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%.

Percutaneous spinal endoscopy with unilateral interlaminar approach to perform bilateral decompression for central lumbar spinal stenosis: radiographic and clinical assessment.

BACKGROUND: Recently, a percutaneous spinal endoscopy unilateral posterior interlaminar approach to perform bilateral decompression has been proposed for use in treatment of lumbar spinal stenosis, As a development and supplement to traditional surgery, its advantages regarding therapeutic effects and prognosis, such as minor soft tissue damage, little intraoperative blood loss, and a quick return to daily life. However, there are few analyses of this surgery with a follow-up of more than 1 year,we conducted this study in order to quantitatively investigate radiographic and clinical efficacies of this surgery for central lumbar spinal stenosis. MATERIALS AND METHODS: Forty-six patients with central lumbar spinal stenosis were enrolled from January 2017 to July 2018. The visual analog scale (VAS) for back pain and leg pain, Oswestry disability index (ODI), modified MacNab criteria were used to evaluate clinical efficiency at preoperative and postoperative time points. The intervertebral height index (IHI), cross-sectional area of the spinal canal (CSAC), calibrated disc signal (CDS) and spinal stability were examined to assess radiographic decompression efficiency via magnetic resonance imaging and X-ray at preoperative and postoperative time points. RESULTS: The VAS score for lower back pain and leg pain improved from 7.50 ± 0.78 to 1.70 ± 0.66 and from 7.30 ± 0.79 to 1.74 ± 0.68, respectively, and the ODI improved from 72.35 ± 8.15 to 16.15 ± 4.51. In terms of modified MacNab criteria, 91.3% of the patients achieved good or excellent outcomes. Furthermore, significant changes after surgery were observed for the percentage of CSAC, increasing from 125.3 ± 53.9 to 201.4 ± 78 mm2; however, no significant differences were observed for the remaining measurement indicators. CONCLUSIONS: The clinical and radiographic efficacies of this surgery for central lumbar spinal stenosis were good in short-term follow-up, and this surgery did not cause meaningful changes in IHI, CDS, and spine stability in short-term follow-up. The effect of long-term follow-up needs further investigation.

Multi-UAV Reconnaissance Task Assignment for Heterogeneous Targets Based on Modified Symbiotic Organisms Search Algorithm.

This paper considers a reconnaissance task assignment problem for multiple unmanned aerial vehicles (UAVs) with different sensor capacities. A modified Multi-Objective Symbiotic Organisms Search algorithm (MOSOS) is adopted to optimize UAVs' task sequence. A time-window based task model is built for heterogeneous targets. Then, the basic task assignment problem is formulated as a Multiple Time-Window based Dubins Travelling Salesmen Problem (MTWDTSP). Double-chain encoding rules and several criteria are established for the task assignment problem under logical and physical constraints. Pareto dominance determination and global adaptive scaling factors is introduced to improve the performance of original MOSOS. Numerical simulation and Monte-Carlo simulation results for the task assignment problem are also presented in this paper, whereas comparisons with non-dominated sorting genetic algorithm (NSGA-II) and original MOSOS are made to verify the superiority of the proposed method. The simulation results demonstrate that modified SOS outperforms the original MOSOS and NSGA-II in terms of optimality and efficiency of the assignment results in MTWDTSP.