In this paper, ultrasound breast image segmentation is improved by using the volumetric data available in neighboring slices. The new algorithm extends the EM/MPM framework to 3D by including pixels from neighboring f...
详细信息
An error-resilient coding scheme is proposed for the transmission of images over unreliable channels. Forward Error Correction is used in conjunction with the error-resilient source coder for the protection of the com...
详细信息
The present paper proposes a hybrid content-based image search and retrieval technique based on the use of the DC coefficient information and the Encoding Cost Map (ECM), extracted from compressed JPEG data. The propo...
详细信息
In this research we considered the development of a system for automatically detecting and reporting traffic accidents at intersections. A system with these properties would be a great benefit in determining the cause...
详细信息
In this research we considered the development of a system for automatically detecting and reporting traffic accidents at intersections. A system with these properties would be a great benefit in determining the cause of accidents and could also be useful in determining features of the intersection that relate to safety. A complete system would automatically detect and record traffic conditions associated with accidents such as time of the accident, video of the accident, and the traffic light signal controller parameters. In this project, the basic research required to develop the system has been considered. This involves developing methods for processing acoustic signals and recognizing accident events from the background traffic events. A database consisting of sounds from vehicle crashes, car braking sounds, construction sounds, and traffic sounds was created. We compute the Mel Frequency Cepstral Coefficients as a feature vector for input to the classification system. A neural network is used to classify these features into categories of crash and non-crash events. The classification testing results achieved 99% accuracy
Thresholdging video images is very challenging due to the fact that image background generally has low resolution and is also more complicated and highly distorted than document images. As a result, thresholding metho...
详细信息
Rail-to-rail differential mode input capability in low voltage CMOS transconductor design is implemented by a pull-down and a pull-up follower in an input buffer. By generating three intermediate voltages in the buffe...
详细信息
Rail-to-rail differential mode input capability in low voltage CMOS transconductor design is implemented by a pull-down and a pull-up follower in an input buffer. By generating three intermediate voltages in the buffer stage, three voltages are converted to three currents and subsequently summed using MOSFETs operating in the triode region. The nonlinear current components can be cancelled completely. The lowest supply voltage V/sub dd/ is constrained by 2V/sub th/ of the MOS transistors. A single 1.2V operational transconductor amplifier (OTA) was designed using 0.35/spl mu/m CMOS technology and the simulated I-V linearity error is less than 1% within the rail-to-rail differential input range. The achieved THD is less than 0.6% for a 1 KHz, 1.2 V/sub pp/ input signal.
Limited authority of actuators implies that real control signals are always constrained, and in almost all cases, this produces a degradation in the performance of the system. It is thus of practical importance to und...
详细信息
Limited authority of actuators implies that real control signals are always constrained, and in almost all cases, this produces a degradation in the performance of the system. It is thus of practical importance to understand the fundamental aspects of this performance degradation. In this paper, we take an initial step by proposing a way to characterize the performance limitations that arise in closed-loop stable linear systems due to the constraints on the magnitude of the control signal. Specifically, we evaluate the cost associated with the constraints via the L 2 norm of the tracking error of a constrained limiting optimal compensator.
A classification scheme is developed for classifying underwater mine-like and non-mine-like objects from acoustic backscattered signals. This scheme uses a predictive network along with a neural network classifier. Th...
详细信息
A classification scheme is developed for classifying underwater mine-like and non-mine-like objects from acoustic backscattered signals. This scheme uses a predictive network along with a neural network classifier. The results of this scheme on an acoustic backscattered data set are given.
Thresholdging video images is very challenging due to the fact that image background generally has low resolution and is also more complicated and highly distorted than document images. As a result, thresholding metho...
详细信息
A simulation program has been developed to calculate the power-spectral density of thin avalanche photodiodes, which are used in optical networks. The program extends the time-domain analysis of the dead-space multipl...
详细信息
A simulation program has been developed to calculate the power-spectral density of thin avalanche photodiodes, which are used in optical networks. The program extends the time-domain analysis of the dead-space multiplication model to compute the autocorrelation function of the APD impulse response. However, the computation requires a large amount of memory space and is very time consuming. We describe our experiences in parallelizing the code using both MPI and OpenMP. Several array partitioning schemes and scheduling policies are implemented and tested Our results show that the OpenMP code is scalable up to 64 processors on an SGI Origin 2000 machine and has small average errors.
暂无评论