Dubok Park

Single image dehazing with image entropy and information fidelity

In this paper, we propose a new single image dehazing approach based on information fidelity and image entropy. The global atmospheric light is estimated by quadtree subdivision using transformed hazy images. Then, transmission is estimated by an objective function which is comprised of information fidelity and image entropy at non-overlapped sub-block regions. This is further refined by a Weighted Least Squares (WLS) optimization procedure to alleviate block artifacts. We compared performance of the proposed method with conventional methods to validate its effectiveness in an experiment.

A novel approach for denoising and enhancement of extremely low-light video

In this paper, a novel approach for noise reduction and enhancement of extremely low-light video is proposed. For noise removal, a motion adaptive temporal filtering based on a Kalman structured updating is presented. Dynamic range of denoised video is increased by adjustment of RGB histograms using Gamma correction with adaptive clipping thresholds. Finally, residual noise is removed using a nonlocal means (NLM) denoising filter. The proposed method works directly on the color filter array (CFA) raw video for achieving low memory consumption1.

Fog-degraded image restoration using characteristics of RGB channel in single monocular image

Images captured under foggy conditions often have poor contrast and color. This is primarily due to air-light which degrades image quality exponentially with fog depth between the scene and the camera. In this paper, we restore fog-degraded images by first estimating depth using the physical model characterizing the RGB channels in a single monocular image. The fog effects are then removed by subtracting the estimated irradiance, which is empirically related to the scene depth information obtained, from the total irradiance received by the sensor. Effective restoration of color and contrast of images taken under foggy conditions are demonstrated. In the experiments, we validate the effectiveness of our method via representative performance measurements.

Single image haze removal using novel estimation of atmospheric light and transmission

This paper presents a new single image dehaze approach that uses a novel estimation of the atmospheric light and media transmission. Conventional dehaze methods often result in degraded images with low contrast and/or oversaturation of color in some regions. In order to mitigate these problems we use local atmospheric light and estimate the media transmission for each local region by using an objective function represented by modified saturation evaluation metric and intensity difference. Experimental results on a variety of outdoor haze images show that the proposed method achieves excellent restoration in terms of contrast, color fidelity and image visibility.

A novel framework for extremely low-light video enhancement

In this paper, we propose a novel framework for enhancement of very low-light video. For noise reduction, motion adaptive temporal filtering based on the Kalman structured updating is presented. Dynamic range of denoised video is increased by adaptive adjustment of RGB histograms. Finally, remaining noise is removed using Non-local means (NLM) denoising. The proposed method exploits color filter array (CFA) raw data for achieving low memory consumption.

Enhancing underwater color images of diving mask mounted digital camera via non-local means denoising

This paper proposes a novel framework for enhancing underwater images captured by digital camera embedded into underwater diving mask. Our approach adjusts the color balance using biasness and average of luminance. Then, scene visibility is enhanced based on underwater image model. Magnified noise in enhanced images is alleviated by Non-local means (NLM) denoising. The final enhanced images are characterized by improved visibility while retaining color fidelity and reduced noise. Our method does not require specialized hardware or prior knowledge about the underwater environment.

Image enhancement for extremely low light conditions

In this paper, a novel methodology is proposed for contrast enhancement and noise reduction in very noisy data with low dynamic range on images captured by surveillance camera under extremely low light condition. For the initial noise reduction, a motion adaptive temporal filtering based on the Kalman filter is employed. Then, the denoised image is first inverted and subsequently dehazed as a tone mapping to enhance the visibility based on the observation that the inverted low light image presents quite similar characteristics to hazy image. Finally, the remaining noise is removed using the Non-local means (NLM) denoising step. The overall approach essentially transforms very dark images progressively into more visible form and effectively reduces the high intensity noise generated by the tone mapping process. From the experimental results, effectiveness of the proposed method is validated by comparing with the most recent and leading conventional method.

Nighttime image dehazing with local atmospheric light and weighted entropy

In this paper, we propose a novel framework for nighttime image dehazing based on a nighttime haze model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by combining global and local atmospheric lights using a local atmospheric selection map. The transmission is estimated by maximizing an objective function designed with weighted entropy. Finally, haze is removed using two estimated parameters which are atmospheric light and transmission. Experimental results validate the proposed method can achieve haze-free results while alleviating the glow effect.

Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems

Optical imaging systems are often degraded by scattering due to atmospheric particles, such as haze, fog, and mist. Imaging under nighttime haze conditions may suffer especially from the glows near active light sources as well as scattering. We present a methodology for nighttime image dehazing based on an optical imaging model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by assessing global and local atmospheric light using a local atmospheric selection rule. The transmission of light is then estimated by maximizing an objective function designed on the basis of weighted entropy. Finally, haze is removed using two estimated parameters, namely, atmospheric light and transmission. The visual and quantitative comparison of the experimental results with the results of existing state-of-the-art methods demonstrates the significance of the proposed approach.

Top-view people detection based on multiple subarea pose models for smart home system

In this paper, an effective top-view people detection algorithm based on multiple subarea models is proposed for smart home system. Conventional single model based detector is difficult to achieve high performance in top-view people detection since there are too many possible individual poses in the top-view based image scene and it is impossible to cover all the poses with single model. Therefore, this paper develops a model of 9 typical poses to mitigate the low detection performance problem of conventional method. Moreover, by restricting the local scope of every pose model, the proposed approach yields an improved detection rate while reducing false alarm compared to the conventional single model based detector.