Chunmei Qing

DehazeNet: An End-to-End System for Single Image Haze Removal

Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts convolutional neural network-based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, the layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called bilateral rectified linear unit, which is able to improve the quality of recovered haze-free image. We establish connections between the components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use.Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts convolutional neural network-based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, the layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called bilateral rectified linear unit, which is able to improve the quality of recovered haze-free image. We establish connections between the components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use.

Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging

Stacked autoencoders (SAEs), as part of the deep learning (DL) framework, have been recently proposed for feature extraction in hyperspectral remote sensing. With the help of hidden nodes in deep layers, a high-level abstraction is achieved for data reduction whilst maintaining the key information of the data. As hidden nodes in SAEs have to deal simultaneously with hundreds of features from hypercubes as inputs, this increases the complexity of the process and leads to limited abstraction and performance. As such, segmented SAE (S-SAE) is proposed by confronting the original features into smaller data segments, which are separately processed by different smaller SAEs. This has resulted in reduced complexity but improved efficacy of data abstraction and accuracy of data classification.

Simple to Complex Transfer Learning for Action Recognition

Recognizing complex human actions is very challenging, since training a robust learning model requires a large amount of labeled data, which is difficult to acquire. Considering that each complex action is composed of a sequence of simple actions which can be easily obtained from existing data sets, this paper presents a simple to complex action transfer learning model (SCA-TLM) for complex human action recognition. SCA-TLM improves the performance of complex action recognition by leveraging the abundant labeled simple actions. In particular, it optimizes the weight parameters, enabling the complex actions to be learned to be reconstructed by simple actions. The optimal reconstruct coefficients are acquired by minimizing the objective function, and the target weight parameters are then represented as a combination of source weight parameters. The main advantage of the proposed SCA-TLM compared with existing approaches is that we exploit simple actions to recognize complex actions instead of only using complex actions as training samples. To validate the proposed SCA-TLM, we conduct extensive experiments on two well-known complex action data sets: 1) Olympic Sports data set and 2) UCF50 data set. The results show the effectiveness of the proposed SCA-TLM for complex action recognition.

Temporal Variance Analysis for Action Recognition

Slow feature analysis (SFA) extracts slowly varying signals from input data and has been used to model complex cells in the primary visual cortex (V1). It transmits information to both ventral and dorsal pathways to process appearance and motion information, respectively. However, SFA only uses slowly varying features for local feature extraction, because they represent appearance information more effectively than motion information. To better utilize temporal information, we propose temporal variance analysis (TVA) as a generalization of SFA. TVA learns a linear transformation matrix that projects multidimensional temporal data to temporal components with temporal variance. Inspired by the function of V1, we learn receptive fields by TVA and apply convolution and pooling to extract local features. Embedded in the improved dense trajectory framework, TVA for action recognition is proposed to: 1) extract appearance and motion features from gray using slow and fast filters, respectively; 2) extract additional motion features using slow filters from horizontal and vertical optical flows; and 3) separately encode extracted local features with different temporal variances and concatenate all the encoded features as final features. We evaluate the proposed TVA features on several challenging data sets and show that both slow and fast features are useful in the low-level feature extraction. Experimental results show that the proposed TVA features outperform the conventional histogram-based features, and excellent results can be achieved by combining all TVA features.

Underwater video dehazing based on spatial---temporal information fusion

In this paper, a novel multidimensional underwater video dehazing method is presented to restore and enhance the underwater degraded videos. Videos in the underwater suffer from medium scattering and light absorption. The absorption of light traveling in the water makes the underwater hazing videos different from the atmosphere hazing videos. In order to dehaze the underwater videos, a spatial–temporal information fusion method is proposed which includes two main parts. One is transmission estimation, which is based on the correlation between the adjacent frames of videos to keep the color consistency, where fast tracking and the least square method are used to reduce the influence of camera and object motions and water flowing. Another part is background light estimation to keep consistent atmospheric light values in a video. Extensive experimental results demonstrate that the proposed algorithm can have superior haze removing and color balancing capabilities.

Underwater image enhancement with an adaptive dehazing framework

In this paper, we propose a novel method to restore and enhance the underwater degraded images. Underwater images suffer from two major problems of distortion: scattering and color change. Scattering is caused by large suspended particles and color distortion is caused by the varying degrees of attenuation encountered by light traveling in the water with different wavelengths, rendering some characteristics which are different from the foggy images in the atmosphere. Our key contribution is proposed an adaptive dahazing framework for underwater image enhancement, which includes two main parts: adaptive underwater brightness estimation and locally adaptive histogram equalization. The enhanced images are characterized by more accurate exposure of underwater images, especially in the dark regions. And improved contrast for the better details and edges are enhanced significantly in the images. Extensive experimental results demonstrate that our method is comparable to higher quality than the state-of-the-art methods.

Robust object tracking based on sparse representation and incremental weighted PCA

Object tracking plays a crucial role in many applications of computer vision, but it is still a challenging problem due to the variations of illumination, shape deformation and occlusion. A new robust tracking method based on incremental weighted PCA and sparse representation is proposed. An iterative process consisting of a soft segmentation step and a foreground distribution update step is adpoted to estimate the foreground distribution, cooperating with incremental weighted PCA, we can get the target appearance in terms of the PCA components with less impact of the background in the target templates. In order to make the target appearance model more discriminative, trivial and background templates are both added to the dictionary for sparse representation of the target appearance. Experiments show that the proposed method with some level of background awareness is robust against illumination change, occlusion and appearance variation, and outperforms several latest important tracking methods in terms of tracking performance.

Image and video dehazing using view-based cluster segmentation

To avoid distortion in sky regions and make the sky and white objects clear, in this paper we propose a new image and video dehazing method utilizing the view-based cluster segmentation. Firstly, GMM(Gaussian Mixture Model)is utilized to cluster the depth map based on the distant view to estimate the sky region and then the transmission estimation is modified to reduce distortion. Secondly, we present to use GMM based on Color Attenuation Prior to divide a single hazy image into K classifications, so that the atmospheric light estimation is refined to improve global contrast. Finally, online GMM cluster is applied to video dehazing. Extensive experimental results demonstrate that the proposed algorithm can have superior haze removing and color balancing capabilities.

Dehazing with improved heterogeneous atmosphere light estimation and a nonlinear color attenuation prior model

In this paper, we propose an improved heterogeneous atmosphere light estimation method and a novel depth estimation algorithm with Color Attenuation Prior (CAP) to dehaze single image. Firstly, it estimates the atmosphere light with mean-pooling on the illuminance component from HSV color space. The estimated atmosphere light is more robust because of its independence of a specified pixel. Secondly, the scene depth is estimated by a nonlinear CAP model which can overcome the defects of the occurrence of negative scene depths from the linear CAP model. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art methods in dehazing images.

High speed deep networks based on Discrete Cosine Transformation

The traditional deep networks take raw pixels of data as input, and automatically learn features using unsupervised learning algorithms. In this configuration, in order to learn good features, the networks usually have multi-layer and many hidden units which lead to extremely high training time costs. As a widely used image compression algorithm, Discrete Cosine Transformation (DCT) is utilized to reduce image information redundancy because only a limited number of the DCT coefficients can preserve the most important image information. In this paper, it is proposed that a novel framework by combining DCT and deep networks for high speed object recognition system. The use of a small subset of DCT coefficients of data to feed into a 2-layer sparse auto-encoders instead of raw pixels. Because of the excellent decorrelation and energy compaction properties of DCT, this approach is proved experimentally not only efficient, but also it is a computationally attractive approach for processing high-resolution images in a deep architecture.