Asian Surveying & Mapping
Breaking News
Indian Small Satellite Launch Vehicle Fails in Maiden Launch Attempt
India’s new Small Satellite Launch Vehicle failed to orbit...
M2 satellite delivers Australia’s first high-res Earth observation images
A UNSW Canberra Space satellite mission, known as M2,...
Japan plans green transition road map for emissions-heavy industries
TOKYO -- Japan will outline steps for a green...
Mappls RealView by MapmyIndia Launched as Google Street View Competitor in India
Mappls RealView was launched by MapmyIndia in India on...
Earth Observation Drones Global Market to Surpass $18.2 Billion by 2032
The "Earth Observation Drones Market - A Global and Regional...
China’s Long March rocket launches 16 satellites
According to the Chinese news agency, Xinhua, 16 new satellites...
Russia Fires Iranian Satellite Into Space, Prompting Spying Concerns
This is the moment Russia launched an Iranian space...
NEA AND SLA SIGN MOU TO SHARE GLOBAL NAVIGATION SATELLITE SYSTEM (GNSS)-DERIVED MOISTURE DATA FOR WEATHER MONITORING APPLICATION
Singapore – The National Environment Agency (NEA) and the Singapore...
UAE to develop SAR satellite constellation for remote sensing
The UAE Space Agency, on Monday announced a new...
China launches new group of remote sensing satellites
XICHANG - China successfully launched a new group of...

October 15th, 2018
SITECO’s NEW Road-SIT Survey v. 7.0 AT INTERGEO 2018

Bologna, Italy – SITECO Infomatica SRL will be attending Intergeo 2018 in Frankfurt, Hall 12.0, Stand 12.OB.073, showcasing the Road-Scanner family of Mobile Mapping Systems and the NEW software release of Road-SIT Survey.

Road-SIT Survey is the mobile mapping data application developed by Siteco, fully compatible with the most widespread mobile mapping systems like the Optech-Lynx, Riegl-VMX, Topcon IPS3 and Leica Pegasus. And of course with the well known Siteco’s Road-Scanner.

This new release has been developed in collaboration with the Bologna University Computer Vision Lab (CVLAB) and includes smart features for the point-cloud classification:

  • Geometric classification which brings big advantages to edge detection and point-cloud editing;
  • Semantic classification that allows a selective view of the point clouds and object detection through a sophisticated 2D and 3D deep-learning algorithm.

The geometric classification consists in computing NORMALS and CURVATURES in the neighbourhood of each point:

  • The Normal is the direction of the tangent plane
  • The Curvature is the degree of non-coplanarity:

Both parameters are of a great help for edge detection and feature extraction.

The user interface has been improved in order to exploit the new features in the best way. In all the views and projections, the point clouds can be displayed in different color ramps based on: Intensity, Elevation, True color,  Normals, Curvature, Semantic Classification.

For the NORMAL the RGB color ramp is: Blue = vertical (direction Z),  Red = horizontal (direction X), Green = horizontal (direction Y)

For the CURVATURE:  (GREEN=LOW=plane surfaces, RED=HIGH=edges , corners, natural elements like leaves and terrain)

The new display options are of great help to the feature extraction activities thanks to an real-time representation of the horizontal and vertical surfaces, allowing an immediate identification of the objects to be mapped (roads, furniture, buildings, signage, etc.) from others that can be considered as noise (vegetation, cars, pedestrians).

The curvature value allows the  immediate location of the edges and makes it easier to extract them.

The Semantic Classification allows the automatic assignment, to every pixel of the camera pictures, of a LABEL  with a class object, out of the 16 recognized classes of the neural network. It is then applied to the point-cloud, divided into 5-cm boxes (voxels).

The new features include also the object detection for Signs, Posts, Poles and Buildings:

  • The application detects clusters of adjacent voxels as single objects (poles, signs, buildings);
  • Each of them is stored as a new object in a database with its position, picture and dimensional features;
  • The detected objects can be edited in the feature extraction environment.

The Technical Director of SITECO, Augusto Burchi, stated: “We are very proud of these innovative features. Thanks to them we are now developing new powerful functions for edge detection, object recognition and for registration of point clouds surveyed during different missions”.