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.
Remarkable hardware robustness of deep learning (DL) is revealed by error injection analyses performed using a custom hardware model implementing parallelized restricted Boltzmann machines (RBMs). RBMs in deep belief networks demonstrate robustness against memory errors during and after learning. Fine-tuning significantly affects the recovery of accuracy for static errors injected to the structural...
A key aspect of constructing highly scalable Deep-learning microelectronic systems is to implement fault tolerance in the learning sequence. Error-injection analyses for memory is performed using a custom hardware model implementing parallelized restricted Boltzmann machines (RBMs). It is confirmed that the RBMs in Deep Belief Networks (DBNs) provides remarkable robustness against memory errors. Fine-tuning...
Live results obtained from the first real-time high-resolution free viewpoint synthesis hardware that utilizes three-camera disparity estimation are presented. The proposed hardware generates high-quality free viewpoint video at 55 frames per second on a Virtex-7 FPGA at a 1024×768 XGA video resolution for any horizontally-aligned arbitrary camera positioned between the leftmost and rightmost physical...
The recent development of high-quality free viewpoint synthesis algorithms and their implementations allows to realize glasses-free 3D perception. Although many algorithms have been developed in this domain, the real-time hardware realization of a free viewpoint synthesis for real-world images is challenging due to its high computational load and memory bandwidth requirements. In this paper, the first...
We address four problems related to the precision in analog hardware implementations of fuzzy and neuro-fuzzy systems, namely the precision of approximation/ interpolation; errors due to hardware implementation — manufacturing factors in integrated circuit (IC); errors due to sensitivity to external factors, and dynamical errors.
This paper proposes a hardware-oriented trinocular adaptive window size disparity estimation (T-AWDE) algorithm and the first real-time trinocular disparity estimation (DE) hardware that targets high-resolution images with high-quality disparity results. The proposed trinocular DE hardware is the enhanced version of the recently published binocular AWDE implementation. The T-AWDE hardware generates...
An edge-detection scheme suitable for machine vision and digital motion detection applications is presented. The scheme is inspired by the human visual system (human retina) and modified for a compact and scalable CMOS hardware implementation. In addition, pixel circuit and implementation of the scheme on a CMOS focal-plane are proposed and simulation results are presented. The circuit performs thresholding...
A novel compressive sampling scheme suitable for highly scalable hardware implementations is presented. The scheme utilizes an identical pseudo-random sequence for every image column, therefore reducing in-pixel hardware complexity and allowing measurement matrix generation in a single clock cycle. As a result, high frame rates and low power consumption are achievable with an acceptable reduction...
Omnidirectional stereoscopy and depth estimation are complex problems of image processing to which the Panoptic camera offers a novel solution. The Panoptic camera is a biologically-inspired vision sensor made of multiple cameras. It is a polydioptric system mimicking the eyes of flying insects where multiple imagers, each with a distinct focal point, are distributed over a hemisphere. Recently, the...
A novel hardware implementation of an omnidirectional image sensor is presented which is capable of acquiring and processing 3D image sequences in real time. The system consists of a hemispherical arrangement of a large number of CMOS imagers, connecting to a layered arrangement of a high-end FPGA platform that is responsible data framing and image processing. The hardware platform in charge of real-time...
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.