An unsupervised single-image dehazing method using a multiple scattering model is proposed. The method uses an undegraded atmospheric multiple scattering model and unsupervised learning to implement dehazing on single real-world image. The atmospheric multiple scattering model can avoid the influence of multiple scattering on the image and the unsupervised neural network can avoid the intensive operation on the data set. In this method, three unsupervised learning branches and a blur kernel estimation module estimate the scene radiation layer, transmission layer, atmospheric light layer, and blur kernel layer, respectively. In addition, the unsupervised loss function is constructed by prior knowledge to constrain the unsupervised branches. Finally, the output of the three unsupervised branches and the blur kernel estimation module synthesizes the haze image in a self-supervised way. A large number of experiments show that the proposed method has good performance in image dehazing compared with the six most advanced dehazing methods.

Unsupervised single-image dehazing using the multiple-scattering model.

While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. Unpaired real-world clean and hazy images are easily captured, and will serve as the important positive and negative samples respectively when training our UCL-Dehaze network. To train the network more effectively, we formulate a new self-contrastive perceptual loss function, which encourages the restored images to approach the positive samples and keep away from the negative samples in the embedding space. Besides the overall network architecture of UCL-Dehaze, adversarial training is utilized to align the distributions between the positive samples and the dehazed images. Compared with recent image dehazing works, UCL-Dehaze does not require paired data during training and utilizes unpaired positive/negative data to better enhance the dehazing performance. We conduct comprehensive experiments to evaluate our UCL-Dehaze and demonstrate its superiority over the state-of-the-arts, even only 1,800 unpaired real-world images are used to train our network. Source code has been available at https://github.com/yz-wang/UCL-Dehaze.

UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning

D<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e841" altimg="si1.svg"><mml:msup><mml:mrow /><mml:mrow><mml:mn>3</mml:mn></mml:mrow></mml:msup></mml:math>-Net: Integrated multi-task convolutional neural network for water surface deblurring, dehazing and object detect

This thesis describes research to prevent maritime safety accidents by notifying navigational signs when sea fog and haze occur in the marine environment. Artificial intelligence, a camera sensor, an embedded board, and an LED marine lantern were used to conduct the research. A deep learning-based dehaze model was learned by collecting real marine environment and open haze image data sets. By applying this learned model to the original hazy images, we obtained clear dehaze images. Comparing those two images, the concentration level of sea fog was derived into the PSNR and SSIM values. The brightness of the marine lantern was controlled through serial communication with the derived PSNR and SSIM values in a realized sea fog environment. As a result, it was possible to autonomously control the brightness of the marine lantern according to the concentration of sea fog, unlike the current marine lanterns, which adjust their brightness manually. This novel-developed lantern can efficiently utilize power consumption while enhancing its visibility. This method can be used for other fog concentration estimation systems at the embedded board level, so that applicable for local weather expectations, UAM navigation, and autonomous driving for marine ships.

/pdf/enhancement-of-marine-lanterns-visibility-under-high-haze-7vjchlg6.pdf

Enhancement of Marine Lantern’s Visibility under High Haze Using AI Camera and Sensor-Based Control System

This paper firstly introduces the background of the research on neural network and anomaly identification screening and mineralization prediction under semisupervised learning, then introduces supervised learning, semisupervised learning, unsupervised learning, and reinforcement learning, analyzes and compares their advantages and disadvantages, and concludes that unsupervised learning is the best way to process the data. In the research method, this paper classifies the obtained geochemical data by using semisupervised learning and then trains the obtained samples using the convolutional neural network model to obtain the mineralization prediction model and check its correctness, which finally provides the direction for the subsequent mineralization prediction research. 

Research on Anomaly Identification and Screening and Metallogenic Prediction Based on Semisupervised Neural Network

A semi-supervised image dehazing network was proposed which consists of the supervised branch and the unsupervised branch. In the supervision branch, the encoding–decoding neural network is used as the network structure, and the network is constrained by the supervision loss. In the unsupervised branch, two similar sub-networks are used to estimate the transmission map and atmospheric light, and the unsupervised loss is constructed through prior knowledge to constrain the unsupervised branch. In the semi-supervised image dehazing network, the supervised branch and the unsupervised branch will output dehazing result, respectively. Then by minimizing the reconstruction loss between the two images, the supervised and unsupervised branches are constrained to make the network more generalizable. The entire semi-supervised image dehazing network is trained in an end-to-end manner, and the supervised and unsupervised branch shares weights in the encoding part. Extensive experimental results show that the proposed method has good performance in image dehazing compared with six advanced dehazing methods.

