Single Image Haze Removal With Haze Map Optimization for Various Haze Concentrations

Ganguly, Biswarup; Bhattacharya, Anwesa; Srivastava, Ananya; Dey, Debangshu; Munshi, Sugata

doi:10.1109/tcsvt.2021.3059573

Cited by 21 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To finish image enhancement, the image is changed from HSV space to red, green, blue (RGB) space. Ganguly et al [24] proposed a single image de-hazing method by cascading two models. Atmospheric light and transmission map is estimated for the first model, and haze map estimation for the second model.…”

Section: Related Workmentioning

confidence: 99%

Digital image enhancement by brightness and contrast manipulation using Verilog hardware description language

Azhari

Setumin

Noorsal

2023

IJECE

View full text Add to dashboard Cite

A foggy environment may cause digitally captured images to appear blurry, dim, or low in contrast. This will impact computer vision systems that rely on image information. With the need for real-time image information, such as a plate number recognition system, a simple yet effective image enhancement algorithm using a hardware implementation is very much needed to fulfil the need. To improve images that suffer from low exposure and hazy, the hardware implementations are usually based on complex algorithms. Hence, the aim of this paper is to propose a less complex enhancement algorithm for hardware implementation that is able to improve the quality of such images. The proposed method simply combines brightness and contrast manipulation to enhance the image. In order to see the performance of the proposed method, a total of 100 vehicle registration number images were collected, enhanced, and evaluated. The evaluation results were compared to two other enhancement methods quantitatively and qualitatively. Quantitative evaluation is done by evaluating the output image using peak signal-to-noise ratio and mean-square error evaluation metrics, while a survey is done to evaluate the output image qualitatively. Based on the quantitative evaluation results, our proposed method outperforms the other two enhancement methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Digital image enhancement by brightness and contrast manipulation using Verilog hardware description language

Azhari

Setumin

Noorsal

2023

IJECE

View full text Add to dashboard Cite

show abstract

“…Ganguly et al 5 . proposed a cascading model to estimate an atmospheric scattering model and haze map.…”

Section: Related Workmentioning

confidence: 99%

“…These prior-based methods introduce artifacts in some regions and could not preserve details. Subsequent dehazing models 5 – 7 combined physical priors and deep learning, most of them introduce Eq. (1) into deep learning architecture.…”

Section: Introductionmentioning

confidence: 99%

Multi-patch integrated learning dehazing network for small-scale dataset

Zhao,

Han,

Liu

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

.To further improve the feature representation ability of haze removal model on small-scale datasets, we propose a three-hierarchical encoder–decoder integrating learning architecture. Unlike increasing the depth of network to improve the performance, we use three sets of transfer learning encoders to aggregate features on multiple patches. This strategy makes full use of deep and shallow features from different spatial parts of original hazy images. These different spatial parts are used to jointly optimize non-homogeneous hazy images with different scene depths and degradation degrees. We propose an integrated learning decoder, in which the internal integrated learning module decodes by gradually infusing the deep and shallow features of the identical patch. We fuse all encoded features at each stage for original resolution decoder. We report the quantitative and visual results of eight advanced haze removal methods (2019 to 2021). We compare these methods on five real-world and synthetic hazy datasets, including homogeneous and non-homogeneous degraded datasets. We present the results of the ablation study for key components. The generalization of our method is significantly better than other methods on real hazy scenes. We report improvements in semantic segmentation performance. This result could be used for autonomous driving, automated guided vehicle scheduling in closed factory area, etc.

show abstract

“…Dudhance et al [7] reported a deep fusion network for haze removal, while Yeh et al [2] used multiscale residual learning to decompose foggy images and remove fog. More recently, Chen et al [3] discussed patch-based learning for dehazing, while Ganguly et al [8] optimized haze maps for various haze concentrations. In general, existing methods are still challenging to inhomogenous fog, directional lighting, and complex depth map.…”

Section: Introductionmentioning

confidence: 99%

Deeply Learned Structure-Aware Transmission for Image Haze Removal

Luo

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Atmospheric haze degenerates image visibility or visual quality. Unfortunately, characterizing scene depth and scene radiance uncertainties to precisely recover the transmission still remains challenging. This paper proposes a new structureaware transmission recovery strategy for single image dehazing. Specifically, such a new strategy is a coarse-to-refined dehazing approach that integrates multiscale convolutional neural networks and structure-aware retinex modeling into filtering-based fusion to accurately recover the transmission map. The proposed method was evaluated on benchmark data and compared with currently available dehazing approaches by quantifying colorfulness, contrast, and structural fidelity information of dehazed photographs. The experimental results demonstrate that the robust structure-preserving dehazing method outperforms other approaches, with significantly improving the average visual quality or content of the colorfulness, contrast, structural sharpness, and visibility from (0.63, 0.72, 0.15, 0.62) to (0.81, 0.84, 0.18, 0.78).

show abstract

Single Image Haze Removal With Haze Map Optimization for Various Haze Concentrations

Cited by 21 publications

References 37 publications

Digital image enhancement by brightness and contrast manipulation using Verilog hardware description language

Digital image enhancement by brightness and contrast manipulation using Verilog hardware description language

Multi-patch integrated learning dehazing network for small-scale dataset

Deeply Learned Structure-Aware Transmission for Image Haze Removal

Contact Info

Product

Resources

About