1. Mobile Mapping Data

Detekt works with georeferenced images, point clouds and GIS data with a wide variety of localization features.

Panoramic 360° image
Panoramic 360°
Object detection with Artificial Intelligence in dashboard camera or mobile phone images
Dashcam & Phone
Point clouds
Point Cloud
Aerial image
Aerial & Satellite

2. AI Object Detection

The pipeline processes the mobile mapping data through a 3-stage instance segmentation process. The example below demonstrates this step for road signs detection and classification.

Input RGB image for detection of objects in mobile mapping image data with Artificial Intelligence
Input RGB Image
AI Traffic Sign Object Detection
1) Binary Segmentation
AI Binary Segmentation of Traffic Signs
2) Instance Identification
AI Instance Identification of Traffic Signs
3) Instance Classification

3. Localization

The processed detection results (points and polygons) are transformed into world coordinates using 3D information from lidar data or a depth map. As a result, we receive world-space projected points and polygons to determine the exact position of a detected object or surface.

Localization of objects in mobile mapping image data with Artificial Intelligence

4. Detection Fusion

Objects are detected within multiple images and at different times. All individual detections are then fused to one unified detection which increases robustness and accuracy due to multiple "votes" for the same object.

Depending on the characteristics of each object, we either apply point fusion, surface fusion or volume fusion to achieve the most accurate results.

Detection fusion of objects in mobile mapping image data with Artificial Intelligence

5. Results

Detections and location data are individually integrated into internal processes & workflows.

Detekt Viewer

Viewer

The viewer is one of the core elements of Detekt and lets you navigate through your available image/point cloud data to visually understand the results of the AI model detections. Detection classes can be easily changed and annotations can be manually added for for model improvements via re-training.

Visualization of detections with AI in map view

Map

The map is part of the viewer and offers a comprehensive understanding of all detections within your city or municipality. Objects like traffic signs or single road damages can be displayed as icons, road condition is shown as a heatmap.

AI Asset Management

Matching with Inventory

Comparing the detections and their exact location with existing asset databases is essential to improve data accuracy of any managed asset within a city.

Comparison of detected objects with Artificial Intelligence

Comparison over Time

Where mobile mapping data is available from at least two separate campaigns, any detected object can be assigned a unique identifier to compare its condition, location and proportions over a given timespan.

REST API for object detection with Artificial Intelligence

REST API

The Detekt API lets you easily connect any application to use the gathered information for your own needs.

Export of detections with AI in GIS file formats

Export as Shapefile

Detection results can be exported as shapefiles (points, lines or polygons) for further use in any GIS software.