A deep learning approach for rooftop geocoding

  title={A deep learning approach for rooftop geocoding},
  author={Zhengcong Yin and Andong Ma and Daniel W. Goldberg},
  journal={Transactions in GIS},
  pages={495 - 514}
Geocoding has become a routine task for many research investigations to conduct spatial analysis. However, the output quality of geocoding systems is found to impact the conclusions of subsequent studies that employ this workflow. The published development of geocoding systems has been limited to the same set of interpolation methods and reference data sets for quite some time. We introduce a novel geocoding approach utilizing object detection on remotely sensed imagery based on a deep learning… 

A probabilistic framework for improving reverse geocoding output

A probabilistic framework that includes a new workflow that can adapt all existing address models and unitizes distance and topology relations among retrieved reference data for candidate selections, an advanced scoring mechanism that quantifies characteristics of the entire workflow and orders candidates according to their likelihood of being the best candidate, and a novel algorithm that derives statistical surfaces for input GPS uncertainties and propagates such uncertainties into final output lists are proposed.

Address points of landmarks and paratransit services as a credible reference database for geocoding

Address and location challenges are global, yet sub‐Saharan Africa (SSA) is the most poorly referenced geographically due to poor spatial referencing of mobility infrastructure and landmarks, poor

Geocoding user queries

The measurements prove that the path chosen in this thesis is a viable method to create geocoded systems that can handle user queries better than geocoding systems relying on common techniques.

Fast Attention-based Learning-To-Rank Model for Structured Map Search

This work proposes a novel deep neural network LTR architecture, capable of seamlessly handling heterogeneous inputs, similar to GBDT-based methods, and is a low-cost alternative suitable to power ranking in industrial map search engines across a variety of languages and markets.

A Deep Learning based Illegal Parking Detection Platform

A web-based analytic platform is proposed that provides an algorithm to improve the performance of detecting vehicle license plates from videos, based on an existing deep learning approach, and a method to estimate vehicle parking locations.

English Out-of-Vocabulary Lexical Evaluation Task

This is the first attempt to focus on out-of-vocabulary lexical evaluation tasks that does not require any prior knowledge and utilizes unsupervised word embedding methods such as Word2Vec and Word2GM to perform the baseline experiments on the categorical classification task and OOV words attribute prediction tasks.


CoMiner: nationwide behavior-driven unsupervised spatial coordinate mining from uncertain delivery events

A new cost-effective Geocoding framework to automatically infer the geographic coordinates from textual addresses for service providers, based on textual address data, delivery event data, and courier trajectory data is designed.



Improving Geocoding Match Rates with Spatially‐Varying Block Metrics

The technical approach of a geocoding system that includes a nearby matching approach is described along with a method for scoring candidates based on spatially‐varying neighborhoods that indicates this approach is viable for improving match rates while maintaining acceptable levels of spatial accuracy.

Geocoding Quality and Implications for Spatial Analysis

The foundation of geocoded is reviewed and a framework for evaluating geocoding quality is presented and it is suggested that substantial bias may be introduced in spatial analysis that employs the results of Geocoding.

A comparison of address point, parcel and street geocoding techniques

Quality Assessment of Online Street and Rooftop Geocoding Services

The results reveal that both rooftop and street geocoding produce high match rates and high accuracy for residential addresses, however, positional accuracies of agricultural and industrial address types are not very reliable due to the small sample sizes.

A Hybrid Geocoding Methodology for Spatio‐Temporal Data

A methodology for geocoding spatio‐temporal data in ArcGIS that utilizes several additional supporting procedures to enhance spatial accuracy, including the use of supplementary land use information, aerial photographs and local knowledge is presented.

Exploiting online sources to accurately geocode addresses

This work proposes two new methods for geocoding that take into consideration the number of addresses/lots present on the street segment to approximate the location of an address and describes an implementation of these methods using an information mediator to obtain information about actual number of lots and sizes of the lots on the streets from various property tax web sites.

Positional error in automated geocoding of residential addresses

  • M. CayoT. Talbot
  • Environmental Science
    International journal of health geographics
  • 2003
This study evaluated the positional error caused during automated geocoding of residential addresses and how this error varies between population densities, and an alternative method of geocoded using residential property parcel data.


The assignment of geo-referenced coordinates to individual households, known as geocoding, is a fundamental and important task for urban data management. Not surprisingly, geographic information

Modeling the probability distribution of positional errors incurred by residential address geocoding

Mixtures of bivariate t distributions with few components appear to be flexible enough to fit many positional error datasets associated with geocoding, yet parsimonious enough to be feasible for nascent applications of measurement-error methodology to spatial epidemiology.

From Text to Geographic Coordinates: The Current State of Geocoding

This article will survey the field of geocoding through a cross-disciplinary study of theGeocoding literature focusing foremost on the technical aspects of the process, and potential sources of error in the geocoded process will be explored.