Modeling the Performance of Image Restoration From Motion Blur

Boracchi, Giacomo; Foi, Alessandro

doi:10.1109/tip.2012.2192126

Cited by 149 publications

(100 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their analysis concludes that align-and-average works better than singleimage deconvolution. Boracchi and Foi [1] made the similar observation that restoration error of single-image deconvolution stabilizes after reaching a minimum. However, these results are limited to the single-image approach, while we focus on the case when multiple images are used.…”

Section: Related Workmentioning

confidence: 77%

Gyro-Based Multi-image Deconvolution for Removing Handshake Blur

Park

Levoy

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Image deblurring to remove blur caused by camera shake has been intensively studied. Nevertheless, most methods are brittle and computationally expensive. In this paper we analyze multi-image approaches, which capture and combine multiple frames in order to make deblurring more robust and tractable. In particular, we compare the performance of two approaches: align-and-average and multi-image deconvolution. Our deconvolution is nonblind, using a blur model obtained from real camera motion as measured by a gyroscope. We show that in most situations such deconvolution outperforms align-and-average. We also show, perhaps surprisingly, that deconvolution does not benefit from increasing exposure time beyond a certain threshold. To demonstrate the effectiveness and efficiency of our method, we apply it to still-resolution imagery of natural scenes captured using a mobile camera with flexible camera control and an attached gyroscope.

show abstract

Section: Related Workmentioning

confidence: 77%

Gyro-Based Multi-image Deconvolution for Removing Handshake Blur

Park

Levoy

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…(), we adopt a novel motion blurring augmentation strategy. We choose the image formation model developed by Boracchi and Foi () to simulate the motion blur effect,

z_{T} false(x false) = κ false(u_{T} (x) + η (x) false), x \in X

where

X \subseteq {double-struckR}^{2}

denotes the sampling grid, and

κ > 0

is a scaling factor. The two terms

u_{T} false(x false)

and

η (x)

are two independent random variables, which represent, respectively, the observation and a source of noise that is independent from the original image.…”

Section: Methodsmentioning

confidence: 99%

Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization

Yuan

Zhang

et al. 2018

Computer aided Civil Eng

120

View full text Add to dashboard Cite

Vision‐based autonomous inspection of concrete surface defects is crucial for efficient maintenance and rehabilitation of infrastructures and has become a research hot spot. However, most existing vision‐based inspection methods mainly focus on detecting one kind of defect in nearly uniform testing background where defects are relatively large and easily recognizable. But in the real‐world scenarios, multiple types of defects often occur simultaneously. And most of them occupy only small fractions of inspection images and are swamped in cluttered background, which easily leads to missed and false detections. In addition, the majority of the previous researches only focus on detecting defects but few of them pay attention to the geolocalization problem, which is indispensable for timely performing repair, protection, or reinforcement works. And most of them rely heavily on GPS for tracking the locations of the defects. However, this method is sometimes unreliable within infrastructures where the GPS signals are easily blocked, which causes a dramatic increase in searching costs. To address these limitations, we present a unified and purely vision‐based method denoted as defects detection and localization network, which can detect and classify various typical types of defects under challenging conditions while simultaneously geolocating the defects without requiring external localization sensors. We design a supervised deep convolutional neural network and propose novel training methods to optimize its performance on specific tasks. Extensive experiments show that the proposed method is effective with a detection accuracy of 80.7% and a localization accuracy of 86% at 0.41 s per image (at a scale of 1,200 pixels in the field test experiment), which is ideal for integration within intelligent autonomous inspection systems to provide support for practical applications.

show abstract

“…After obtaining the sequential image displacements, there are several methods can be used to construct the long-exposure-time blur kernel [13]. The motion kernel (x, y) h is calculated by the relation…”

Section: Experiments Setupmentioning

confidence: 99%

Development of a blurred spectral images restoration technology for CTIS imaging spectrometer

Zhou

Jin

Dong³

et al. 2016

Opt. Express

View full text Add to dashboard Cite

The platform vibration will cause spectral images blurring when using computed tomographic imaging spectrometer (CTIS) on unstable platform, especially in space-borne or ship-based application. As a result, a phenomenon of blur-induced spectral distortion occurs, which greatly affects the accuracy of classification of target. However, without easy accessibility of the knowledge of image motion kernel, it is difficult to restore the degraded images accurately. With the desire to solve the motion function, this paper has made a breakthrough by proposing a motion detection method using short exposure images from zeroth order beam light of 2D-grating. Contributed by the accurate motion kernel, blurred spectral images could be reliably restored as well as the improvement of spectra accuracy. Laboratory experiment result shows the robust spectra restoration capability of this technique.

show abstract

Modeling the Performance of Image Restoration From Motion Blur

Cited by 149 publications

References 37 publications

Gyro-Based Multi-image Deconvolution for Removing Handshake Blur

Gyro-Based Multi-image Deconvolution for Removing Handshake Blur

Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization

Development of a blurred spectral images restoration technology for CTIS imaging spectrometer

Contact Info

Product

Resources

About