Depth-Guided Two-Way Saliency Network for 2D Images

Das, Dibyendu; Shit, Sahadeb; Ray, Dip Narayan

doi:10.1007/978-981-16-4369-9_7

Cited by 1 publication

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, visibility increases when the haze is removed from a hazy image caused due to atmospheric particles. Haze removal is becoming essential to develop collision-free transportation systems 2,3 for operation during the winter and rainy seasons with the help of computer vision and image processing techniques. When light diffuses into the atmosphere, the images in the outdoor environment are degraded by the dense medium (such as fog, haze, rain, etc.).…”

Section: Introductionmentioning

confidence: 99%

“…So, the removal of haze is needed for collision-free driving. Many of the existing works [3][4][5][6] have attempted to render a clear image by estimating the atmospheric light and the transmission map based on a variety of prior artifacts, such as color attenuation, 4 dark channel prior, 6 local prior, 5 and nonlocal prior. 4 These previous techniques usually depend on the atmospheric scattering model to generate a transmission map, which is subsequently used to calculate the clear view using Equation (1).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An encoder‐decoder based CNN architecture using end to end dehaze and detection network for proper image visualization and detection

Shit

Das

Ray

et al. 2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Industrial sectors are reinventing in automation, stability, and robustness due to the rapid development of artificial intelligence technologies, resulting in significant increases in quality and production. Visual‐based sensor networks capture various views of the surrounding environment and are used to monitor industrial and transportation sectors. However, due to unclean suspended air particles that damage the whole monitoring and transportation systems, the visual quality of the images is degraded under adverse weather conditions. This research proposed a convolutional neural network‐based image dehazing and detection approach, called end to end dehaze and detection network (EDD‐N), for proper image visualization and detection. This network is trained on real‐time hazy images that are directly used to recover dehaze images without a transmission map. EDD‐N is robust, and accuracy is higher than any other proposed model. Finally, we conducted extensive experiments using real‐time foggy images. The quantitative and qualitative evaluations of the hazy dataset verify the proposed method's superiority over other dehazing methods. Moreover, the proposed method validated real‐time object detection tasks in adverse weather conditions and improved the intelligent transportation system.

show abstract

Section: Introductionmentioning

confidence: 99%