Object Detection

Pixel Classification

Object Classification

Instance Segmentation

Models:

- Single Shot Detector

- Retina Net

- Faster RCNN

Applications:

- Detect trees, cars, airplanes, swimming pool, well pads.

- Detect encroaching structures.

- Moving objects like road cracks/catfish on video

- Road signs, and other assets in oriented imagery

- Detecting and counting vehicles.

- Shipwrecks in Bathymetric data.

- Fire hydrants in Oriented imagery.

Models:

- UNet Classifier

- PSPNet Classifier

- Deep Lab

- Point Rend support for better accuracy

Applications:

- Land Cover Classification.

- Pervious/Impervious Mapping.

- Building Footprint Extraction.

- Cloud detection.

- Road detection.

- Water meters from oblique images.

Model:

- Feature Classifier.

Applications:

- Damaged building classification.

- Clean pools.

- Broken/flashed insulators.

- Identifying plant species.

Models:

- Mask RCNN

Applications:

- Building footprint extraction.

- 3D roof reconstruction.

- Sinkholes

Scanned Map Digitization

Image Translation

Point Cloud Classification

Image Captioning

Class:

- Scanned Map Digitizatizer

Applications:

- Digitizing scanned maps.

- Geo referencing Scanned maps.

Models:

- Pix2Pix

- Cycle GAN

- Super Resolution

Applications:

- SAR to Optical imagery.

- Imagery to Map generation.

- Annotate Imagery.

- Increase image resolution.

Models:

- Point CNN

Applications:

- Classifying point cloud data (building/ground, etc)

- Power line and utility poles extraction.

Models:

- Image Captioner

Applications:

- Annotating Images.

- Accessibility for Images.

Road Extraction

Change Detection

Edge Detection

Models:

- Multi Task Road Extractor

Applications:

- Extract Road Networks

- Routing

Models:

- Change Detector

(based on STANet)

Applications:

- Identify new building.

- Identify new construction.

Models:

- BDCN Edge Detector

- HED Edge Detector

Applications:

- Residential parcel extraction.

- Agricultural farm boundaries.