The article is focused on a particular aspect of classification, namely the issue of class imbalance. Imbalanced data adversely affects the recognition ability and requires proper classifier’s construction. In this w...
详细信息
This paper presents a novel, drastically simplified method to compute optic flow on a miniaturized embedded vision system, suitable on-board of miniaturized indoor flying robots. Estimating optic flow is a common tech...
详细信息
ISBN:
(纸本)9781467396769
This paper presents a novel, drastically simplified method to compute optic flow on a miniaturized embedded vision system, suitable on-board of miniaturized indoor flying robots. Estimating optic flow is a common technique for robotic motion stabilization in systems without ground contact, such as unmanned aerial vehicles (UAVs). Because of high computing power requirements to process video camera data, most optic flow algorithms are implemented off-board on PCs or on dedicated hardware, connected through tethered or wireless links. Here, in contrast, we present a miniaturized stand-alone embedded system that utilizes a novel neuro-biologically inspired event-based vision sensor (DVS) to extract optic flow on-board in real-time with minimal computing requirements. The DVS provides asynchronous events that resemble temporal contrast changes at individual pixel level, instead of full image frames at regular time intervals. Such a representation provides high temporal resolution while simultaneously reducing the amount of data to be processed. We present a simple algorithm to extract optic flow information from such event-based vision data, which is sufficiently efficient in terms of data storage and processing power to be executed on an embedded 32bit ARM7 microcontroller in real-time. The developed stand-alone system is small, lightweight and energy efficient, and is ready to serve as sensor for ego motion estimates based on optic flow in autonomous UAVs.
The paper discusses the conditions for the development of the combustion process control system and presents an algorithm to optimize the boiler operation based on information obtained from conventional instrumentatio...
详细信息
ISBN:
(纸本)9788362065189
The paper discusses the conditions for the development of the combustion process control system and presents an algorithm to optimize the boiler operation based on information obtained from conventional instrumentation and incorporate model reference control scheme to assess the quality of the process, Comparative studies between two simulated MRAC systems show that neural adaptive control may mitigate disturbances on the system outputs,
A detailed simulative and experimental analysis of different CPE schemes for 64-QAM systems is presented. The best compromise between linewidth tolerance and complexity is achieved using a recently proposed multi-stag...
详细信息
ISBN:
(纸本)9781479930661
A detailed simulative and experimental analysis of different CPE schemes for 64-QAM systems is presented. The best compromise between linewidth tolerance and complexity is achieved using a recently proposed multi-stage architecture, based on a modification of the standard V&V algorithm.
Shape sensing, where the shape of an object is estimated using fiber optical Fiber Bragg Grating (FBG) sensors, has gained increasing popularity in the last years. While the production process and the applications are...
详细信息
ISBN:
(纸本)9781479967315
Shape sensing, where the shape of an object is estimated using fiber optical Fiber Bragg Grating (FBG) sensors, has gained increasing popularity in the last years. While the production process and the applications are different for the various research groups, the basic principle of shape sensing is the same: at certain cross-sections along the observed object, the information of three strain measurements is merged to one curvature information, and the information of these curvatures is then used to estimate the shape with various mathematical theories, depending on the application. Some effort has been made to calibrate and determine the accuracy of the shape sensor, but research on the influence of bad positioning of the Fiber Bragg Gratings seems relatively unattended. In this paper, one aspect of bad FBG positioning, namely inaccurate placement of the FBGs within one cross-section, and its influence on the reconstruction results is investigated. Furthermore, a modified approach for the reconstruction algorithm is presented, improving the reconstruction results for bad FBG placement compared to the conventional approach.
We propose digital-signal-processingalgorithms that achieve fast decoding and LLR-computation for high-order set-partitioned 4D-QAM formats based on their parity-check functions. Computer-simulation results show that...
详细信息
We propose digital-signal-processingalgorithms that achieve fast decoding and LLR-computation for high-order set-partitioned 4D-QAM formats based on their parity-check functions. Computer-simulation results show that computational complexity of the decoder can significantly be reduced with negligible power penalty using such algorithms.
Compressive spectral imaging captures the spatial and spectral information of a scene using a set of two-dimensional random projections. Compressed sensing reconstruction algorithms are then used to recover the underl...
详细信息
ISBN:
(纸本)9781479928934
Compressive spectral imaging captures the spatial and spectral information of a scene using a set of two-dimensional random projections. Compressed sensing reconstruction algorithms are then used to recover the underlying threedimensional source. This work presents a new generation of devices that attain compressive spectral image measurements by means of a colored-patterned detector and a dispersive element. Simulations show that these new generation devices can recover spectral scenes with up to 5 dB gain in PSNR with respect to traditional Coded Aperture Snapshot Spectral Imaging (CASSI) systems.
The paper shows the application of election algorithms in networks of comparators. We have described and adopted six election methods which have been used as an aggregator of partial results. We have performed experim...
详细信息
opticalinformationprocessingsystems have been widely applied, this paper studies the calculation of the amount of a reduction in the use of genetic algorithms to increase the diversity of the sample algorithm to re...
详细信息
We propose and numerically investigate an improved decision directed (IDD) carrier phase estimation (CPE) to mitigate fiber nonlinearity in 16 quadrature amplitude modulation (QAM) coherent transmission systems. The p...
详细信息
ISBN:
(纸本)9781479956012
We propose and numerically investigate an improved decision directed (IDD) carrier phase estimation (CPE) to mitigate fiber nonlinearity in 16 quadrature amplitude modulation (QAM) coherent transmission systems. The proposed IDD-CPE algorithm is derived based on a two stage approach and compared with other CPE algorithms namely, the pre-decision directed (PDD) CPE and the decision directed (DD) phase locked loop (PLL). By exploiting the symbol position information in the I-Q plane and a euclidean distance measure, the proposed IDD-CPE algorithm outperforms the PDD-CPE and DD-PLL methods, exhibiting an optimal performance at signal launch power of 0 dBm and at optical signal to noise ratios (OSNRs) greater than 28dB, where no bit errors are detected.
暂无评论