详细信息
ISBN:
(纸本)9781509064847
This paper investigates the traffic flow characteristics of mixed stream of autonomous and human-driven vehicles. The proposed model aims at understanding the fundamental properties of mixed flow of human-driven (N) and autonomous vehicles (AV) such as headway, capacity, and delay at signalized intersections. This is challenging because of intrinsic differences between longitudinal driving characteristics of these two types of vehicles and the convoluted dynamics of car following situation within various combinations of AV and human-driven vehicles. The expected headway of the mixed flow is determined based on the penetration rate of AV and the headways between two successive AV-AV, AV-N, N-AV, and N-N. Furthermore, the upper and lower bounds of mixed flow headway is presented. The theoretical headway is validated by microsimulation data. The estimated headways are then incorporated to derive the delay of a mixed flow at a signalized 2-lane link. Four combination of (i) mixed lanes, (ii) dedicated lanes for AV and human-driven vehicles, (iii) one mixed lane and one AV dedicated lane, and (iv) one mixed lane and one human-driven vehicle dedicated lane are considered. The results demonstrate the performance of the four lane configurations for various stages of AV deployment penetration rate.
In this paper, imageprocessingalgorithms are designed using high level synthesis and implemented on different hardware platforms. These implementations are compared in terms of speed, latency and resource utilizatio...
详细信息
ISBN:
(纸本)9781538639016
In this paper, imageprocessingalgorithms are designed using high level synthesis and implemented on different hardware platforms. These implementations are compared in terms of speed, latency and resource utilization on various hardware platforms. The use of pipelining to reduce the latency is illustrated with an example. Using high level synthesis the designer has the opportunity to employ libraries similar to OpenCV and can take advantage of the productivity benefits of working at a higher level of abstraction, while creating high-performance hardware. Basic imageprocessingalgorithms like calculating histogram, histogram equalization, averaging filter and laplacian filter are chosen to explain hardware acceleration using high level synthesis. The workflow of implementing high level C / C++ / SystemC code in hardware using Vivado high level synthesis tool is explained along with implementation results of various imageprocessingalgorithms.
The proceedings contain 49 papers. The topics discussed include: models and approaches for the safety and the security of distributed systems;redesign CloudRAID for flexible and secure enterprise file sharing over pub...
ISBN:
(纸本)9781450353038
The proceedings contain 49 papers. The topics discussed include: models and approaches for the safety and the security of distributed systems;redesign CloudRAID for flexible and secure enterprise file sharing over public cloud storage;a universal user revocation scheme with key-escrow resistant for Ciphertext-policy attribute-based access control systems;an enhanced parallel version of RSA public key crypto based algorithm using OpenMP;a model of a secure electronic voting system based on blind intermediaries using Russian cryptographic algorithms;privacy preserving two-server Diffie-Hellman key exchange protocol;attribute-based approach of defining the secure behavior of automata objects;network security architectures for VANET;tamperproof complex event processing in IoT devices using side channel information;integer overflow vulnerabilities detection in software binary code;a novel malware analysis for malware detection and classification using machine learning algorithms;collaborative representation of Grassmann manifold projection metric for robust multi-spectral face recognition;extended multi-spectral imaging for gender classification based on image set;parameters of the two-stage synchronization algorithm for the quantum key distribution system;abnormal leakage of energy in battery-based IoT-devices;a framework for data security in the cloud using collaborative intrusion detection scheme;and integration of role based access control with homomorphic cryptosystem for secure and controlled access of data in cloud.
Rheumatic Fever and Rheumatic Heart Disease remain a major burden among children in developing countries. Echocardiography with colour flow Doppler is key to early diagnosis. However, the technique requires time and e...
详细信息
ISBN:
(纸本)9789897582158
Rheumatic Fever and Rheumatic Heart Disease remain a major burden among children in developing countries. Echocardiography with colour flow Doppler is key to early diagnosis. However, the technique requires time and experienced operators, which are scarce resources in the affected areas. Automatic segmentation of colour Doppler regurgitation jets could, potentially, reduce the cost of screening, and spread diagnostic accessibility for a larger number of patients. Ultrasound processing is very challenging due to speckle noise and similarity of representation of all kinds of tissue. Region-based active contours are suitable tools for the segmentation in cases of intensity heterogeneities, which makes them interesting algorithms for left atrium segmentation. HSV colour space describes colour in terms of hues and saturation, which may facilitate the translation of medical interpretation of the Doppler pseudo-colour into mathematical expression for colour segmentation. A total of 979 frames from 20 sequences were manually annotated and used to validate the proposed pipeline. Overall, the results for colour pattern segmentation are promising (sensitivity=0.91 false detection rate=0.10), but further developments are required for the atrium segmentation (sensitivity=0.80, false detection rate=0.28).
Optical metrology using phase measurements has benefited significantly from the introduction of phase-shifting methods, first in interferometry, then also in fringe projection and fringe reflection. As opposed to inte...
详细信息
ISBN:
(纸本)9781510611047;9781510611030
Optical metrology using phase measurements has benefited significantly from the introduction of phase-shifting methods, first in interferometry, then also in fringe projection and fringe reflection. As opposed to interferometry, the latter two techniques generally use a spatiotemporal phase-shifting approach: A sequence of fringe patterns with varying spacing is used, and a phase map of each is generated by temporal phase shifting, to allow unique assignments of projector or screen pixels to camera pixels. One ubiquitous problem with phase-shifting structured-light techniques is that phase artefacts appear near regions of the image where the modulation amplitude of the projected or reflected fringes changes abruptly, e. g. near dirt/dust particles on the surface in deflectometry or bright-dark object colour transitions in fringe projection. Near the bright-dark boundaries, responses in the phase maps appear that are not plausible as actual surface features. The phenomenon has been known for a long time but is usually ignored because it does not compromise the overall reliability of results. In deflectometry, however, often the objective is to find and classify small defects, and of course it is then important to distinguish between bogus phase responses caused by fringe modulation changes, and actual surface defects. We present, for what we believe is the first time, an analytical derivation of the error terms, study the parameters influencing the phase artefacts (in particular the fringe period), and suggest some simple algorithms to minimise them.
On the basis of the evaluation of local properties of the data many nonlinear techniques have been suggested the field of computer vision. The application of the dimensionality reduction covers many fields like medica...
详细信息
ISBN:
(纸本)9781509027170
On the basis of the evaluation of local properties of the data many nonlinear techniques have been suggested the field of computer vision. The application of the dimensionality reduction covers many fields like medical, geographical, simulation and many more. I have studied MDS, LLE and LTSA. Overall, the users a re allowed to access the search-tools in linear system. A review and systematic comparison of all the existing techniques has been presented in this paper. The outputs have been explained through identification of current non-linear techniques, and suggestions pertaining to the way the performance of nonlinear dimensionality reduction techniques can be improved. The Purpose of this idea is based on the to implement it in manifold fields by analyzing the result of face detector and recognizer for multiple people in real time with Principal Component analysis on eigen face. According to the most recent research, some issues are confronted in the security at public places. The efficiency and accuracy of these problems can be improved with the range and intricacy of camera networks are booming and the audited surroundings have become more and more entangled and crowded. How these emerging challenges are faced is discussed in the paper.
Digital watermarking is an efficient method for digital access rights management utilized in the scope of multimedia data. A possibility to combine the procedure of compression and watermarking in effective way for di...
详细信息
暂无评论