During our first test flight, we collected a set of hyperspectral data. The lighting conditions were not optimal at the time of collection. Nevertheless, the data achieved excellent resolution and ortho-rectification. Future data collection efforts will focus on optimizing lighting conditions to further refine the quality of the imagery captured.
We've applied Principal Component Analysis (PCA) to resample our dataset, seeking to distill the information into a more manageable form. The resulting PCA output offers a rescaled view of the data, identifying key variances and patterns within the spectral information. Recognizing the importance of data quality, we are planning to collect additional data with an emphasis on improving lighting conditions. This approach aims to enhance the reliability of our subsequent analyses. As we proceed, we will continue to share updates on our progress and the data we gather.
Now that we have some data to test with we're testing a new data format that combines LiDAR and hyperspectral imaging, which we're calling "HyperLAS." This format integrates the dimensional detail of LiDAR with the spectral range of hyperspectral imaging into a single dataset. By appending spectral band data as additional fields in a traditional LAS format, we aim to explore improved methods for environmental analysis, specifically in segmentation and species identification.
Our work is in the experimental phase, and we look forward to sharing our findings as we assess the capabilities of this integrated approach.
Comments