$$D^2ehazing$$ : Real-Time Dehazing in Traffic Video Analytics by Fast Dynamic Bilateral Filtering

Das, Apurba; Pai, Shashidhar; Shenoy, Vinayak S; Vinay, Tanush; Shylaja, S S

doi:10.1007/978-981-32-9291-8_11

Cited by 8 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the method is effective to remove haze on images or frames, the flickering artifacts appear on the dehazed videos when the camera shakes or the scene changes rapidly. To exploit the temporal information from consecutive adjacent frames, some prior-based video dehazing methods [16], [15], [17], [18], [19], [20] introduce the temporal information of adjacent frames on the estimation process of the transmission map. For example, Zhang et al [16] first use the guided filter to extract the transmission map of each frame.…”

Section: Related Workmentioning

confidence: 99%

Progressive Deep Video Dehazing without Explicit Alignment Estimation

Li¹

2021

Preprint

View full text Add to dashboard Cite

To solve the issue of video dehazing, there are two main tasks to attain: how to align adjacent frames to the reference frame; how to restore the reference frame. Some papers adopt explicit approaches (e.g., the Markov random field, optical flow, deformable convolution, 3D convolution) to align neighboring frames with the reference frame in feature space or image space, they then use various restoration methods to achieve the final dehazing results. In this paper, we propose a progressive alignment and restoration method for video dehazing. The alignment process aligns consecutive neighboring frames stage by stage without using the optical flow estimation. The restoration process is not only implemented under the alignment process but also uses a refinement network to improve the dehazing performance of the whole network. The proposed networks include four fusion networks and one refinement network. To decrease the parameters of networks, three fusion networks in the first fusion stage share the same parameters. Extensive experiments demonstrate that the proposed video dehazing method achieves outstanding performance against the-state-of-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Progressive Deep Video Dehazing without Explicit Alignment Estimation

Li¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Ряд работ посвящен применению компьютерного зрения в целях повышения пропускной способности перекрестков [9][10][11][12].…”

Section: вд шепелев зв альметова ад моор ви берстеневаunclassified

“…Отличительной особенностью работы авторов Das A., Pai S., Shenoy V.S., Vinay T. и Shylaja S.S. является повышение точности распознавания транспортных средств компьютерным зрением в неблагоприятных погодных условиях с помощью алгоритма, основанного на R-CNN и быстрой двусторонней фильтрации [12].…”

Section: вд шепелев зв альметова ад моор ви берстеневаunclassified

Performance Optimization of Adaptive Traffic Lights Using Machine Vision

Shepelev¹,

Almetova²,

Moor³

et al. 2020

View full text Add to dashboard Cite

show abstract

“…числе при неблагоприятных погодных условиях и темного времени суток. Этой проблемой занимались исследователи в работе [13], где предложен алгоритм, основанный на R-CNN и быстрой двусторонней фильтрации.…”

Section: Introductionunclassified

Predicting and Managing Lane Capacity at a Signal-Controlled Intersection

Shepelev¹,

Gorodokin²,

Slobodin³

et al. 2021

View full text Add to dashboard Cite

$$D^2ehazing$$ : Real-Time Dehazing in Traffic Video Analytics by Fast Dynamic Bilateral Filtering

Cited by 8 publications

References 13 publications

Progressive Deep Video Dehazing without Explicit Alignment Estimation

Progressive Deep Video Dehazing without Explicit Alignment Estimation

Performance Optimization of Adaptive Traffic Lights Using Machine Vision

Predicting and Managing Lane Capacity at a Signal-Controlled Intersection

Contact Info

Product

Resources

About