To increase the efficiency of the laser coagulation surgery the problem of the most accurate segmentation of fundus images is especially relevant. Fundus image segmentation is carried out with high accuracy using effe...
To increase the efficiency of the laser coagulation surgery the problem of the most accurate segmentation of fundus images is especially relevant. Fundus image segmentation is carried out with high accuracy using effective features and the minimum number of parameters for segmentation of a single image fragment. This paper describes a modified technique for smart textural feature selection to extract retinal regions of interest using image preprocessingalgorithms. Preprocessingalgorithms significantly influence the selected features which provide a minimum error of object recognition. In addition image preprocessingalgorithms provide a more precise object selection. The informativeness of the obtained feature space is studied using discriminant data analysis. The best fragmentation block size segmentation and feature sets provides the necessary accuracy to identify regions of interest. Those regions are determined by the analysis of the following 4 classes of fundus images: exudates, thick, thin vessels and healthy areas. The advantages and disadvantages of the considered preprocessingalgorithms were identified.
This work introduces an Artificial Neuro-Fuzzy Inference System functioning as a selector of color constancy algorithms for the enhancement of dark images. The system selects among three algorithms, the White-Patch, t...
详细信息
ISBN:
(纸本)9781509008704
This work introduces an Artificial Neuro-Fuzzy Inference System functioning as a selector of color constancy algorithms for the enhancement of dark images. The system selects among three algorithms, the White-Patch, the Gray-World and the Gray-Edge according to real content of an image. These three algorithms have been considered due to their simplicity and accurate remotion of the illuminant, further showing an outstanding color enhancement on images. The diverse image features are involved in the selection process, so the design of selector system is not a trivial task. For this reason we developed a fuzzy rule based system to model the information through simple rules. While addressing the problem of dark image enhancement this approach can handle large amount of data and is tolerant to ambiguity.
In this paper, an impulse radio ultra-wideband (IR-UWB) radar is used to continuously monitor a resting subject's respiration and heart rates in a noninvasive fashion in order to observe the corresponding health s...
详细信息
ISBN:
(纸本)9781538631706
In this paper, an impulse radio ultra-wideband (IR-UWB) radar is used to continuously monitor a resting subject's respiration and heart rates in a noninvasive fashion in order to observe the corresponding health status. These two cardiopulmonary vital signs are inferred based on the processing of recorded waveforms that are collected by the IR-UWB radar, after getting reflected-off the resting subject's body. A novel algorithm that processes the recorded waveforms is proposed to extract these vitals' signals and, accordingly, estimate their rates. This algorithm is comprised of three major parts: i) noise reduction, ii) respiration rate extraction, and iii) heart rate extraction. Furthermore, the algorithm addresses the effects of harmonics and intermodulation between the breathing and heartbeat signals without requiring the implementation of filters. Given an alphabet of datasets that are collected on multiple subjects, numerical results are presented to corroborate the proposed algorithm's accuracy.
Practical application of smart materials for moving robots enabled to solve difficult mechatronic positioning and movement problems. Movement in such systems is generated using piezoelectrical devices. Therefore, clas...
详细信息
ISBN:
(纸本)9781538639993
Practical application of smart materials for moving robots enabled to solve difficult mechatronic positioning and movement problems. Movement in such systems is generated using piezoelectrical devices. Therefore, classical trajectories formation and control methods are not suitable. For these specific problems positioning and piezorobot control methods and algorithms are created. In order to practically realize these algorithms a novel software and hardware is needed. This article presents movement formation methods and movement in predefined trajectory on some plane algorithms for cylindrical piezorobot. It is shown how they can be implemented using Matlab and LabVIEW software. Trajectory movement is controlled using special software and specifically designed motion control system. Control signal is amplified by electronics hardware. It also matches industrial PXI computer to piezorobot's motion actuator which requires high voltage signal and capacitance load. The path of piezorobot is registered using imageprocessing and computer vision technologies. The paper presents experimental results of piezorobot movement when different input data set applied. Piezorobot point-to-point movement on plane without rotation is analyzed. Such movement is created when only one electrode is excited at a time. This generates forces at every segment and their cumulative force ensures precise control of piezorobot movement direction and speed.
Detection and identification of vehicles in traffic surveillance videos is very important to automate the surveillance system and also to build an intelligent transportation system. In this paper a robust method to de...
