Search

Image dehazing is always a hot topic in the field of computer vision since haze has significant impact on the imaging quality of camera. Therefore, many image dehazing methods have been proposed for the past decades. To help researchers who are new to this field quickly figure out the development history as well as the current status of image dehazing, this review analyzes some representative dehazing methods, evaluates their advantages and disadvantages, and most importantly, points out the best dehazing method from different viewpoints. A large quantity of experiments show that AECR-Net can be generally considered to be the best dehazing algorithm and Tarel method can be regarded as the best real-time dehazing method. Besides, the mainstream benchmark, metrics, challenges and opportunities for image dehazing are also discussed in this review. [ABSTRACT FROM AUTHOR]

Main challenges for developing data-based models lie in the existence of high-dimensional and possibly missing observations that exist in stored data from industry process. Variational autoencoder (VAE) as one of the deep learning methods has been applied for extracting useful information or features from high-dimensional dataset. Considering that existing VAE is unsupervised, an output-relevant VAE is proposed for extracting output-relevant features in this work. By using correlation between process variables, different weight is correspondingly assigned to each input variable. With symmetric Kullback–Leibler (SKL) divergence, the similarity is evaluated between the stored samples and a query sample. According to the values of the SKL divergence, data relevant for modeling are selected. Subsequently, Gaussian process regression (GPR) is utilized to establish a model between the input and the corresponding output at the query sample. In addition, owing to the common existence of missing data in output data set, the parameters and missing data in the GPR are estimated simultaneously. A practical debutanizer industrial process is utilized to illustrate the effectiveness of the proposed method. • An output-relevant VAE is proposed for extracting output-relevant features by using correlation between process variables. • With symmetric Kullback–Leibler divergence, the similarity is evaluated between the stored samples and a query sample. According to the values of the SKL divergence, data relevant for modeling are selected. • Owing to the common existence of missing data in output data set, the parameters and missing data in the GPR are estimated simultaneously. • A practical debutanizer industrial process is utilized to illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a deep convolutional network for single image dehazing based on derived image fusion strategy. Instead of estimating the transmission map and atmospheric light as previously performed, we directly generate a haze-free image by the proposed end-to-end trainable neural network. We derive five maps from the original hazy image based on the characteristics of the hazy scene to improve the dehazing performance. First, the exposure map (EM) and saliency map (SM) complement each other to focus on details in far-away and near-region scenes. Second, the white balance map (BM) and gamma correction map (GM) are employed to recover the latent colour and intensity components of the scene. Finally, the haze veil map (VM) is introduced to enhance the global image contrast. To efficiently blend the five derived maps, we propose a U-shaped deep convolutional network consisting of encoder and decoder layers to generate a haze-free image. The convolutional layers transferred from the pretrained ResNet50 are used as encoder layers for hierarchical feature extraction. Two efficient blocks, named the cascaded residual block and the channel compression block, are proposed in the network for better dehazing performance. The final dehazed result is generated by combining the significant features of the different derived maps. Additionally, perceptual loss is introduced for better visual quality. The experimental results for both synthetic and natural hazy images demonstrate that our algorithm performs comparably or even better than state-of-the-art methods in terms of the peak signal-to-noise ratio (PSNR), structure similarity (SSIM) and visual quality. [ABSTRACT FROM AUTHOR]

