A motion deblurring method with long/short exposure image pairs

2018 ◽  
Author(s):  
Guangmang Cui ◽  
Weiping Hua ◽  
Jufeng Zhao ◽  
Xiaoli Gong ◽  
Liyao Zhu
Keyword(s):  
Short Exposure ◽  
Motion Deblurring ◽  
Image Pairs

Motion deblurring using edge map with blurred/noisy image pairs

2012 ◽  
Vol 285 (7) ◽  
pp. 1777-1786 ◽  
Author(s):  
Ser-Hoon Lee ◽  
Hyung-Min Park ◽  
Sun-Young Hwang
Keyword(s):  
Noisy Image ◽  
Motion Deblurring ◽  
Image Pairs

scholarly journals Motion Blur Removal for Uav-Based Wind Turbine Blade Images Using Synthetic Datasets

2021 ◽  
Vol 14 (1) ◽  
pp. 87
Author(s):  
Yeping Peng ◽  
Zhen Tang ◽  
Genping Zhao ◽  
Guangzhong Cao ◽  
Chao Wu
Keyword(s):  
Wind Turbine ◽  
Turbine Blades ◽  
Synthesis Method ◽  
Motion Blur ◽  
Image Motion ◽  
Video Sequences ◽  
Synthetic Image ◽  
Motion Deblurring ◽  
Image Pairs ◽  
Blurred Images

Unmanned air vehicle (UAV) based imaging has been an attractive technology to be used for wind turbine blades (WTBs) monitoring. In such applications, image motion blur is a challenging problem which means that motion deblurring is of great significance in the monitoring of running WTBs. However, an embarrassing fact for these applications is the lack of sufficient WTB images, which should include better pairs of sharp images and blurred images captured under the same conditions for network model training. To overcome the challenge of image pair acquisition, a training sample synthesis method is proposed. Sharp images of static WTBs were first captured, and then video sequences were prepared by running WTBs at different speeds. The blurred images were identified from the video sequences and matched to the sharp images using image difference. To expand the sample dataset, rotational motion blurs were simulated on different WTBs. Synthetic image pairs were then produced by fusing sharp images and images of simulated blurs. Finally, a total of 4000 image pairs were obtained. To conduct motion deblurring, a hybrid deblurring network integrated with DeblurGAN and DeblurGANv2 was deployed. The results show that the integration of DeblurGANv2 and Inception-ResNet-v2 provides better deblurred images, in terms of both metrics of signal-to-noise ratio (80.138) and structural similarity (0.950) than those obtained from the comparable networks of DeblurGAN and MobileNet-DeblurGANv2.

Multiple phase transitions investigated by high-speed TEM

1990 ◽  
Vol 48 (4) ◽  
pp. 550-551
Author(s):  
Oleg Bostanjoglo ◽  
Peter Thomsen-Schmidt
Keyword(s):  
Phase Transitions ◽  
High Speed ◽  
Short Exposure ◽  
Semiconductor Film ◽  
Time Resolved ◽  
Short Exposure Time ◽  
Multiple Phase ◽  
Model Substance ◽  
History Of ◽  
Electron Image

Thin GexTe1-x (x = 0.15-0.8) were studied as a model substance of a composite semiconductor film, in addition being of interest for optical storage material. Two complementary modes of time-resolved TEM were used to trace the phase transitions, induced by an attached Q-switched (50 ns FWHM) and frequency doubled (532 nm) Nd:YAG laser. The laser radiation was focused onto the specimen within the TEM to a 20 μm spot (FWHM). Discrete intermediate states were visualized by short-exposure time doubleframe imaging /1,2/. The full history of a transformation was gained by tracking the electron image intensity with photomultiplier and storage oscilloscopes (space/time resolution 100 nm/3 ns) /3/. In order to avoid radiation damage by the probing electron beam to detector and specimen, the beam is pulsed in this continuous mode of time-resolved TEM,too.Short events ( <2 μs) are followed by illuminating with an extended single electron pulse (fig. 1c)

Adverse Influence of Cigarette Smoking on the Endothelium

1993 ◽  
Vol 70 (04) ◽  
pp. 707-711 ◽  
Author(s):  
Andrew D Blann ◽  
Charles N McCollum
Keyword(s):  
Endothelial Cells ◽  
Von Willebrand Factor ◽  
Tobacco Smoke ◽  
Lipid Peroxides ◽  
Short Exposure ◽  
Acute Effects ◽  
Adverse Influence ◽  
Von Willebrand ◽  
Willebrand Factor

SummaryThe effect of smoking on the blood vessel intima was examined by comparing indices of endothelial activity in serum from smokers with that from non-smokers. Serum from smokers contained higher levels of von Willebrand factor (p <0.01), the smoking markers cotinine (p <0.02) and thiocyanate (p <0.01), and was more cytotoxic to endothelial cells in vitro (p <0.02) than serum from non-smokers. The acute effects of smoking two unfiltered medium tar cigarettes was to briefly increase von Willebrand factor (p <0.001) and cytotoxicity of serum to endothelial cells in vitro (p <0.005), but lipid peroxides or thiocyanate were not increased by this short exposure to tobacco smoke. Although there were correlations between von Willebrand factor and smokers consumption of cigarettes (r = 0.28, p <0.02), number of years smoking (r = 0.41, p <0.001) and cotinine (r = 0.45, p <0.01), the tissue culture of endothelial cells with physiological levels of thiocyanate or nicotine suggested that these two smoking markers were not cytotoxic. They are therefore unlikely to be directly responsible for increased von Willebrand factor in the serum of smokers. We suggest that smoking exerts a deleterious influence on the endothelium and that the mechanism is complex.

