The discrete-time double-integrator consensus and rendezvous problems are both addressed for distributed multiagent systems with directed switching topologies and input *** develop model predictive control algorithms ...
详细信息
ISBN:
(纸本)9781479947249
The discrete-time double-integrator consensus and rendezvous problems are both addressed for distributed multiagent systems with directed switching topologies and input *** develop model predictive control algorithms to achieve stable consensus or rendezvous provided that the proximity nets always have a directed spanning tree and the sampling period is sufficiently ***,the control horizon is extended to larger than one as well,which endows sufficient degrees of freedom to facilitate controller *** simulations are finally conducted to show the effectiveness of the control algorithms.
Optic disc (OD) is an important part of the eye. OD detection is an important step in developing systems for automated diagnosis of various serious ophthalmic diseases like Diabetic retinopathy, Glaucoma, hypertension...
详细信息
Optic disc (OD) is an important part of the eye. OD detection is an important step in developing systems for automated diagnosis of various serious ophthalmic diseases like Diabetic retinopathy, Glaucoma, hypertension etc. The variation of intensity within the optic disc and intensity close to the optic disc boundary are the major hurdle in automated optic disc detection. General edge detection algorithms are frequently unsuccessful to segment the optic disc because of this. Complexity increases due to the presence of blood vessels. This paper presents simple method for OD segmentation by using techniques like principal component analysis (PCA), mathematical morphology and Watershed Transform. PCA used for good presentation of input image and mathematical morphology is used to remove blood vessels from image. Watershed Transform is used for boundary segmentation.
The present book is based on the research papers presented in the International Conference on Soft Computing for Problem Solving (SocProS 2012), held at JK Lakshmipat University, Jaipur, India. This book provides the ...
ISBN:
(数字)9788132216018;9788132216025
ISBN:
(纸本)9788132216018;9788132216025
The present book is based on the research papers presented in the International Conference on Soft Computing for Problem Solving (SocProS 2012), held at JK Lakshmipat University, Jaipur, India. This book provides the latest developments in the area of soft computing and covers a variety of topics, including mathematical modeling, imageprocessing, optimization, swarm intelligence, evolutionary algorithms, fuzzy logic, neural networks, forecasting, data mining, etc. The objective of the book is to familiarize the reader with the latest scientific developments that are taking place in various fields and the latest sophisticated problem solving tools that are being developed to deal with the complex and intricate problems that are otherwise difficult to solve by the usual and traditional methods. The book is directed to the researchers and scientists engaged in various fields of Science and Technology.
The Deep Spatio-Temporal Inference Network (DeSTIN) is a deep learning architecture which combines unsupervised learning and Bayesian inference. The original version of DeSTIN incorporates k-means clustering inside ea...
详细信息
ISBN:
(纸本)9781479914821
The Deep Spatio-Temporal Inference Network (DeSTIN) is a deep learning architecture which combines unsupervised learning and Bayesian inference. The original version of DeSTIN incorporates k-means clustering inside each processing node. Here we propose to replace k-means with a more sophisticated algorithm, online EM (Expectation Maximization), and show that this improves DeSTIN's performance on image classification and restoration tasks.
Multiplier is one of the primary hardware blocks in modern day digital signal processing (DSP) and communication systems. It is extensively used in DSP and imageprocessing applications such as, Fast Fourier Transform...
详细信息
ISBN:
(纸本)9781479930814
Multiplier is one of the primary hardware blocks in modern day digital signal processing (DSP) and communication systems. It is extensively used in DSP and imageprocessing applications such as, Fast Fourier Transform (FFT), convolution, correlation, filtering and in ALU of microprocessors. Therefore, high speed, low area and power efficient multiplier design remain the critical factors for the overall system. This paper presents high performance and energy efficient implementation of the binary multiplier. The design is based on ancient Indian vedic multiplication process and the low power energy recovery (aka adiabatic logic). The generation of partial sums and products in a single step in the vedic approach and the energy recovery capability of the adiabatic logic together realize high speed and low power operation of the design. A 16X16 vedic multiplier and conventional array multiplier based on the Differential Cascode Pre-resolve Adiabatic Logic (DCPAL) is proposed in the paper. Simulation results validate this design incurring 87.21 percent lesser power than the standard CMOS equivalent design.
