The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we focus on constructing an accurate super resolution system based on multiple Convolution Neural Networks (CNNs). Each individual CNN is trained separately with different network structure. A Context-wise Network Fusion (CNF) approach is proposed to integrate the outputs of individual networks by additional convolution layers. With fine-tuning the whole fused network, the accuracy...
The convolutional neural network (CNN) is more and more popular in computer vision and widely used in acoustic signal processing, image classification, and image segmentation. In this work, an architecture which is a combination of the 3-D convolutional neural network and the long short term memory (LSTM) was proposed for action recognition. It stacks the consecutive video frames, extracts spatial...
CNNs (Convolutional Neural Networks) have demonstrated superior results in a wide range of applications. However, the time-consuming convolution operations required by CNNs pose great challenges to designers. GPGPUs (General Purpose Graphic Processing Units) have been widely used to exploiting the massive parallelism of convolution operations. This paper proposes a software-based loop-unrolling technique...
In the paper we propose a discrete singular convolution method to perform the steady-state analysis of relaxation oscillators in time domain. Approximation of derivatives in the ordinary differential equations representing the oscillators' mathematical model is provided in the matrix form with usage of the Shannon's series kernel. The examples are given to illustrate the application of the developed...
Target detection is a hard real-time task for video and image processing. This task has recently been accomplished through the feedforward process of convolutional neural net-works (CNN), which is usually accelerated by general-purpose graphic units (GPUs). However, there is a challenge for this task. The running speed remains to be improved. In this paper, we present an efficient image combination...
Parabolic motion cameras are used to obtain better deblurring results of scenes with multiple moving objects. The core of its deblurring process is Iterative Re-weighted Least Squares (IRLS) method. In this paper, we design a hardware accelerator for IRLS flow. The ASIC chip is implemented using TSMC 90 nm technology. It is capable of deblurring a 640 × 480 image captured by a parabolic camera with...
This paper presents several novel GPU optimization technologies to accelerate the SRCNN(Super-Resolution Convolutional Neural Network) — one of the best super-resolution algorithm. We first directly parallelize and implement the SRCNN, then accelerate the convolution by making use of the hierarchical feature of GPU memory. We explore different optimization methods on each convolution and select the...
Compared to more mundane blind deconvolution problems, blind deconvolution in seismic applications involves a feedback mechanism related to the free surface. The presence of this feedback mechanism gives us an unique opportunity to remove ambiguities that have plagued blind deconvolution for a long time. While beneficial, this feedback by itself is insufficient to remove the ambiguities even with...
Non uniform kernels is important for many image processing algorithms. However, for large kernel sizes the filtering can become computationally expensive. We introduce cosine integral images (CII) which represent a large set of spatial and range filters, based on their frequency decomposition. The filtering requires a constant number of operations per image pixel, independent of filter size. We make...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.