详细信息
ISBN:
(纸本)9781509047611;9781509047604
Detection and identification of vehicles in traffic surveillance videos is very important to automate the surveillance system and also to build an intelligent transportation system. In this paper a robust method to detect and identify vehicles is proposed which deals with problem like change in illumination. Background subtraction is done using both Gaussian Mixture Model and Visual Background Extractor and supports dynamic changes in background. Vehicles are detected by finding contours in the image frame. Vehicles are tracked by assigning unique ID for each vehicles. Distance between the centroid of detected vehicle and existing vehicles is calculated. If the distance is greater than threshold value then vehicle is considered to be arrived newly and a unique ID is assigned for further tracking. Otherwise, it is the vehicle will get the same ID as in previous frame. Detected vehicle is classified using Support Vector Machine in each frame and final decision is taken when the vehicle is about to exit from the scene.
In this paper, we propose a novel supervoxel segmentation method designed for mediastinal lymph node by embedding Hessian-based feature extraction. Starting from a popular supervoxel segmentation method, SLIC, which c...
详细信息
Particle filters are powerful methods for state estimation in nonlinear/non-Gaussian dynamical systems. However due to the heavy computational requirements, they may not satisfy the real-time constraints in many appli...
详细信息
Particle filters are powerful methods for state estimation in nonlinear/non-Gaussian dynamical systems. However due to the heavy computational requirements, they may not satisfy the real-time constraints in many applications requiring a large number of particles. By means of distributed implementation, real-time particle filtering can be achieved. However, the resampling stage in particle filters requires particle interaction which causes communication overhead. In this work, we propose a distributed resampling algorithm based on Butterfly Resampling previously described in the literature. We describe three interaction schemes (i) the complete interaction, (ii) the pairwise interaction where the nodes are constrained to communicate in pairs and (iii) the partial pairwise interaction in which only one pair is allowed to communicate. The goal is to diminish the communication cost in exchange for negligible loss of effective sample size. We conduct experiments on a cluster environment and compare our methods in terms of execution time, communication time and effective sample size. We find that the sparse interaction schemes show better performance for distributed systems and they keep the effective sample size nearly as high as the complete interaction scheme does.
Signal reconstruction from magnitude-only measurements presents a long-standing problem in signal processing. In this contribution, we propose a phase (re)construction method for filter banks with uniform decimation a...
详细信息
Signal reconstruction from magnitude-only measurements presents a long-standing problem in signal processing. In this contribution, we propose a phase (re)construction method for filter banks with uniform decimation and controlled frequency variation. The suggested procedure extends the recently introduced phase-gradient heap integration and relies on a phase-magnitude relationship for filter bank coefficients obtained from Gaussian filters. Admissible filter banks are modeled as the discretization of certain generalized translation-invariant systems, for which we derive the phase-magnitude relationship explicitly. The implementation for discrete signals is described and the performance of the algorithm is evaluated on a range of real and synthetic signals.
Contemporary sensor-based robotic systems tend to use an ad-hoc combination of off-the-shelf components for onboard computational needs. The number and type of sensors present, the number and organization of the onboa...
详细信息
ISBN:
(纸本)9781509064472
Contemporary sensor-based robotic systems tend to use an ad-hoc combination of off-the-shelf components for onboard computational needs. The number and type of sensors present, the number and organization of the onboard processors, and the algorithms utilized for processing high bandwidth real-time sensor data present researchers and designers with a wide range of choices for which they are currently ill-equipped to evaluate the best options. We present a co-simulation framework for sensor-based mobile robots that allows for the power and performance analysis of custom embedded computing platforms for mobile robots with a range of onboard sensors. We demonstrate the utility of our co-simulation framework by analyzing the power and performance tradeoffs for the computational subsystem of a quadrotor unmanned aerial vehicle (UAV) with onboard camera sensor performing imageprocessing tasks while operating in a custom virtual testbed.
The development in computing power highlights some forgotten algorithms, which were neglected because of their complexity and slowness on early computers. One example is the Wavelet-Transformation Profilometry (WTP) o...
详细信息
ISBN:
(纸本)9781509012169
The development in computing power highlights some forgotten algorithms, which were neglected because of their complexity and slowness on early computers. One example is the Wavelet-Transformation Profilometry (WTP) of which successful application is demonstrated in the paper. WTP is a high level signal processing method using orthogonal algorithms for huge datasets. The high performance in quality and running speed makes the described method suitable for medical imageprocessing applications.
暂无评论