Automatic Image Stitching, Segmentation, Classification, Mapping, and Analysis

1. GeoAI-driven Automatic Land Cover and Land User Classification

Upload an Image to SGA’s Cloud Platform for Automatic Land Cover and Land Use Segmentation and Classification.

Uploaded Sample Image

AI Generated Results

2. Automated Image Stitching, Mapping, and Analysis

Upload drone images to SGA’s cloud platform for stitching, 2D and 3D mapping, and analysis.

3. SGA Researchers Publish Groundbreaking Study on Quantum Machine Learning for Image Classification in the Journal of Remote Sensing

Super GeoAI Technology Inc. (SGA) is excited to announce that our researchers, Dr. Riyaaz Uddien Shaik and Dr. Weiping Zeng, have published a groundbreaking paper titled “Quantum-Based Pseudo-Labelling for Hyperspectral Imagery: A Simple and Efficient Semi-Supervised Learning Method for Machine Learning Classifiers” in the highly esteemed Journal of Remote Sensing. This publication underscores our commitment to advancing the field of geospatial artificial intelligence (GeoAI) and contributing valuable insights to the academic community.

For more information, please read the full paper on the MDPI website:

Super GeoAI Technology Inc. Paper in the Journal of Remote Sensing

4. SGA Researchers Publish Paper on Hyperspectral Imagery for Remote Sensing Applications in the Journal of Remote Sensing

We are thrilled to announce that SGA researchers, Dr. Weiping Zeng and Dr. Riyaaz Uddien Shaik, have successfully published two papers in the Journal of Remote Sensing within just four months. This achievement underscores our team’s expertise in remote sensing, geospatial AI, agriculture, and forestry.

Our latest study highlights the pivotal role of hyperspectral imagery in precision agriculture, forestry, environmental monitoring, and geological applications. By conducting a comprehensive SWOT analysis, we explored the immense potential of hyperspectral imagery across various remote sensing applications. The analysis revealed that the higher reflectance spectra of hyperspectral imagery, with its extensive coverage, have a superior ability to extract vegetation biophysical parameters compared to other methods.

We are confident that our findings will make a significant contribution to the field of precision agriculture and beyond.