Search

Stripe and random noise are two different degradation phenomena commonly co-existing in optical remote sensing images, which are often modelled as inverse problems, respectively. When solving those inverse problems, model-based optimization and discriminative learning methods are fashionably employed but have their respective merits and drawbacks, e.g., model-based optimization methods are flexible but usually time-consuming while discriminative learning methods have fast testing speed but are limited by the specialized task. To improve testing speed and obtain good performance, this paper integrates deep convolutional neural network (DCNN) denoiser prior into unidirectional variation (UV) model, named as UV-DCNN, to simultaneously destripe and denoise optical remote sensing images. The proposed UV-DCNN method can be efficiently solved by the alternating minimization optimization method. Both quantitative and qualitative experiment results validate that the proposed method is effective and even better than the state-of-the-arts, its satisfactory computation time makes it suitable for extensive application. [ABSTRACT FROM AUTHOR]

A kind of portable device for detecting common lung function parameters is mentioned in this paper. Using the singlechip microcomputer as the master control block to collect and process the data from high-accuracy gas pressure sensor, through the way of parametric calibration and linear interpolation to test and calculate the Forced Vital Capacity (FVC), Peak Expiratory Flow (PEF), Forced Expiratory Volume in one second (FEV1), and FEV1/FVC. Meanwhile, the detected parameters can be uploaded to the intelligent mobile terminal through the wireless transmission module. The device is able to show expiratory volume-time curve and the final parameters clearly, the error of measurement is less than 5%. In addition, that device is small and convenient, not only is good for clinical application, but also can be used for family in a house.