Geospatial Annotation Tool

Satellite imagery is essential to train Machine Learning models or computer vision models that aim to analyze our world: fire and natural disasters prevention, deforestation monitoring, traffic and weather analysis. By analyzing and labeling geospatial images, you can build any AI app based on aerial imagery by creating a powerful training dataset.

With Kili Technology, our image annotation tools support GeoTiff files, meaning you can do all labeling tasks on aerial imagery: object detection, image segmentation, box annotations, track objects, image classification. And you can do them with a selection of tools: bounding boxes, polygons, semantic & interactive segmentation, and much more.

What are the labeling formats supported by Kili Technology? Kili Technology, as a training data labeling platform, supports labeling tasks on all asset types. Computer vision tasks: image classification, video classification, bounding box, polygon, point, line, geospatial data annotation, object tracking, object detection, etc. Natural language processing with text annotation (rich text, and conversation). Document annotation (documents, pdfs, OCR). On text and documents, you can do classification, named entity recognition, and objects relations to name a few.

Kili Technology as an image annotation tool is fully secure with a SOC2, ISO 27001 & HIPAA certification. We put a high priority on privacy preserving images, as well as any kind of protection against bias (perceived gender presentation, cultural and racial representation, etc). We also provide different deployment options to fit the data security needs of our customers. Note that data management options may vary depending on your hosting mode (Cloud or On-premise).

Kili Technology's API is accessible to our users. Therefore, you can connect your machine-learning model to generate pre-annotations. We also support segmentation tasks augmented with the Segment Anything Model (SAM) and any other foundation model with prompt engineering or segmentation model based on input prompts. To learn more about prompt engineering, you can check our recent webinars here.

Kili Technology is not an open-source software. However, you can use our free plan to do image annotation and computer vision tasks, use our geospatial tools & segmentation masks, and do everything needed to output multiple valid masks & training data into powerful datasets and in the end, powerful segmentation models. Note that when using our free plan, you may not benefit from all our various tools at 100% of their capacity.

There are a few things that ML engineers should understand when working with geospatial imagery and data labeling. Here is a list of definitions to help you. remote sensing: Remote sensing is the process of detecting and monitoring the physical characteristics of an area by measuring its reflected and emitted radiation at a distance deep learning: Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. cloud optimized geotiffs: A Cloud Optimized GeoTIFF (COG) is a regular GeoTIFF file, aimed at being hosted on a HTTP file server, with an internal organization that enables more efficient workflows on the cloud. geospatial use cases: many machine learning & deep learning use cases leverage aerial imagery & computer vision. The main examples are the analysis of land use, prevention of natural disasters, defense and military surveillance, weather prediction, and many more. These use cases are time consuming to build as they require a cloud or on-prem labeling tool, satellite images to label, a team capable of annotating & analyzing objects on the image to create labels, and more. Machine learning models built with geospatial data and the right annotation tools are extremely powerful.