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.
Very large-scale Deep Neural Networks (DNNs) have achieved remarkable successes in a large variety of computer vision tasks. However, the high computation intensity of DNNs makes it challenging to deploy these models on resource-limited systems. Some studies used low-rank approaches that approximate the filters by low-rank basis to accelerate the testing. Those works directly decomposed the pre-trained...
Convolutional neural networks (CNNs) have recently broken many performance records in image recognition and object detection problems. The success of CNNs, to a great extent, is enabled by the fast scaling-up of the networks that learn from a huge volume of data. The deployment of big CNN models can be both computation-intensive and memory-intensive, leaving severe challenges to hardware implementations...
Traditional background modeling methods often require complicated computations and suffer from cavity problems in foreground objects. In this paper, we propose a block-based background modeling method combining multiple detection results derived from color and texture characteristics. This method can significantly alleviate the cavity problem and resist certain shadow interference. Since the proposed...
Background construction is the base of object detection and tracking for the machine vision system. Traditional background modeling methods often require complicated computations and are sensitive to illumination changes and shadow interference. In this paper, we propose a block-based background modeling method, which fully utilizes the color and texture characteristics of each incoming frame. The...
In this study, the numerical investigation was adopted to analyze the deposition characteristic of polycrystalline silicon in a rib reactor. Fluent 6.2 was utilized to simulate the simultaneous momentum transfer, energy transfer and mass transfer, and to couple the gas-phase reaction with surface reaction in SiHC13 -H2 system. Computed flow structure, thermal and species distributions indicated that...
The uniformity level of simulation signal is expressed as a fuzzy number by using the fitting method, and its contrast analysis is naturally ascribed to the sequence of fuzzy numbers. Considering the influence of information quantity upon sequence of fuzzy numbers, a sequencing method which ponders the generalized average value, deviation, and information quantity of fuzzy number comprehensively is...
In this paper we examine the application of repetitive control schemes for robot manipulators. The controllers consist of a fixed PD action and a repetitive action for feed-forward nonlinearity compensation. When the manipulator is required to track a periodic desired trajectory, better tracking performance can be obtained using repetitive control algorithms than using conventional linear controllers...
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.