The ultimate goal of this indoor mapping research is to automatically reconstruct a floorplan simply by walking through a house with a smartphone in a pocket. This paper tackles this problem by proposing FloorNet, a novel deep neural architecture. The challenge lies in the processing of RGBD streams spanning a large 3D space. FloorNet effectively processes the data through three neural network branches: 1) PointNet with 3D points, exploiting the 3D information; 2) CNN with a 2D point density image in a top-down view, enhancing the local spatial reasoning; and 3) CNN with RGB images, utilizing the full image information. FloorNet exchanges intermediate features across the branches to exploit the best of all the architectures. We have created a benchmark for floorplan reconstruction by acquiring RGBD video streams for 155 residential houses or apartments with Google Tango phones and annotating complete floorplan information. Our qualitative and quantitative evaluations demonstrate that the fusion of three branches effectively improves the reconstruction quality. We hope that the paper together with the benchmark will be an important step towards solving a challenging vector-graphics reconstruction problem. Code and data are available at https://github.com/art-programmer/FloorNet.

Figure 1. The proposed system, dubbed Floor-SP, takes aligned panorama RGBD scans as input, finds room segments, solves an optimization problem to reconstruct a floorplan graph as multiple polygonal loops (one for each room), and merges them into a 2D graph via simple post-processing heuristics. The optimization is the technical contribution of the paper, which employs the room-wise coordinate descent strategy and sequentially solves shortest path problems to optimize the room structure. AbstractThis paper proposes a new approach for automated floorplan reconstruction from RGBD scans, a major milestone in indoor mapping research. The approach, dubbed Floor-SP, formulates a novel optimization problem, where room-wise coordinate descent sequentially solves shortest path problems to optimize the floorplan graph structure. The objective function consists of data terms guided by deep neural networks, consistency terms encouraging adjacent rooms to share corners and walls, and the model complexity term. The approach does not require corner/edge primitive extraction unlike most other methods. We have evaluated our system on production-quality RGBD scans of 527 apartments or houses, including many units with non-Manhattan structures. Qualitative and quantitative evaluations demonstrate a significant performance boost over the current state-of-the-art. Please refer to our project website

An expedient transition to lead-free electronics has become necessary for most electronics industry sectors, considering the European directives 1 other possible legislative requirements, and market forces [1], [2]. In fact, the consequences of not meeting the European July 2006 deadline for transition to lead-free electronics may translate into global market losses.Considering that lead-based electronics have been in use for over 40 years, the adoption of lead-free technology represents a dramatic change. The industry is being asked to adopt different electronic soldering materials [3], component termination metallurgies, and printed circuit board finishes. This challenge is accompanied by the need to requalify component-board assembly and rework processes, as well as implement test, inspection, and documentation procedures. In addition, lead-free technology is associated with increased materials, design, and manufacturing costs. 2 The use of lead-free materials and processes has also prompted new reliability concerns [1], as a result of different alloy metallurgies and higher assembly process temperatures relative to tin-lead soldering.This paper provides guidance to efficiently implement the lead-free transition process that accounts for the company's market share, associated exemptions, technological feasibility, product reliability requirements, and cost. Lead-free compliance, part and supplier selection, manufacturing, and education and training are addressed. The guidance is presented in the form of answers to key questions.

We analyze the ROCSAT-1 IPEI data collected between March and June 1999 to study the statistical features of the ion vertical drifts at equa torial and tropical latitudes. The dependencies of ion vertical drifts on lo cal time, longitude and georn�gnetic field configuration, as well as geomag netic activity are examined. The variations of the equatorial vertical drifts near the dawn and dusk terminators are of particular interest. From this preliminary study, we have shown that the overall local-time characteris tics of the quiet-time equatorial vertical drift patterns derived from IPEI are in good agreement with those observed by other satellites and ground based instruments. More importantly, several new results due to the unique 35° orbital inclination of ROCSAT-1 and the 100% duty-cycle operation of IPEI are found. These include: (a) enhanced upward ion drifts to a critical level of 30-60 mis at post-sunset hours strongly correlate with the occur rence of rising bubbles in the pre-midnight local time sector; (b) large(> 300 m/s) downward ion drifts are most often found near sunrise and at longitudes where the geomagnetic field has greatest variations; (c) the sta tistical drift patterns strongly depend on the hemispheres at the equatorial anomaly latitudes. This north-south asymmetry may result from seasonal effects and/or from differences in geomagnetic field configuration.

No abstract