In this paper, we study the employment of multiple Unmanned Aerial Vehicles (UAVs) to monitor Points of Interests (PoIs) in a disaster area, e.g., collapsed buildings after an earthquake, where the UAVs can take photos and videos for the people trapped at PoIs, because such valuable information is imperative to make rescue decisions. Unlike most existing studies that ignored the monitoring time of PoIs and simply minimized the longest flying distance among the UAVs, we observe that it takes time to monitor the PoIs. Then, it is possible that the flying distance of a UAV in its flying tour may not be too long, the tour however contains many densely-located PoIs. Therefore, it will take a very long time for the UAV to monitor the PoIs in its tour. In this paper, we first formulate a problem of finding flying tours for $K$ given UAVs to collaboratively monitor PoIs in a disaster area, such that the maximum spent time of the $K$ UAVs among their tours is minimized, where the spent time of a UAV in its tour consists of the flying time and the PoI monitoring time. We then propose a novel $5\frac{1}{3}$ -approximation algorithm for the problem, improving the best approximation ratio 6 so far for the problem of minimizing the longest flying distance among the UAVs. In addition, we extend the proposed algorithm to the case that each UAV may not be able to monitor all PoIs assigned to it, due to its limited maximum flying time (e.g., 30 minutes), and the UAV must return to its depot to replace its battery. We finally evaluate the performance of the proposed algorithms via simulation environments, and experimental results show that the proposed algorithms are very promising. Especially, the maximum spent times of the $K$ UAVs in their tours by the proposed algorithms are up to 30 percent shorter than those by existing algorithms. In addition, the empirical approximation ratios of the proposed algorithms are no more than 2.4, which are much smaller than their theoretical approximation ratios that are at least $5\frac{1}{3}$ .

Outdoor images captured under bad weathers often suffer from low visibility. In this study, a novel method is presented to improve the visibility of a single input hazy image. On the basis of the observation that degradation of a hazy image occurs both in contrast and colour, the authors method aims at compensating the contrast and colour of the image, respectively. To achieve this, they propose a multi‐scale gradient domain contrast enhancement approach that handles the different residual images rather than the entire image, and correct the attenuation of colour according to the estimated transmission. Since there is no need to recover the scene radiance by the degradation model, their method depends less on the accuracy of transmission and does not require the estimation of atmospheric light. Experiments on a variety types of hazy images show that their method yields accurate results with fine details and vivid colour, even better than other state‐of‐the‐art dehazing methods.

In the clinical environment, myocardial infarction (MI) as one common cardiovascular disease is mainly evaluated using late gadolinium enhancement (LGE) cardiac magnetic resonance images (CMRIs). Accurate segmentation of the ventricles and the myocardium is a prerequisite for quantitative assessment of cardiac functions and disease progression. Performing the task using LGE images is, however, rather challenging due to heterogeneous image intensity distribution and lack of clear boundaries between adjacent organs and tissues. In this paper we propose a deep neural network method for automatic segmentation of the left ventricle (LV), right ventricle (RV), and left ventricular myocardium (LVM) from LGE CMRIs, which also leverages complementary information from cine and T2-weighted CMRIs if available. In the proposed method, termed SK-Unet, we augment the original U-Net model by adding a squeeze-and-excitation residual (SE-Res) module in the encoder and a selective kernel (SK) module in the decoder. The SE-Res module applies an attention mechanism to enhance informative feature extraction and suppress redundant ones. The SK module offers the ability to adaptively learn task-relevant multi-scale spatial features. We tested our method by participating in the MICCAI 2019 MS-CMRSeg challenge and achieved a mean dice score of 0.922 for LV segmentation, 0.827 for LVM, and 0.874 for RV. The results placed our method at the 1st place in the competition, and our accuracy of 0.827 also greatly surpasses the measured inter-observer agreement of 0.757 for manual segmentation of LVM in LGE CMRIs. The code accompanying our method is made available online at https://github.com/Xiyue-Wang/1st-in-MS-CMRSeg-2019 .

Pneumothorax is a common but life-threatening thoracic disease, which is difficult to diagnose based on chest X-ray images due to its subtle characteristics and low contrast of the disease regions. We aim to develop a fully automatic pneumothorax segmentation method to assist radiologists for timely and accurate diagnosis of pneumothorax. We propose a two-stage deep learning method. In the first stage, the chest X-ray image is classified as having pneumothorax or not using an ensemble of multiple modified U-Net models. Each model is trained using a multi-task learning strategy with two highly correlated tasks: pneumothorax classification and segmentation. The segmentation task helps the model focus on more relevant regions to improve classification accuracy. The second stage performs precise segmentation of pneumothorax regions, which applies another ensemble model that consists of four U-Net-like models and one Deeplabv3+ model. We validated our method by participating in the 2019 SIIM-ACR pneumothorax segmentation challenge. Our method produced a classification AUC of 0.9795 and a Dice score of 0.8883, which secured the 2nd place among 1475 teams. Fine-tuning the models using all available data led to more accurate results that surpassed all other competing methods. The code is made publicly available online at https://github.com/yelanlan/Pneumothorax-Segmentation-2nd-place-solution. Validation on extra polyp and lung segmentation data further proved the general applicability of the proposed method.

A three-dimensional reconstruction algorithm based on line laser rotation scanning is proposed. The rotating platform vision measurement system is designed. The system calibration method consisting of laser, camera and turntable is studied. The axis-eye calibration algorithm is introduced to register the point cloud in the same coordinate. In the system, the camera driven by the turntable is rotated to scan the target object for three-dimensional measurement. The method can obtain the point cloud information of the object by linear laser rotation scanning, and further recover the geometric shape of the three-dimensional visible surface of the object, which not only meets the requirements of the three-dimensional reconstruction target, but also verifies the feasibility and effectiveness of the system.