Detail Preserving Low Illumination Image and Video Enhancement Algorithm Based on Dark Channel Prior

In low illumination situations, insufficient light in the monitoring device results in poor visibility of effective information, which cannot meet practical applications. To overcome the above problems, a detail preserving low illumination video image enhancement algorithm based on dark channel prior is proposed in this paper. First, a dark channel refinement method is proposed, which is defined by imposing a structure prior to the initial dark channel to improve the image brightness. Second, an anisotropic guided filter (AnisGF) is used to refine the transmission, which preserves the edges of the image. Finally, a detail enhancement algorithm is proposed to avoid the problem of insufficient detail in the initial enhancement image. To avoid video flicker, the next video frames are enhanced based on the brightness of the first enhanced frame. Qualitative and quantitative analysis shows that the proposed algorithm is superior to the contrast algorithm, in which the proposed algorithm ranks first in average gradient, edge intensity, contrast, and patch-based contrast quality index. It can be effectively applied to the enhancement of surveillance video images and for wider computer vision applications.

Underwater video transmission with video enhancement using reduce hazing algorithm

Underwater video regulation is an insightful research field that can help engineers with bettering investigation on the lowered condition. Submerged video preparing has been utilized in a many fields, such as submerged infinitesimal location, landscape examining, mine identification, media transmission connections, and self-proficient lowered vehicles. Be that as it may, submerged video experiences solid assimilation, dissipating, shading contortion, and clamor from the manufactured light sources, causing video obscure, cloudiness, and a somewhat blue or greenish tone. In this way, the improvement can be separated into two techniques, submerged video de-preliminaries and underexposed video concealing remaking. Relentless in remote correspondence structures, for instance 3G, 4G, and so on, a coming crisis is endless deftly of the nonattendance of consistently Radio Frequency (RF) resources; this deterrent in moving speed cannot strengthen the improvement notable for high information speed. So the new innovation of Light-Fidelity (Li-Fi) came into picture. This innovation can be contrasted to that of Wi-Fi and offers points of interest like expanded available spectrum efficiency, effectiveness, security, low idleness and a lot higher speed. Communication is accomplished by exchanging light-emitting diode (LED) lights on and off at a speed higher than what is detectable to the human eye. This paper presents the explanation behind underexposed picture corruption and surveys the cutting-edge knowledge calculations like video reduce hazing algorithm. In this calculation, it uses two different de-hazing methods, simple Dark Channel Prior (DCP) and Approximate Dark Channel Prior (ADCP), to reduce haze in a video.

Spatio-temporal deep learning model for distortion classification in laparoscopic video

Background: Laparoscopy is a surgery performed in the abdomen without making large incisions in the skin and with the aid of a video camera, resulting in laparoscopic videos. The laparoscopic video is prone to various distortions such as noise, smoke, uneven illumination, defocus blur, and motion blur. One of the main components in the feedback loop of video enhancement systems is distortion identification, which automatically classifies the distortions affecting the videos and selects the video enhancement algorithm accordingly. This paper aims to address the laparoscopic video distortion identification problem by developing fast and accurate multi-label distortion classification using a deep learning model. Current deep learning solutions based on convolutional neural networks (CNNs) can address laparoscopic video distortion classification, but they learn only spatial information. Methods: In this paper, utilization of both spatial and temporal features in a CNN-long short-term memory (CNN-LSTM) model is proposed as a novel solution to enhance the classification. First, pre-trained ResNet50 CNN was used to extract spatial features from each video frame by transferring representation from large-scale natural images to laparoscopic images. Next, LSTM was utilized to consider the temporal relation between the features extracted from the laparoscopic video frames to produce multi-label categories. A novel laparoscopic video dataset proposed in the ICIP2020 challenge was used for training and evaluation of the proposed method. Results: The experiments conducted show that the proposed CNN-LSTM outperforms the existing solutions in terms of accuracy (85%), and F1-score (94.2%). Additionally, the proposed distortion identification model is able to run in real-time with low inference time (0.15 sec). Conclusions: The proposed CNN-LSTM model is a feasible solution to be utilized in laparoscopic videos for distortion identification.

Real Time Night Vision Surveillance using Improved Dark Channel Prior

Videos taken under low lighting conditions usually result in severe loss of visibility and contrast and are uncomfortable for observation and analysis. Night vision cameras that cater to the needs are expensive and less versatile. To be cost effective and extract maximum information from videos taken in low lit conditions, video enhancing techniques must be used. Though there are many night vision enhancement techniques available in literature, this paper particularly emphasizes about Improved Dark Channel Prior algorithm and its results. This approach suits well for real time night video enhancement. It has been found that a pixel-wise inversion of a night video appears very similar to the video obtained during foggy days. The same idea of haze removal approach is used to boost the visual quality of night videos. An improved dark channel prior model is presented that is integrated with Gaussian Pyramid operators for local smoothing. The experimental results show that the proposed method can boost the perceptual quality of detailing in night videos.