EVALUATION OF OCCUPATIONAL RADIATION EXPOSURE IN A RADIO-DIAGNOSTIC FACILITY IN KATSINA- NIGERIA

2020 ◽  
Vol 4 (2) ◽  
pp. 722-729
Author(s):  
Usman Sani ◽  
Bashir Gide Muhammad ◽  
Dimas Skam Joseph ◽  
D. Z. Joseph
Keyword(s):  
Radiation Dose ◽  
Radiation Exposure ◽  
Short Exposure ◽  
Skin Dose ◽  
Continuous Training ◽  
Short Exposure Time ◽  
Occupational Dose ◽  
Dose Limits ◽  
Radiation Workers ◽  
Occupational Radiation

Poor implementation of quality assurance programs in the radiation industry has been a major setback in our locality. Several studies revealed that occupational workers are exposed to many potential hazards of ionizing radiation during radio-diagnostic procedures, yet radiation workers are often not monitored. This study aims to evaluate the occupational exposure of the radiation workers in Federal Medical Centre Katsina, and to compare the exposure with recommended occupational radiation dose limits. The quarterly readings of 20 thermo-luminescent dosimeters (TLDs') used by the radiation workers from January to December, 2019 were collected from the facility's radiation monitoring archive, and subsequently assessed and analyzed. The results indicate that the average annual equivalent dose per occupational worker range from 0.74 to 1.20 mSv and 1.28 to 2.21 mSv for skin surface and deep skin dose, measured at 10 mm and 0.07 mm tissue depth respectively. The occupational dose was within the recommended national and international limits of 5 mSv per annum or an average of 20 mSv in 5 years. Therefore, there was no significant radiation exposure to all the occupational workers in the study area. Though, the occupational radiation dose is within recommended limit, this does not eliminate stochastic effect of radiation. The study recommended that the occupational workers should adhere and strictly comply with the principles of radiation protection which includes distance, short exposure time, shielding and proper monitoring of dose limits. Furthermore, continuous training of the radiation workers is advised.

THE EFFECT OF AIR GAP THICKNESS ON HEAT TRANSFER IN FIREFIGHTERS' PROTECTIVE CLOTHING UNDER CONDITIONS OF SHORT EXPOSURE TO HEAT

2012 ◽  
Vol 43 (8) ◽  
pp. 749-765 ◽  
Author(s):  
Song He ◽  
Dongmei Huang ◽  
Zhengkun Qi ◽  
Hui Yang ◽  
Yin Hu ◽  
...  
Keyword(s):  
Heat Transfer ◽  
Protective Clothing ◽  
Air Gap ◽  
Short Exposure

LambdaNet: A Fully Convolutional Architecture for Directional Change Detection

2020 ◽  
Vol 2020 (8) ◽  
pp. 114-1-114-7
Author(s):  
Bryan Blakeslee ◽  
Andreas Savakis
Keyword(s):  
Change Detection ◽  
Satellite Imagery ◽  
Classification Scheme ◽  
Deep Architecture ◽  
Binary Process ◽  
Directional Change ◽  
Class Labels ◽  
Image Pairs

Change detection in image pairs has traditionally been a binary process, reporting either “Change” or “No Change.” In this paper, we present LambdaNet, a novel deep architecture for performing pixel-level directional change detection based on a four class classification scheme. LambdaNet successfully incorporates the notion of “directional change” and identifies differences between two images as “Additive Change” when a new object appears, “Subtractive Change” when an object is removed, “Exchange” when different objects are present in the same location, and “No Change.” To obtain pixel annotated change maps for training, we generated directional change class labels for the Change Detection 2014 dataset. Our tests illustrate that LambdaNet would be suitable for situations where the type of change is unstructured, such as change detection scenarios in satellite imagery.

Three-dimensional Reconstruction of Microscopic Image Based on Multi-ST Algorithm

2020 ◽  
Vol 64 (2) ◽  
pp. 20506-1-20506-7
Author(s):  
Min Zhu ◽  
Rongfu Zhang ◽  
Pei Ma ◽  
Xuedian Zhang ◽  
Qi Guo
Keyword(s):  
3D Reconstruction ◽  
Three Dimensional ◽  
Scale Model ◽  
Microscopic Image ◽  
Multi Scale ◽  
Gaussian Pyramid ◽  
Cost Aggregation ◽  
Dimensional Reconstruction ◽  
Image Pairs ◽  
Accurate Matching

Abstract Three-dimensional (3D) reconstruction is extensively used in microscopic applications. Reducing excessive error points and achieving accurate matching of weak texture regions have been the classical challenges for 3D microscopic vision. A Multi-ST algorithm was proposed to improve matching accuracy. The process is performed in two main stages: scaled microscopic images and regularized cost aggregation. First, microscopic image pairs with different scales were extracted according to the Gaussian pyramid criterion. Second, a novel cost aggregation approach based on the regularized multi-scale model was implemented into all scales to obtain the final cost. To evaluate the performances of the proposed Multi-ST algorithm and compare different algorithms, seven groups of images from the Middlebury dataset and four groups of experimental images obtained by a binocular microscopic system were analyzed. Disparity maps and reconstruction maps generated by the proposed approach contained more information and fewer outliers or artifacts. Furthermore, 3D reconstruction of the plug gauges using the Multi-ST algorithm showed that the error was less than 0.025 mm.

Sign in / Sign up

Export Citation Format

Share Document