iTwin Capture detectors download page


Detectors

Here is a list of detectors already trained. They can be executed in ContextCapture, Orbit Feature Extraction Pro, Orbit 3DM Manage and Extract and Reality Data Analysis Service to run Annotation jobs.
Each detector was trained:

Meaning, while running on your dataset, each detector type can only be used for the same specific type of job.

The quality of the detection will depend on the similarity between your dataset and the training dataset’s description.

If using ContextCapture, we recommend you to update your version to the latest one.

In case no detector fits your purpose, you are welcome to submit a help ticket from your personal portal describing your expectations.

Name

Detector Type

Description

Illustration

Links

Cracks

Photo Segmentation

Detect cracks in concrete infrastructure to enable defect inspection workflows.

Dataset used: drone + handheld

Resolution: around 1cm/pix

Geographic area: multiple

Face & License plates

Photo Object Detection

Detect faces and license plates to enable anonymization workflows.

Dataset Used: mobile mapping device - Panoramas

Resolution: N/A

Geographic area: Western Europe

Traffic signs

Photo Object Detection

Detect traffic signs to enable asset inventory workflows
Dataset used: Terrestrial imagery captured by mobile mapping devices
Geographic area: Multiple

Cracks Ortho

Orthophoto Segmentation

Detect cracks in concrete infrastructure to enable defect inspection workflows.

Dataset used: drone + handheld

Resolution: around 1cm/pix

Geographic area: multiple

Manholes

Photo Object Detection

Detect manholes to support mapping & surveying workflows
- Dataset used : Drone images in urban environment
- Resolution : Around 2cm/pix
- Geographic Area : Eastern Europe

Terrain

Pointcloud Segmentation

Extract ground from your reality-mesh
Dataset used: Drone
Resolution: Under 70cm
Geographic area: multiple

RoofsA

Orthophoto Segmentation

Dataset used: vertical/aerial mapping camera

Resolution: around 30cm/pix

Geographic area: multiple

RoofsB

Orthophoto Segmentation

Dataset used: vertical/aerial mapping camera

Resolution: around 7.5cm/pix

Geographic area: Christchurch - New Zealand

Datasets

Here is a list of sample datasets. They can be used to test the detectors above and the use of services like RDAS.
To use one of the examples, you must replace the absolute path inside the "References" tag of the example's ContextScene.xml file with the absolute path leading to where the images were saved.

Name

Illustration

Link

Orthophoto Segmentation / Roofs

iTwin Capture Modeler
Reality Analysis Service

Photo Object / Face and License Plates / Traffic signs

iTwin Capture Modeler
Reality Analysis Service

iTwin Capture Manage and Extract

Photo Segmentation / Cracks

iTwin Capture Modeler
Reality Analysis Service

iTwin Capture Manage and Extract

Photo Segmentation / Cracks3d

iTwin Capture Modeler
Reality Analysis Service

Pointcloud Segmentation / Trees

iTwin Capture Modeler
Reality Analysis Service

iTwin Capture Manage and Extract

Detectors For Testing

Below is an extension of primary detectors’ list.

These detectors are meant to support testing of all job types.

Their training pattern is very specific and a high accuracy on personal data cannot be expected.

Name

Detector Type

Description

Illustration

Links

Coco

Photo Object Detection

Detect 90 classes for everyday life objects: cars, books, chairs, etc…
Dataset used: Handheld camera
Resolution: Not available
Geographic area: multiple

Pascal

Photo Segmentation

Detect 20 classes for everyday life elements: cars, motorbikes, persons, etc…
Dataset used: Handheld camera
Resolution: Not available
Geographic area: multiple

CityA

Pointcloud Segmentation

Detect 7 classes in city environment: Roofs, vegetation, poles, power lines, ground, cars, fences
Dataset used: Aerial Lidar
Resolution: 3cm
Geographic area: United States

CityB

Pointcloud Segmentation

Detect 5 classes in city environment: Roofs, vegetation, bridges, power lines, ground
Dataset used: RGB - Aerial Lidar
Resolution: 20cm
Geographic area: Western Europe

Ghost

Pointcloud Segmentation

Detect moving elements of pointcloud capture to clan-up mapping data
- Dataset used : mobile mapping pointcloud
- Resolution : 5cm
- Geographic Area : Western Europe

Light poles

Pointcloud Segmentation

Detect lightpoles to support mapping and asset-inventory workflows
- Dataset used : mobile mapping pointcloud
- Resolution : 5cm
- Geographic Area : Western Europe

Rail

Pointcloud Segmentation

Detect 13 classes for usual rail assets: signals, sensors, rails, etc…
Dataset used: RGB - Mobile mapping system
Resolution: 3cm
Geographic area: Western Europe

Trees

Pointcloud Segmentation

Detect trees for mapping or clash prediction workflows
- Dataset used : Mobile mapping pointcloud
- Resolution : 4cm
- Geographic Area : South America