Physicians are motivated to use e-health technology. Use of modern technology enables knowledge extraction which can be used to improve diagnostics and treatment. At present Electronic Patient Record (EPR) are also sh...
详细信息
Physicians are motivated to use e-health technology. Use of modern technology enables knowledge extraction which can be used to improve diagnostics and treatment. At present Electronic Patient Record (EPR) are also shared through cloud among hospitals. Protection of EPR is important to protect the ownership particularly when the data is shared with third parties. Digital watermarking is a proven technique to achieve this goal. Digital watermarking technique can be employed for data hiding and to ensure integrity and authenticity of medical image. Considering this broad scope, a fresh and reversible watermarking scheme is recommended to report this safety production. Hospital Logo, Hash of ROI, Doctor Identification Code (DIC) is embedded using Recursive Dither Modulation (RDM) algorithm subsequent to wavelet transform and singular value decomposition. To improve the performance of the scheme differential evolution based optimization technique is proposed. The scheme is reversible and can also perform tamper detection.
We spend more than 80% of our lives indoors. Future indoor robot navigation is based on intelligent systems that provide accurate and smart information. In this paper we introduce a novel Aesthetic Marker decoding sys...
详细信息
ISBN:
(纸本)9781479940318
We spend more than 80% of our lives indoors. Future indoor robot navigation is based on intelligent systems that provide accurate and smart information. In this paper we introduce a novel Aesthetic Marker decoding system, which finds and decodes machine readable visual markers inside buildings. Focused on seamless integration of visual code into our everyday human environment, our application has custom developed algorithms and functions that handle aesthetic marker data. As a result, imageprocessing time was reduced and extracted information was maximized to calculate accurate robot position. A new Aesthetic Marker decoding method was created connecting the digital and physical world.
Obstacle avoidance is a key feature for automotive navigation that requires an accurate representation of the environment. In the field of visual perception this task has often been addressed with stereo algorithms th...
详细信息
ISBN:
(纸本)9781479936397
Obstacle avoidance is a key feature for automotive navigation that requires an accurate representation of the environment. In the field of visual perception this task has often been addressed with stereo algorithms that try to obtain a depth map of the environment via disparity calculations on a single pair of images. These algorithms do not exploit that especially in automotive scenarios the fields of view between two consecutive frames have large overlapping regions. Instead, the disparity map is computed from scratch for each stereo frame and no information is propagated from one frame to the next. Since monocular imageprocessing has long benefited from recursive estimation techniques, such as the 4D Approach, this paper presents a novel recursive automotive stereo algorithm, called RAS. RAS internally maintains a list of recursively estimated 3D points that are continuously updated based on the vehicle's movement and measurements in the current stereo frame. We show that RAS not only preserves the knowledge of the environment across frames, but also accounts for measurement modalities and is robust against faulty or even missing measurements.
The problem of automatic video restoration and object removal attract the attention of many researchers. In this paper we present a new framework for video inpainting. We consider the case when a camera motion is appr...
详细信息
ISBN:
(纸本)9780819494283
The problem of automatic video restoration and object removal attract the attention of many researchers. In this paper we present a new framework for video inpainting. We consider the case when a camera motion is approximately parallel to the plane of image projection. The scene may consist of a stationary background with a moving foreground, both of which may require inpainting. Moving objects can move differently, but should not to change their size. A framework presented in this paper contains the following steps: moving objects identification, moving objects tracking and background/foreground segmentation, inpainting and, finally, a video rendering. Some results on test video sequence processing are presented
暂无评论