A two-step approach to see-through bad weather for surveillance video quality enhancement

Jia, Zhenhong; Wang, Hongcheng; Caballero, Rodrigo E.; Xiong, Ziyou; Zhao, Jianwei; Finn, Alan

doi:10.1007/s00138-012-0416-6

Cited by 35 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The techniques to eliminate this degradation, known as dehazing (or defogging), can improve the visual quality of images for computer-aided applications and human interpretation and are, consequently, crucial in many applications such as air and maritime transport, surveillance, driver assistance systems, remote sensing, agronomy, archaeology, astronomy, etc. [ 1 , 2 , 3 , 4 , 5 , 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

Single Image Dehazing Algorithm Analysis with Hyperspectral Images in the Visible Range

Martínez-Domingo

Valero

Nieves

et al. 2020

Sensors

View full text Add to dashboard Cite

In foggy or hazy conditions, images are degraded due to the scattering and attenuation of atmospheric particles, reducing the contrast and visibility and changing the color. This degradation depends on the distance, the density of the atmospheric particles and the wavelength. We have tested and applied five single image dehazing algorithms, originally developed to work on RGB images and not requiring user interaction and/or prior knowledge about the images, on a spectral hazy image database in the visible range. We have made the evaluation using two strategies: the first is based on the analysis of eleven state-of-the-art metrics and the second is two psychophysical experiments with 126 subjects. Our results suggest that the higher the wavelength within the visible range is, the higher the quality of the dehazed images. The quality increases for low haze/fog levels. The choice of the best performing algorithm depends on the criterion prioritized by the metric design strategy. The psychophysical experiment results show that the level of agreement between observers and metrics depends on the criterion set for the observers’ task.

show abstract

Section: Introductionmentioning

confidence: 99%

Single Image Dehazing Algorithm Analysis with Hyperspectral Images in the Visible Range

Martínez-Domingo

Valero

Nieves

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…'R image' is computed from the RGB image by separating the R component only as depicted in Equation (1). Similarly, 'G image' and 'B image' are computed from the RGB image by separating the G and B components, respectively as depicted in Equations ( 2) and (3).…”

Section: Start;mentioning

confidence: 99%

“…The lights scattered by these particles will also affect the luminance intensity of the nearby pixels in an image. [1][2][3][4][5] This will create fading and low contrast pixels in an image. Hence, the visibility of the image is degraded with respect to increasing these scattered components in outdoor or indoor environments.…”

mentioning

confidence: 99%

An efficient approach for removing haze from single image using Gaussian pyramidal decomposition

Pandian¹,

Poruran²

2021

Concurrency and Computation

View full text Add to dashboard Cite

The visibility of the image is degraded by haze components which are affected in image during image acquisition process. The haze removal process can be categorized into haze reduction from single image and haze reduction from multiple images. The second case consumes more time and the complexity of algorithm is high. In order to overcome such limitations, this paper proposes an efficient methodology for haze reduction in single acquired image. In this paper, haze detection and removing methodology is proposed using Gaussian pyramidal decomposition. This proposed methodology is tested on both indoor and outdoor haze affected images. The performance of this proposed haze removal algorithm is analyzed with respect to average running time and peak signal to noise ratio, mean square error, mean absolute error, Entropy, and normalized histogram intersection coefficient. K E Y W O R D Sdecomposition, Gaussian pyramidal, haze detection, single image INTRODUCTIONImage surveillance and object detection in an image plays an important role in real world applications. During the acquiring of the images, hazy and foggy particles will present in the image which degrades the quality of the acquired images. The lights scattered by these particles will also affect the luminance intensity of the nearby pixels in an image. [1][2][3][4][5] This will create fading and low contrast pixels in an image. Hence, the visibility of the image is degraded with respect to increasing these scattered components in outdoor or indoor environments. This will create many problems for real time image processing applications such as unmanned vehicle moving system and satellite image system. 6,7 Hence, there is a need for removing the haze components from the acquired image for improving the quality of the image. This will help the computer vision based applications in real time image processing applications. 8 Figure 1(A) shows the haze affected in outdoor images and Figure 1(B) shows the haze affected in indoor images.The performance of computer vision algorithms and advanced image editing algorithms can also be improved. Therefore, haze removal is highly demanded in image processing, computational photography and computer vision applications. Since the amount of scattering depends on the unknown distances of the scene points from the camera and the air-light is also unknown, it is challenging to remove haze from haze images, especially when there is only a single haze image. Many methods were presented for detecting and removing the haze components by using multiple images. [9][10][11][12][13] This process required complex algorithm for removing the haze from the image using multiple images. Also, the average time consumption for removing the haze component from the single image by multiple images is high. In order to overcome such limitations in conventional haze removing process, this paper proposes an efficient methodology for removing the haze components from the single source image only. This method uses Gaussian pyramidal decomposition (GPD) a...

show abstract

“…Recent work done on real-time enhancement methods impose special case limitations making them rather problem oriented, such as the case with [1] who assume static background, or requires stable objects in the training frames for temporal clustering [13], others assume that moving objects (changing pixels across frames) are minimal [14] , while some other methods are meant mainly to enhance dark images and cannot recover information from the shadowed or dark areas of images that had near-black intensities [15], some like [16] focused on finding the visibility distance and other parameters in Koschmieder's model rather than actually enhancing the video. While the method proposed by [6] need a soft matting algorithm to improve the quality of the transmission map needed for the overall enhancement, which consumes a lot of time as stated by [17]: "A component wise analysis of He et al's method shows that the processing time predominantly depends on the soft matting algorithm, therefore reducing or even eliminating the processing time of the soft processing would improve the overall dehazing time greatly".…”

Section: Image Optical Scattering Modelmentioning

confidence: 99%

Various Weather Conditions Using Dark Channel and Fuzzy Logic for Real Time Videos

SAIKUMAR¹

2015

IJRET

View full text Add to dashboard Cite

Rain, fog and haze are natural phenomena that fade scenes, limit the visibility range, and cause shifts in colors. These phenomena also play a decisive role in determining the degree of reliability of many kinds of outdoor applications, such as aerial and satellite imaging, surveillance, and driver assistance systems. Thus, removing their effects from images/videos is very crucial. Due to its mathematically ill posed nature, enhancement process of rain, fog, and haze plagued images/videos is highly challenging. In this paper, we propose a fast yet robust technique to enhance the visibility of video frames using the dark channel prior combined with fuzzy logic-based technique. The dark channel prior is a statistical regularity of outdoor haze-free images based on the observation that most local patches in the haze-free images contain pixels which are dark in at least one color channel, where the fuzzy logic-based technique is used to map an input space to an output space using a collection of fuzzy membership functions and rules to decide softly in case of uncertainties. The combination of the dark channel and the fuzzy logic-based technique will produce high quality haze-free images in real-time. Furthermore, it will be combined with rules derived from the stable atmospheric scattering model and will yield a fast yet high quality enhancement results.

show abstract

A two-step approach to see-through bad weather for surveillance video quality enhancement

Cited by 35 publications

References 13 publications

Single Image Dehazing Algorithm Analysis with Hyperspectral Images in the Visible Range

Single Image Dehazing Algorithm Analysis with Hyperspectral Images in the Visible Range

An efficient approach for removing haze from single image using Gaussian pyramidal decomposition

Various Weather Conditions Using Dark Channel and Fuzzy Logic for Real Time Videos

Contact Info

Product

Resources

About