Semi-Supervised image dehazing network

An end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. Compared with the atmospheric single scattering model, the atmospheric multiple scattering model could more comprehensively consider the effect of multiple scattering, which was important to the dense fog scenes, such as in ocean scene. Therefore, we used the atmospheric multiple scattering model to avoid image blurring. The model can directly generate the dehazing results, and unify the three parameters of the transmission map, the atmospheric light and the blur kernel into one formula. The latest smooth dilation and sub-pixel techniques were used in the network model. The latest techniques can avoid the gridding artifacts and the halo artifacts, the multi-scale sub-network was used to consider the features of multi-scale. In addition, multiple loss functions were used in end-to-end network. In the experimental results, the model was superior to the state-of-the-art models in terms of quantitatively and qualitatively.

/pdf/an-end-to-end-sea-fog-removal-network-using-multiple-43htba1se1.pdf

An end-to-end sea fog removal network using multiple scattering model

Automatic detection of surface defects in electronic panels is receiving increasing attention in the quality control of products. The surface defect detection of electronic panels is different from other target detection scenarios and is a meaningful and challenging problem. Its main manifestation is that surface defects of electronic panels usually exhibit extreme irregularity and small target characteristics, which bring great difficulties to the task of surface defect target detection including feature extraction and so on. The traditional methods can only detect a very small number of defect classes under specific detection conditions. And due to the weak robustness of these methods, they cannot be applied in real production scenarios on a large scale. Based on this, this paper applies the target detection technique under deep learning to the surface defect detection scenario of electronic panels for the first time. At the same time, in order to make the designed target detection network applicable to the electronic panel surface defect detection scenario and to enhance the interpretability of the designed target detection network in terms of computer mechanism. We design a deformable convolution module with a convolutional self-attentive module to learn the offset and a dual detection head incorporating the SE (Squeeze-and-Excitation) mechanism for the irregular characteristics of electronic panel surface defects and the small target characteristics, respectively. Finally, we carried out a series of experiments on our own electronic panel defect data set, including comparison with the most advanced target detection algorithms and a series of ablation experiments against our proposed method. The final experimental results prove that our method not only has better interpretability, but also has better metric performance, in which the map_0.5 metric reaches 78.257%, which is an increase of 13.506 percentage points over YOLOV5 and 33.457 percentage points higher than Retinanet. The results prove the proposed method is effective.

/pdf/surface-defect-detection-method-for-electronic-panels-based-2yawsagn.pdf

Surface defect detection method for electronic panels based on attention mechanism and dual detection heads

In water scenes, where hazy images are subject to multiple scattering and where ideal data sets are difficult to collect, many dehazing methods are not as effective as they could be. Therefore, an unsupervised water scene dehazing network using atmospheric multiple scattering model is proposed. Unlike previous image dehazing methods, our method uses the unsupervised neural network and the atmospheric multiple scattering model and solves the problem of difficult acquisition of ideal datasets and the effect of multiple scattering on the image. In our method, in order to embed the atmospheric multiple scattering model into the unsupervised dehazing network, the unsupervised dehazing network uses four branches to estimate the scene radiation layer, transmission map layer, blur kernel layer and atmospheric light layer, the hazy image is then synthesized from the four output layers, minimizing the input hazy image and the output hazy image, where the output scene radiation layer is the final dehazing image. In addition, we constructed unsupervised loss functions which applicable to image dehazing by prior knowledge, i.e., color attenuation energy loss and dark channel loss. The method has a wide range of applications, with haze being thick and variable in marine, river and lake scenes, the method can be used to assist ship vision for target detection or forward road recognition in hazy conditions. Through extensive experiments on synthetic and real-world images, the proposed method is able to recover the details, structure and texture of the water image better than five advanced dehazing methods.

Zhangjing Zheng

Papers

Semi-Supervised image dehazing network

An end-to-end sea fog removal network using multiple scattering model

Unsupervised single-image dehazing using the multiple-scattering model.

Surface defect detection method for electronic panels based on attention mechanism and dual detection heads

Unsupervised water scene dehazing network using multiple scattering model.