Unsupervised Learning for Depth, Ego-Motion, and Optical Flow Estimation Using Coupled Consistency Conditions.

Herein, we propose an unsupervised learning architecture under coupled consistency conditions to estimate the depth, ego-motion, and optical flow. Previously invented learning techniques in computer vision adopted a large amount of the ground truth dataset for network training. A ground truth dataset, including depth and optical flow collected from the real world, requires tremendous effort in pre-processing due to the exposure to noise artifacts. In this paper, we propose a framework that trains networks while using a different type of data with combined losses that are derived from a coupled consistency structure. The core concept is composed of two parts. First, we compare the optical flows, which are estimated from both the depth plus ego-motion and flow estimation network. Subsequently, to prevent the effects of the artifacts of the occluded regions in the estimated optical flow, we compute flow local consistency along the forward-backward directions. Second, synthesis consistency enables the exploration of the geometric correlation between the spatial and temporal domains in a stereo video. We perform extensive experiments on the depth, ego-motion, and optical flow estimation on the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset. We verify that the flow local consistency loss improves the optical flow accuracy in terms of the occluded regions. Furthermore, we also show that the view-synthesis-based photometric loss enhances the depth and ego-motion accuracy via scene projection. The experimental results exhibit the competitive performance of the estimated depth and the optical flow; moreover, the induced ego-motion is comparable to that obtained from other unsupervised methods.

Development and calibration of differential mobility analyzer for 20 to 80 nm particles under low pressure conditions.

The vienna-type differential mobility analyzer (DMA) was developed for the measurement of wide-range nm-sized particles under low-pressure conditions (2.9-8 kPa) with the faraday cup electrometer (FCE). The length, inner and outer diameter of DMA are calculated as a function of flow rate, applied voltage, pressure, and particle diameter to avoide breakdown in DMA. The algorithm for the diffusion transfer function of the DMA was successfully developed and verified by comparing the numerical and experimental results. The DMA was calibrated via the tandem DMA (TDMA) method which using two DMA in parallel. The inversion algorithm was applied to the size distribution obtained from the current of the FCE. The calibration experiment was performed with 1% NaCl particles under atmospheric and low-pressure conditions. The calibration result showed that the development of the DMA was successful as it was able to measure 20- to 80-nm paricles under low-pressure conditions with various flow rates (0.1-0.5 l/min).

Histopathological pictures of the initial changes of the hair bulbs in alopecia areata.

A biopsy of the seemingly normal scalp of a patient who had just begun to develop alopecia areata showed distinctive changes in bulbar morphology, in addition to peribulbar lymphocytic infiltrates. One of these changes was a loss of structural integrity of the centrally located supramatrical upper bulbar region. The other was the shrinkage of hair bulbs in the direction of club shape. Uninvolved intact anagen follicles were also present among these involved follicles.