Traditional methods for motion estimation estimate the motion field F between a pair of images as the one that minimizes a predesigned cost function. In this paper, we propose a direct method and train a Convolutional Neural Network (CNN) that when, at test time, is given a pair of images as input it produces a dense motion field F at its output layer. In the absence of large datasets with ground truth motion that would allow classical supervised training, we propose to train the network in an unsupervised manner. The proposed cost function that is optimized during training, is based on the classical optical flow constraint. The latter is differentiable with respect to the motion field and, therefore, allows backpropagation of the error to previous layers of the network. Our method is tested on both synthetic and real image sequences and performs similarly to the state-of-the-art methods.
In this paper a 2-way broadband power combiner that can handle up to 1 kW output power is designed and fabricated. The combiner covers the frequency range of 30 to 500 MHz, which is intended for industrial, scientific, and medical (ISM) applications. The power handling of the power combiner depends on the power handling of the components that constitute the combiner. The combiner is composed of some coaxial transmission lines and a transmission line transformer. The ferrite cores, which are used to suppress the common mode current, are one of the major limiting factors, regarding the power handling of the combiner. The power combiner is implemented with some binuclear and some stacked toroids of material 61, which is extensively used for common mode current suppression in this frequency range. As real ferrites have complex permeability, some of the input power dissipates as heat in the ferrite cores. The power dissipation due to the equivalent parallel resistance of each ferrite core is calculated. The proper operation of the high power combiner is verified by simulation of the temperature rise in the ferrite cores due to heat dissipation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.