Solving sub-pixel image registration problems using phase correlation and Lucas-Kanade optical flow method

Douini, Youssef; Riffi, Jamal; Mahraz, Mohamed Adnane; Tairi, Hamid

doi:10.1109/isacv.2017.8054948

Cited by 12 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A brief review of current state-of-the-art Fourier-based methods for optical flow estimation is presented [27]. Several subpixel motion estimation and image registration algorithms operating in the frequency domain have been introduced [11], [13], [18], [34], [35], [46]- [48], [52]. In [22], Hoge proposes to apply a rank-1 approximation to the phase difference matrix and then performs unwrapping estimating the motion vectors.…”

Section: Related Workmentioning

confidence: 99%

“…The threshold T r is specified based on the logarithm of the current window size m w . Additionally, for the points that were removed after down-sampling pd = p d p d (13) motion vectors are estimated using [32]. In order to obtain a dense vector field non-uniform interpolation with bilateral filtering is applied on the motion components of the sparse key point locations.…”

Section: B Optical Flow Estimation Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain

Argyriou

2018

2018 14th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

We address the problem of motion estimation in images operating in the frequency domain. A method is presented which extends phase correlation to handle multiple motions present in an area. Our scheme is based on a novel Bilateral-Phase Correlation (BLPC) technique that incorporates the concept and principles of Bilateral Filters retaining the motion boundaries by taking into account the difference both in value and distance in a manner very similar to Gaussian convolution. The optical flow is obtained by applying the proposed method at certain locations selected based on the present motion differences and then performing non-uniform interpolation in a multiscale iterative framework. Experiments with several well-known datasets with and without ground-truth show that our scheme outperforms recently proposed state-of-the-art phase correlation based optical flow methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: B Optical Flow Estimation Frameworkmentioning

confidence: 99%

Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain

Argyriou

2018

2018 14th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

show abstract

“…Haar-like feature and Adaboost method algorithm [8] is utilized to catch these points. Combined with pre-trained computer vision classifiers of face, hands and other parts of human body from OpenCV lib, specific target parts of human body could be detected.Then Lucas-Kanade optical flow [9] is utilized to track target points. This method bases on the assumption that the intensity of the target pixels does not change between consecutive frames.…”

Section: Baby Sleeping Detectionmentioning

confidence: 99%

An Implementation of Cloud Based Camera Monitoring System for Healthcare

Gao¹,

Wang

Fang

2018

Proceedings of the 11th EAI International Conference on Mobile Multimedia Communications

View full text Add to dashboard Cite

New babies bring numerous happiness to parents as well as responsibilities. Parents would better fix their eyes on babies to guarantee everything run smoothly during their growing process. But it's hard to handle all other issues meantime looking after baby, especially for working couples. Baby Care Cloud Monitoring System help to solve such problem, then parents could get baby status anywhere anytime. It detects baby's sleeping status through OpenCV computer vision method and baby's crying through SVM Machine Learning method combined with MFCC acoustic character, assisting pediatrician to make a precise diagnose. The whole system consists of wireless terminal running on Openwrt Operating System and the Media Cloud Server built on AWS platform. The terminal captures and sends the live steaming complied by ffmpeg multimedia lib with the RTMP protocol to server. Media Cloud Server analyzes the received video and audio streaming separately, displays result and store the useful information.

show abstract

“…It has been reported that optical flow can reduce the uncertainty caused by user inputs and is less affected by rotation and scale than template matching. This has been achieved because the calculation speed of optical flow is faster than that of template matching and only requires an interrogation area parameter [ 20 , 28 , 29 , 30 , 31 ]. Using UAV-based RGB and hyperspectral image data from a river system, we focused on the following research objectives: (1) introduction of Harris corner detection, which defines singularity, optical flow algorithm calculation of the displacement between RGB and hyperspectral images from the detected singularity, and a 2D transformation method to warp hyperspectral images to RGB images based on the calculated displacement; (2) suggestion of hyperspectral imaging with high resolution and high spatial accuracy by applying the method presented in this study to RGB and hyperspectral images measured in a real river system; (3) validation of the method presented in this study compared with only geometric correction and template matching as conventional methods; (4) application of the image registered hyperspectral image for water body detection; (5) discussions and conclusion, including limitations of the proposed method.…”

Section: Introductionmentioning

confidence: 99%

Development of an Image Registration Technique for Fluvial Hyperspectral Imagery Using an Optical Flow Algorithm

You

Kim

2021

Sensors

View full text Add to dashboard Cite

Fluvial remote sensing has been used to monitor diverse riverine properties through processes such as river bathymetry and visual detection of suspended sediment, algal blooms, and bed materials more efficiently than laborious and expensive in-situ measurements. Red–green–blue (RGB) optical sensors have been widely used in traditional fluvial remote sensing. However, owing to their three confined bands, they rely on visual inspection for qualitative assessments and are limited to performing quantitative and accurate monitoring. Recent advances in hyperspectral imaging in the fluvial domain have enabled hyperspectral images to be geared with more than 150 spectral bands. Thus, various riverine properties can be quantitatively characterized using sensors in low-altitude unmanned aerial vehicles (UAVs) with a high spatial resolution. Many efforts are ongoing to take full advantage of hyperspectral band information in fluvial research. Although geo-referenced hyperspectral images can be acquired for satellites and manned airplanes, few attempts have been made using UAVs. This is mainly because the synthesis of line-scanned images on top of image registration using UAVs is more difficult owing to the highly sensitive and heavy image driven by dense spatial resolution. Therefore, in this study, we propose a practical technique for achieving high spatial accuracy in UAV-based fluvial hyperspectral imaging through efficient image registration using an optical flow algorithm. Template matching algorithms are the most common image registration technique in RGB-based remote sensing; however, they require many calculations and can be error-prone depending on the user, as decisions regarding various parameters are required. Furthermore, the spatial accuracy of this technique needs to be verified, as it has not been widely applied to hyperspectral imagery. The proposed technique resulted in an average reduction of spatial errors by 91.9%, compared to the case where the image registration technique was not applied, and by 78.7% compared to template matching.

show abstract

Solving sub-pixel image registration problems using phase correlation and Lucas-Kanade optical flow method

Cited by 12 publications

References 9 publications

Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain

Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain

An Implementation of Cloud Based Camera Monitoring System for Healthcare

Development of an Image Registration Technique for Fluvial Hyperspectral Imagery Using an Optical Flow Algorithm

Contact Info

Product

Resources

About