Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
This addresses pixel-precise segmentation for Earth observation, which has economic and environmental implications, but is incremental as it extends existing methods to temporal data.
The authors tackled panoptic segmentation of agricultural parcels from satellite image time series by introducing the first end-to-end, single-stage method with a temporal self-attention encoder, achieving state-of-the-art results on the new PASTIS dataset.
Unprecedented access to multi-temporal satellite imagery has opened new perspectives for a variety of Earth observation tasks. Among them, pixel-precise panoptic segmentation of agricultural parcels has major economic and environmental implications. While researchers have explored this problem for single images, we argue that the complex temporal patterns of crop phenology are better addressed with temporal sequences of images. In this paper, we present the first end-to-end, single-stage method for panoptic segmentation of Satellite Image Time Series (SITS). This module can be combined with our novel image sequence encoding network which relies on temporal self-attention to extract rich and adaptive multi-scale spatio-temporal features. We also introduce PASTIS, the first open-access SITS dataset with panoptic annotations. We demonstrate the superiority of our encoder for semantic segmentation against multiple competing architectures, and set up the first state-of-the-art of panoptic segmentation of SITS. Our implementation and PASTIS are publicly available.