Video dehazing without flicker artifacts using adaptive temporal average

Shin, Do Kyoung; Kim, Yong Min; Park, Ki Tae; Lee, Dong‐Seok; Choi, Wonju; Moon, Young Shik

doi:10.1109/isce.2014.6884454

Cited by 6 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [23] proposed a method based on spatial and temporal correlation that uses spatial and temporal similarity between frames to optimize the estimation of a scene depth map. Shin et al [24] proposed an effective video dehazing technique to reduce flicker artifacts by using adaptive temporal average. However, these methods cannot remove the haze from videos in real time.…”

Section: Related Workmentioning

confidence: 99%

Efficient Traffic Video Dehazing Using Adaptive Dark Channel Prior and Spatial–Temporal Correlations

Dong

Zhao

et al. 2019

Sensors

View full text Add to dashboard Cite

In order to restore traffic videos with different degrees of haziness in a real-time and adaptive manner, this paper presents an efficient traffic video dehazing method using adaptive dark channel prior and spatial-temporal correlations. This method uses a haziness flag to measure the degree of haziness in images based on dark channel prior. Then, it gets the adaptive initial transmission value by establishing the relationship between the image contrast and haziness flag. In addition, this method takes advantage of the spatial and temporal correlations among traffic videos to speed up the dehazing process and optimize the block structure of restored videos. Extensive experimental results show that the proposed method has superior haze removing and color balancing capabilities for the images with different degrees of haze, and it can restore the degraded videos in real time. Our method can restore the video with a resolution of 720 × 592 at about 57 frames per second, nearly four times faster than dark-channel-prior-based method and one time faster than image-contrast-enhanced method.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Traffic Video Dehazing Using Adaptive Dark Channel Prior and Spatial–Temporal Correlations

Dong

Zhao

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The gray-scale opening operation smooths the gray-scale and the white target is eliminated, but it also blurs edges. Shin et al propose an approach to calculate atmospheric light values based on adaptive temporal averaging between adjacent frames to avoid flickering artifacts in a video sequence [22].…”

Section: Introductionmentioning

confidence: 99%

An efficient Video Dehazing Algorithm Based on Spectral Clustering

Zhao¹,

Yao²,

Song³

et al. 2018

KSII TIIS

View full text Add to dashboard Cite

Image and video dehazing is a popular topic in the field of computer vision and digital image processing. A fast, optimized dehazing algorithm was recently proposed that enhances contrast and reduces flickering artifacts in a dehazed video sequence by minimizing a cost function that makes transmission values spatially and temporally coherent. However, its fixed-size block partitioning leads to block effects. The temporal cost function also suffers from the temporal non-coherence of newly appearing objects in a scene. Further, the weak edges in a hazy image are not addressed. Hence, a video dehazing algorithm based on well designed spectral clustering is proposed. To avoid block artifacts, the spectral clustering is customized to segment static scenes to ensure the same target has the same transmission value. Assuming that edge images dehazed with optimized transmission values have richer detail than before restoration, an edge intensity function is added to the spatial consistency cost model. Atmospheric light is estimated using a modified quadtree search. Different temporal transmission models are established for newly appearing objects, static backgrounds, and moving objects. The experimental results demonstrate that the new method provides higher dehazing quality and lower time complexity than the previous technique.

show abstract