An iterative method for optical flow estimation with motion blur

Shi, Xiangxi; Kang, Kai; Cao, Yang

doi:10.1109/vcip.2016.7805541

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…；灰度投影法是对整幅图像的行、列灰度值进行累加，以达到降维处理的目的，但无法避免前景运动物体对运动估计的影响 [6] ；光流法具有很强大的数学理论基础，但对图像中的每一个像素点都计算其光流失量，计算量巨大，无法做到实时稳像处理 [7]…”

unclassified

Electronic Image Stabilization of Airborne Infrared Images Based on Improved Harris Corner Detection

董¹,

王²,

许³

2020

View full text Add to dashboard Cite

：Bumps and sloshing generated during aircraft flights disrupt the capture of a sequence of infrared images. This affects the subsequent observation of the images, as well as the identification, location, and tracking of the target. In this paper, a method for real-time electronic image stabilization of airborne infrared images is proposed based on an improved Harris corner method. First, an improved Harris corner response function was combined with a distance constraint to perform corner detection. This method ensures that a sufficient number of corner points with uniform distribution can be detected, even for infrared images with poor image quality. The proposed key-frame reference method was then combined with the multi-scale pyramid optical flow algorithm; furthermore, the detected corner points were applied to the aforementioned combination, thereby achieving tracking matching and motion estimation. Consequently, electronic image stabilization of the airborne infrared images was realized. Using this method, multiple sets of jittery infrared image sequences were processed; the image size was 640512. Experimental results show that the proposed algorithm exhibits a better corner detection effect than the traditional Harris corner detection algorithm. It can remove jitter from the airborne infrared image sequence and ensure real-time processing at an acquisition rate of 50 fps. Key words：electronic image stabilization, airborne infrared image, Harris corner detection, distance constraint 0 引言由于在高空中气流变化不均，飞机航姿不同等原因使得机载红外采集设备存在不同程度的振动，虽然

show abstract

unclassified

Electronic Image Stabilization of Airborne Infrared Images Based on Improved Harris Corner Detection

董¹,

王²,

许³

2020

View full text Add to dashboard Cite

show abstract

An iterative method for optical flow estimation with motion blur

Cited by 1 publication

References 9 publications

Electronic Image Stabilization of Airborne Infrared Images Based on Improved Harris Corner Detection

Electronic Image Stabilization of Airborne Infrared Images Based on Improved Harris Corner Detection

Contact Info

Product

Resources

About