SPS: Accurate and Real-Time Semantic Positioning System Based on Low-Cost DEM Maps.

This paper presents a Semantic Positioning System (SPS) to enhance the accuracy of mobile device geo-localization in outdoor urban environments. Although the traditional Global Positioning System (GPS) can offer a rough localization, it lacks the necessary accuracy for applications such as Augmented Reality (AR). Our SPS integrates Geographic Information System (GIS) data, GPS signals, and visual image information to estimate the 6 Degree-of-Freedom (DoF) pose through cross-view semantic matching. This approach has excellent scalability to support GIS context with Levels of Detail (LOD). The map data representation is Digital Elevation Model (DEM), a cost-effective aerial map that allows for fast deployment for large-scale areas. However, the DEM lacks geometric and texture details, making it challenging for traditional visual feature extraction to establish pixel/voxel level cross-view correspondences. To address this, we sample observation pixels from the query ground-view image using predicted semantic labels. We then propose an iterative homography estimation method with semantic correspondences. To improve the efficiency of the overall system, we further employ a heuristic search to speedup the matching process. The proposed method is robust, real-time, and automatic. Quantitative experiments on the challenging Bund dataset show that we achieve a positioning accuracy of 73.24%, surpassing the baseline skyline-based method by 20%. Compared with the state-of-the-art semantic-based approach on the Kitti dataset, we improve the positioning accuracy by an average of 5%.

Occurrence and decay of SARS-CoV-2 in community sewage drainage systems.

The rapid spread of the coronavirus disease (COVID-19) pandemic in over 200 countries poses a substantial threat to human health. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes COVID-19, can be discharged with feces into the drainage system. However, a comprehensive understanding of the occurrence, presence, and potential transmission of SARS-CoV-2 in sewers, especially in community sewers, is still lacking. This study investigated the virus occurrence by viral nucleic acid testing in vent stacks, septic tanks, and the main sewer outlets of community where confirmed patients had lived during the outbreak of the epidemic in Wuhan, China. The results indicated that the risk of long-term emission of SARS-CoV-2 to the environment via vent stacks of buildings was low after confirmed patients were hospitalized. SARS-CoV-2 were mainly detected in the liquid phase, as opposed to being detected in aerosols, and its RNA in the sewage of septic tanks could be detected for only four days after confirmed patients were hospitalized. The surveillance of SARS-CoV-2 in sewage could be a sensitive indicator for the possible presence of asymptomatic patients in the community, though the viral concentration could be diluted more than 10 times, depending on the sampling site, as indicated by the Escherichia coli (E. coli) test. The comprehensive investigation of the community sewage drainage system is helpful to understand the occurrence characteristics of SARS-CoV-2 in sewage after excretion with feces and the feasibility of sewage surveillance for COVID-19 pandemic monitoring.

Temporally Coherent Video Harmonization Using Adversarial Networks.

Compositing is one of the most important editing operations for images and videos. The process of improving the realism of composite results is often called harmonization. Previous approaches for harmonization mainly focus on images. In this paper, we take one step further to attack the problem of video harmonization. Specifically, we train a convolutional neural network in an adversarial way, exploiting a pixel-wise disharmony discriminator to achieve more realistic harmonized results and introducing a temporal loss to increase temporal consistency between consecutive harmonized frames. Thanks to the pixel-wise disharmony discriminator, we are also able to relieve the need of input foreground masks. Since existing video datasets which have ground-truth foreground masks and optical flows are not sufficiently large, we propose a simple yet efficient method to build up a synthetic dataset supporting supervised training of the proposed adversarial network. The experiments show that training on our synthetic dataset generalizes well to the real-world composite dataset. In addition, our method successfully incorporates temporal consistency during training and achieves more harmonious visual results than previous methods.

Semantic Labeling and Instance Segmentation of 3D Point Clouds Using Patch Context Analysis and Multiscale Processing.

We present a novel algorithm for semantic segmentation and labeling of 3D point clouds of indoor scenes, where objects in point clouds can have significant variations and complex configurations. Effective segmentation methods decomposing point clouds into semantically meaningful pieces are highly desirable for object recognition, scene understanding, scene modeling, etc. However, existing segmentation methods based on low-level geometry tend to either under-segment or over-segment point clouds. Our method takes a fundamentally different approach, where semantic segmentation is achieved along with labeling. To cope with substantial shape variation for objects in the same category, we first segment point clouds into surface patches and use unsupervised clustering to group patches in the training set into clusters, providing an intermediate representation for effectively learning patch relationships. During testing, we propose a novel patch segmentation and classification framework with multiscale processing, where the local segmentation level is automatically determined by exploiting the learned cluster based contextual information. Our method thus produces robust patch segmentation and semantic labeling results, avoiding parameter sensitivity. We further learn object-cluster relationships from the training set, and produce semantically meaningful object level segmentation. Our method outperforms state-of-the-art methods on several representative point cloud datasets, including S3DIS, SceneNN, Cornell RGB-D and ETH.

[Innovative ET cover system and its hydrologic evaluation].

The evapotranspiration (ET) cover system,as an alternative cover system of landfill, has been used in many remediation projects since 2003. It is an inexpensive, practical,and easily maintained biological system, but is mainly favorable in arid and semiarid sites due to limited water-holding capacity of the single loam layer and limited transpiration of grass. To improve the effectiveness of percolation control, an innovative scheme of ET was suggested in this paper: (1) a clay liner was added under the single loam layer to increase the water-holding capacity; (2) combined vegetation consisting of shrub and grass was used to replace the grass cover. Hydrologic evaluation of conventional cover,ET cover and the innovative ET cover under the same condition was performed using the computer program HELP, which showed the performance of the innovative ET cover is obviously superior to that of ET cover and conventional cover.