Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence
This addresses the problem of segmenting moving objects in turbulent conditions for applications like surveillance or remote sensing, but it is incremental as it builds on existing unsupervised and geometric consistency ideas.
The paper tackles moving object segmentation in videos degraded by atmospheric turbulence by proposing an unsupervised detect-then-grow method, achieving good accuracy and robustness across various turbulence strengths on a newly collected real-captured dataset.
Moving object segmentation in the presence of atmospheric turbulence is highly challenging due to turbulence-induced irregular and time-varying distortions. In this paper, we present an unsupervised approach for segmenting moving objects in videos downgraded by atmospheric turbulence. Our key approach is a detect-then-grow scheme: we first identify a small set of moving object pixels with high confidence, then gradually grow a foreground mask from those seeds to segment all moving objects. This method leverages rigid geometric consistency among video frames to disentangle different types of motions, and then uses the Sampson distance to initialize the seedling pixels. After growing per-frame foreground masks, we use spatial grouping loss and temporal consistency loss to further refine the masks in order to ensure their spatio-temporal consistency. Our method is unsupervised and does not require training on labeled data. For validation, we collect and release the first real-captured long-range turbulent video dataset with ground truth masks for moving objects. Results show that our method achieves good accuracy in segmenting moving objects and is robust for long-range videos with various turbulence strengths.