Image dehazing is a common operation in autonomous driving, traffic monitoring and surveillance. Learning-based image dehazing has achieved excellent performance recently. However, it is nearly impossible to capture pairs of hazy/clean images from the real world to train an image dehazing network. Most of existing dehazing models that are learnt from synthetically generated hazy images generalize poorly on real-world hazy scenarios due to the obvious domain shift. To deal with this unpaired problem arisen by real-world hazy images, we present Cycle Spectral Normalized Soft likelihood estimation Patch Generative Adversarial Network (Cycle-SNSPGAN) for image dehazing. Cycle-SNSPGAN is an unsupervised dehazing framework to boost the generalization ability on real-world hazy images. To leverage unpaired samples of real-world hazy images without relying on their clean counterparts, we design an SN-Soft-Patch GAN and exploit a new cyclic self-perceptual loss which avoids using the ground-truth image to compute the perceptual similarity. Moreover, a significant color loss is adopted to brighten the dehazed images as human expects. Both visual and numerical results show clear improvements of the proposed Cycle-SNSPGAN over state-of-the-arts in terms of hazy-robustness and image detail recovery, with even only a small dataset training our Cycle-SNSPGAN. Code has been available at https://github.com/yz-wang/Cycle-SNSPGAN.

Mobile Laser Scanning (MLS) system can provide high-density and accurate 3D point clouds that enable rapid pavement crack detection for road maintenance tasks. Supervised learning-based algorithms have been proved pretty effective for handling such a large amount of inhomogeneous and unstructured point clouds. However, these algorithms often rely on a lot of annotated data, which is labor-intensive and time-consuming. This paper presents a semi-supervised point-level approach to overcome this challenge. We propose a graph-widen module to construct a reasonable graph structure for point clouds, increasing the detection performance of graph convolutional networks (GCN). The constructed graph characterizes the local features from a small amount of annotated data, avoiding information loss and dramatically reduces the dependence on annotated data. The MLS point clouds acquired by a commercial RIEGL VMX-450 system are used in this study. The experimental results demonstrate that our method outperforms the state-of-the-art point-level methods in terms of recall, F1 score, and efficiency while achieving comparable accuracy.

Point cloud completion is able to estimate the complete point cloud starting from the missing point cloud, which obtains higher quality point cloud data for widely used in remote sensing 3D modeling, medical imaging, robot vision, etc. The challenge of point clouds mainly lies in the disordered and unstructured nature, which makes point cloud completion difficult. Point cloud completion research can be broadly categorized into traditional approaches and deep learning based methods. Recently, intensive research has primarily focused on deep learning based methods, given robustness and efficiency in processing the substantial missing data encountered in complex real world scenes. In addition, deep learning based methods have higher generalization performance. To stimulate future research, this survey presents a comprehensive review of existing traditional and deep learning based 3D point cloud completion methods. This review conducts extensive examinations of each stage of the process, providing a compilation of famous datasets, metrics, and their respective characteristics. Additionally, the impacts of subsequent downstream application tasks with or without completion are discussed, followed by some potential future issues in point cloud completion

Extracting the power lines and pylons automatically and accurately from airborne LiDAR data is a critical step in inspecting the routine power line, especially in the remote mountainous areas. However, challenges arise in using existing methods to extract the targets from large scenarios of remote mountainous areas since the terrain is undulating, and the features are difficult to distinguish. In this article, to overcome these challenges, we propose a graph convolutional network (GCN)-based method to extract power lines and pylons from Airborne LiDAR point clouds. First, data augmentation and near-ground filtering methods are developed to overcome the problems of insufficient and imbalanced samples in the LiDAR data. Then, a GCN-based framework is proposed to extract the power lines and pylons, which consist of two main modules, i.e., the neighborhood dimension information (NDI) module and the neighborhood geometry information aggregation (NGIA) module. These two modules are designed to strengthen the model’s ability to portray local geometric details. Besides, an attention fusion module is investigated to further improve the NDI and NGIA features. Finally, a line structure constraint algorithm is proposed to identify individual power lines, where the power corridor is reconstructed using a polynomial-based algorithm. Numerical experiments are conducted based on two different power line scenarios acquired in mountainous areas. The results demonstrate the superior performances of the proposed method over several existing algorithms, where the $F_{1}$ score and quality of the power line are 99.3% and 98.6%, and the results of the pylon are 96% and 92.4%, respectively. The identification rate of power line identification is above 98%.

Building extraction is a fundamental research topic in remote sensing image interpretation. Convolutional neural network (CNN)-based building extraction algorithms have achieved high accuracy but require a large account of parameters and calculations, which hinders the practical application of these algorithms. To address the challenge, we propose a lightweight network (RSR-Net) for building extraction from remote sensing images. The network consists of three basic units with only a few parameters, and uses the idea of the fusion of shallow features and deep features, which is proposed by U-Net. Before features fusion, the squeeze-and-excitation (SE) module in RSR-Net assigned channel weights to these deep and shallow features. This operation can effectively reduce the influence of noise caused by shallow features in feature fusion, so as to improve the performance of the model. We estimated our network on datasets and achieved 88.32%, 71.58%, and 77.07% intersection-over-union (IoU) on datasets of aerial image and satellite image in Wuhan University (WHU) dataset, and the self-made building dataset of Guangzhou University Town, with only 2.81 M parameters and 6.91 G floating point operations (FLOPs). In addition, we propose a strategy combining target and background prediction, which makes RSR-Net achieve 0.37% improvement in IoU on WHU aerial image dataset. The effectiveness of RSR-Net is high. It showed that the proposed network is light and fast for the application of convolution neural network algorithm in practice.