No abstract

A reference database of addressing is an important resource for urban applications. The efficiency of an addressing system depends on both data quality and technical architecture. Data must respect a standard model that is flexible to meet different cases in the field. The technical architecture should be service oriented to offer a shared resource for multiple users and applications. This paper is to develop an addressing model for Morocco that extends Davis's and Fonseca's model presented in their work on the certainty of locations produced by an address geocoding system. We discuss the addressing data dictionary and acquisition plan in Morocco, revealing a diversified data management environment, characterized by multiple sources and actors. As a novelty in the field of GIS, we establish our technical architecture around cloud computing, according Service Oriented Application (SOA) standards. Our approach is based on the three pillars of cloud computing which are Software as a Service (SaaS), Platform as a Service (PaaS) and Infrastructure as a service (IaaS).

Addresses are important data for urban applications. About 80% of the information local authorities use have a geographic component that is generally related to addresses. Addressing systems efficiency depend on the quality of addresses locators. There are several methods to collect data. Surveys from the field are essential: GPS and pre-printed maps can be used to achieve this goal. GPS surveys from the field may be a solution, but it remains practical only for limited areas. To insure an accepted accuracy, GPS methods need special considerations that are time and money consuming. For Casablanca’s addressing locators, an alternative approach was adopted to collect 400 000 points. It took two months, 200 operators and 3500 printed maps to cover a study area of1,226 km². This paper is to develop an optimized approach based on automated procedure for reintegrating printed maps in a geographic information system (GIS). It saves georeferencing time from 5min to just seconds per document. It insures, more importantly, an accuracy that is between20 cmto1 mfor scales that are between 1/500 and 1/2500. It ensures maps’ integration, independently of base map and coordinates system by introducing the notion of Georeferencing Code (GC).

The latest advances in Deep Learning based methods and computational capabilities provide new opportunities for vehicle tracking. In this study, YO-LOv2 (You Only Look Once-version 2) is used as an open source Convolutional Neural Network (CNN), to process high-resolution satellite images, in order to generate the spatio-temporal GIS (Geographic Information System) tracks of moving vehicles. At first step, YOLOv2 is trained with a set of images of 1024 × 1024 resolution from the VEDAI database. The model showed satisfactory results, with an accuracy of 91%, and then at second step, is used to process aerial images extracted from aerial video. The output vehicle bounding boxes have been processed and fed into the GIS based LinkTheDots algorithm, allowing vehicles identification and spatio-temporal tracks generation in GIS format.