MLMT-CNN for Object Detection and Segmentation in Multi-layer and Multi-spectral Images

TL;DR

This paper introduces a multi-task deep learning framework called MLMT-CNN for precise 3D localization of solar Active Regions in multi-layer and multi-spectral images, addressing the unique challenge of different modalities capturing different object locations.

Contribution

The paper proposes a novel multi-layer, multi-task deep learning approach with a recursive weak label training strategy for improved solar AR detection and segmentation.

Findings

Achieved 0.72 IoU in segmentation and 0.90 F1 in detection on artificial data.

Outperformed baseline methods in both detection and segmentation metrics.

Validated results with expert assessment on real solar AR images.

Abstract

Precisely localising solar Active Regions (AR) from multi-spectral images is a challenging but important task in understanding solar activity and its influence on space weather. A main challenge comes from each modality capturing a different location of the 3D objects, as opposed to typical multi-spectral imaging scenarios where all image bands observe the same scene. Thus, we refer to this special multi-spectral scenario as multi-layer. We present a multi-task deep learning framework that exploits the dependencies between image bands to produce 3D AR localisation (segmentation and detection) where different image bands (and physical locations) have their own set of results. Furthermore, to address the difficulty of producing dense AR annotations for training supervised machine learning (ML) algorithms, we adapt a training strategy based on weak labels (i.e. bounding boxes) in a recursive manner. We compare our detection and segmentation stages against baseline approaches for solar image analysis (multi-channel coronal hole detection, SPOCA for ARs) and state-of-the-art deep learning methods (Faster RCNN, U-Net). Additionally, both detection a nd segmentation stages are quantitatively validated on artificially created data of similar spatial configurations made from annotated multi-modal magnetic resonance images. Our framework achieves an average of 0.72 IoU (segmentation) and 0.90 F1 score (detection) across all modalities, comparing to the best performing baseline methods with scores of 0.53 and 0.58, respectively, on the artificial dataset, and 0.84 F1 score in the AR detection task comparing to baseline of 0.82 F1 score. Our segmentation results are qualitatively validated by an expert on real ARs.