• Dilated convolutions ensure better feature transfer and accurate classification that result in a sensitivity boost. • Dilated convolutions serve as the main constituents of decoder, encoder blocks and skip connections. • Dilated convolutions of different rates are more effective at capturing dynamically complex blood vessels. • Proposed Weighted multi-output fusion retrieves high fidelity vascular map by extracting critical features from each output block. Retinal image segmentation can help clinicians detect pathological disorders by studying changes in retinal blood vessels. This early detection can help prevent blindness and many other vision impairments. So far, several supervised and unsupervised methods have been proposed for the task of automatic blood vessel segmentation. However, the sensitivity and the robustness of these methods can be improved by correctly classifying more vessel pixels. We proposed an automatic, retinal blood vessel segmentation method based on the U-net architecture. This end-to-end framework utilizes preprocessing and a data augmentation pipeline for training. The architecture utilizes multiscale input and multioutput modules with improved skip connections and the correct use of dilated convolutions for effective feature extraction. In multiscale input, the input image is scaled down and concatenated with the output of convolutional blocks at different points in the encoder path to ensure the feature transfer of the original image. The multioutput module obtains upsampled outputs from each decoder block that are combined to obtain the final output. Skip paths connect each encoder block with the corresponding decoder block, and the whole architecture utilizes different dilation rates to improve the overall feature extraction. The proposed method achieved an accuracy: of 0.9680, 0.9694, and 0.9701; sensitivity of 0.8837, 0.8263, and 0.8713; and Intersection Over Union (IOU) of 0.8698, 0.7951, and 0.8184 with three publicly available datasets: DRIVE, STARE, and CHASE, respectively. An ablation study is performed to show the contribution of each proposed module and technique. The evaluation metrics revealed that the performance of the proposed method is higher than that of the original U-net and other U-net-based architectures, as well as many other state-of-the-art segmentation techniques, and that the proposed method is robust to noise. [ABSTRACT FROM AUTHOR]

Considering industrial process with high-dimensional, intrinsic nonlinearities and possibly abnormal observations, a robust deep learning soft sensor model is developed under the just-in-time learning framework. As an unsupervised deep learning approach, Variational Autoencoder (VAE) has been successfully applied to soft sensing problems owing to its ability to describe the latent representations by probability distributions. In this work, to construct high performance soft sensor model, mutual information (MI) is first introduced for input variable selection. By further incorporating MI as weights on variable of the traditional VAE model, a MI-based output-relevant VAE is developed. For each new sample that arrives, by utilizing Symmetric Kullback-Leibler (SKL) divergence, its relevance with historical samples is determined. Based on the SKL divergence, the input samples that are most relevant to the query sample can be collected. The selected historical input samples and corresponding output samples are employed to build a Gaussian process regression (GPR) local model. Expectation maximation (EM) algorithm is utilized to deal with the nonlinearity and abnormal output observations in GPR local model simultaneously for robustness of the soft sensors. Numerical simulations and a benchmark process are employed to validate the effectiveness of the proposed soft sensor, which demonstrates its superior performance over traditional approaches. • A MI-based output-relevant VAE is presented by incorporating MI as weights on variable of the traditional VAE model. • The selected historical samples through SKL divergence are employed to build a GPR local model. • The abnormal output observations in GPR local model for robustness of the soft sensors is dealt with the EM algorithm. • Numerical simulations and a benchmark process are employed to validate the effectiveness of the proposed soft sensor. [ABSTRACT FROM AUTHOR]

This paper presents a variational autoencoder-based just-in-time (JIT) learning framework for soft sensor modeling. Just-in-Time learning is often applied for soft sensor modeling in industrial processes. However, traditional just-in-time learning methods measure the similarity based on Euclidean distance, which has not taken into consideration the uncertainty in variables. To improve traditional just-in-time learning methods, in the proposed approach, the variational autoencoder is employed to extract features from input data set containing noise. Each feature variable is expressed by a Gaussian distribution. Then, by using the distribution of each feature variable, Kullback-Leibler divergence is employed to evaluate the similarity between the historical samples and a query sample. Furthermore, historical samples that are most similar to the query samples based on the values of the Kullback-Leibler divergence are selected for modeling. Finally, Gaussian process regression as a nonlinear regression model, is used to model the relationship between the selected input samples and the corresponding output samples, and then make a prediction. A numerical example as well as application on a practical debutanizer industrial process demonstrates the effectiveness of the proposed method. • Variational autoencoder is employed to extract the distribution of each feature variable. • Kullback-Leibler divergence is employed to evaluate the similarity between the historical samples and a query sample. • Gaussian process regression is used to build model based on the selected samples, and then make a prediction. • The effectiveness of the proposed method is demonstrated through a numerical example and an industrial process. [ABSTRACT FROM AUTHOR]