DeepAutoMapping: low-cost and real-time geospatial map generation method using deep learning and video streams
- PDF / 4,660,449 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 49 Downloads / 193 Views
RESEARCH ARTICLE
DeepAutoMapping: low-cost and real-time geospatial map generation method using deep learning and video streams Jalal Ibrahim Al-Azizi 1 & Helmi Zulhaidi Mohd Shafri 1
&
Shaiful Jahari Bin Hashim 2
&
Shattri B. Mansor 1
Received: 8 January 2020 / Accepted: 24 September 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Field data collection and geospatial map generation are critical aspects in different fields such as road asset management, urban planning, and geospatial applications. However, one of the primary impediments to data collection is the availability of spatial and attribute data. This issue is aggravated by the high cost of conventional data collection and data processing methods and by the lack of geospatial data collection policies. This study proposes an inexpensive approach that enables real-time field data observation and geospatial data generation from video streams connected to a laptop and positioning sensors using deep learning technology. This proposed method was evaluated via an application called “DeepAutoMapping”, which was built on top of Python, then underwent through two different evaluation scenarios. The results demonstrated that the proposed approach is quick, easy to use and that it provides a high detection accuracy and an acceptable positioning accuracy in the outdoor environment. The proposed solution may also be considered as a pipeline for efficient and economical method of geospatial data collection and auto-map generation in the future. Keywords Computer vision for automation . Deep learning neural networks . Geographic information system (GIS) . Geospatial data . Mapping and localization . Surveying methods
Introduction Geospatial data or spatial data is information that has a geographical aspect and is available in different formats depending on its source and type. Typically, it can be classified as either a raster or a vector format. The vector form uses points,
* Helmi Zulhaidi Mohd Shafri [email protected] Jalal Ibrahim Al-Azizi [email protected]; https://orcid.org/0000-0002-9424-1213 Shaiful Jahari Bin Hashim [email protected] Shattri B. Mansor [email protected] 1
Department of Civil Engineering and Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, Universiti Putra Malaysia (UPM), 43400 Serdang, Malaysia
2
Department of Computer and Communication Systems Engineering, Faculty of Engineering, University Putra Malaysia (UPM), 43400 Serdang, Malaysia
lines, and polygons to represent spatial features such as trees, roads, and parcels. The raster form uses cells (computers often use dots or pixels) to represent the spatial features. Aerial photos and satellite images are examples of raster data. Geospatial data plays a key role in several important applications, such as navigation, planning, research, and decisionmaking, and hence, field data observations and mapping are fundamental to collecting and analyzing all geospatial data. Therefore, considerable research efforts have been expended
Data Loading...
