“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

State-of-the-art in artificial neural network applications: A survey

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

This paper proposes an efficient method to modify histograms and enhance contrast in digital images. Enhancement plays a significant role in digital image processing, computer vision, and pattern recognition. We present an automatic transformation technique that improves the brightness of dimmed images via the gamma correction and probability distribution of luminance pixels. To enhance video, the proposed image-enhancement method uses temporal information regarding the differences between each frame to reduce computational complexity. Experimental results demonstrate that the proposed method produces enhanced images of comparable or higher quality than those produced using previous state-of-the-art methods.

Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution

We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together. The end-to-end learning is achieved by directly embedding the atmospheric scattering model into the network, thereby ensuring that the proposed method strictly follows the physics-driven scattering model for dehazing. Inspired by the dense network that can maximize the information flow along features from different levels, we propose a new edge-preserving densely connected encoder-decoder structure with multi-level pyramid pooling module for estimating the transmission map. This network is optimized using a newly introduced edge-preserving loss function. To further incorporate the mutual structural information between the estimated transmission map and the dehazed result, we propose a joint-discriminator based on generative adversarial network framework to decide whether the corresponding dehazed image and the estimated transmission map are real or fake. An ablation study is conducted to demonstrate the effectiveness of each module evaluated at both estimated transmission map and dehazed result. Extensive experiments demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods. Code and dataset is made available at: https://github.com/hezhangsprinter/DCPDN

/pdf/densely-connected-pyramid-dehazing-network-5c16u3fd6v.pdf

Densely Connected Pyramid Dehazing Network

Motion detection is the first essential process in the extraction of information regarding moving objects and makes use of stabilization in functional areas, such as tracking, classification, recognition, and so on. In this paper, we propose a novel and accurate approach to motion detection for the automatic video surveillance system. Our method achieves complete detection of moving objects by involving three significant proposed modules: a background modeling (BM) module, an alarm trigger (AT) module, and an object extraction (OE) module. For our proposed BM module, a unique two-phase background matching procedure is performed using rapid matching followed by accurate matching in order to produce optimum background pixels for the background model. Next, our proposed AT module eliminates the unnecessary examination of the entire background region, allowing the subsequent OE module to only process blocks containing moving objects. Finally, the OE module forms the binary object detection mask in order to achieve highly complete detection of moving objects. The detection results produced by our proposed (PRO) method were both qualitatively and quantitatively analyzed through visual inspection and for accuracy, along with comparisons to the results produced by other state-of-the-art methods. The analyses show that our PRO method has a substantially higher degree of efficacy, outperforming other methods by an metric accuracy rate of up to 53.43%.

An Advanced Motion Detection Algorithm With Video Quality Analysis for Video Surveillance Systems

The visibility of outdoor images captured in inclement weather is often degraded due to the presence of haze, fog, sandstorms, and so on. Poor visibility caused by atmospheric phenomena in turn causes failure in computer vision applications, such as outdoor object recognition systems, obstacle detection systems, video surveillance systems, and intelligent transportation systems. In order to solve this problem, visibility restoration (VR) techniques have been developed and play an important role in many computer vision applications that operate in various weather conditions. However, removing haze from a single image with a complex structure and color distortion is a difficult task for VR techniques. This paper proposes a novel VR method that uses a combination of three major modules: 1) a depth estimation (DE) module; 2) a color analysis (CA) module; and 3) a VR module. The proposed DE module takes advantage of the median filter technique and adopts our adaptive gamma correction technique. By doing so, halo effects can be avoided in images with complex structures, and effective transmission map estimation can be achieved. The proposed CA module is based on the gray world assumption and analyzes the color characteristics of the input hazy image. Subsequently, the VR module uses the adjusted transmission map and the color-correlated information to repair the color distortion in variable scenes captured during inclement weather conditions. The experimental results demonstrate that our proposed method provides superior haze removal in comparison with the previous state-of-the-art method through qualitative and quantitative evaluations of different scenes captured during various weather conditions.

Visibility Restoration of Single Hazy Images Captured in Real-World Weather Conditions

Existing learning-based atmospheric particle-removal approaches such as those used for rainy and hazy images are designed with strong assumptions regarding spatial frequency, trajectory, and translucency. However, the removal of snow particles is more complicated because they possess additional attributes of particle size and shape, and these attributes may vary within a single image. Currently, hand-crafted features are still the mainstream for snow removal, making significant generalization difficult to achieve. In response, we have designed a multistage network named DesnowNet to in turn deal with the removal of translucent and opaque snow particles. We also differentiate snow attributes of translucency and chromatic aberration for accurate estimation. Moreover, our approach individually estimates residual complements of the snow-free images to recover details obscured by opaque snow. Additionally, a multi-scale design is utilized throughout the entire network to model the diversity of snow. As demonstrated in the qualitative and quantitative experiments, our approach outperforms state-of-the-art learning-based atmospheric phenomena removal methods and one semantic segmentation baseline on the proposed Snow100K dataset. The results indicate our network would benefit applications involving computer vision and graphics.

DesnowNet: Context-Aware Deep Network for Snow Removal

The visibility of images of outdoor road scenes will generally become degraded when captured during inclement weather conditions. Drivers often turn on the headlights of their vehicles and streetlights are often activated, resulting in localized light sources in images capturing road scenes in these conditions. Additionally, sandstorms are also weather events that are commonly encountered when driving in some regions. In sandstorms, atmospheric sand has a propensity to irregularly absorb specific portions of a spectrum, thereby causing color-shift problems in the captured image. Traditional state-of-the-art restoration techniques are unable to effectively cope with these hazy road images that feature localized light sources or color-shift problems. In response, the authors present a novel and effective haze removal approach to remedy problems caused by localized light sources and color shifts, which thereby achieves superior restoration results for single hazy images. The performance of the proposed method has been proven through quantitative and qualitative evaluations. Experimental results demonstrate that the proposed haze removal technique can more effectively recover scene radiance while demanding fewer computational costs than traditional state-of-the-art haze removal techniques.

Shih-Chia Huang

Papers

Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution

An Advanced Motion Detection Algorithm With Video Quality Analysis for Video Surveillance Systems

Visibility Restoration of Single Hazy Images Captured in Real-World Weather Conditions

DesnowNet: Context-Aware Deep Network for Snow Removal

An Efficient Visibility Enhancement Algorithm for Road Scenes Captured by Intelligent Transportation Systems