Explaining raw data complexity to improve satellite onboard processing
This addresses the challenge of deploying AI models directly on satellites for remote sensing, though it is incremental as it focuses on adapting existing architectures for raw data.
The study investigated the impact of using raw sensor data versus preprocessed L1 imagery on deep learning models for object detection and classification in satellite onboard processing, finding that models trained on raw data struggle with object boundary identification at high confidence levels.
With increasing processing power, deploying AI models for remote sensing directly onboard satellites is becoming feasible. However, new constraints arise, mainly when using raw, unprocessed sensor data instead of preprocessed ground-based products. While current solutions primarily rely on preprocessed sensor images, few approaches directly leverage raw data. This study investigates the effects of utilising raw data on deep learning models for object detection and classification tasks. We introduce a simulation workflow to generate raw-like products from high-resolution L1 imagery, enabling systemic evaluation. Two object detection models (YOLOv11n and YOLOX-S) are trained on both raw and L1 datasets, and their performance is compared using standard detection metrics and explainability tools. Results indicate that while both models perform similarly at low to medium confidence thresholds, the model trained on raw data struggles with object boundary identification at high confidence levels. It suggests that adapting AI architectures with improved contouring methods can enhance object detection on raw images, improving onboard AI for remote sensing.