Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks

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 s...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE International Conference on Computer Vision pp. 4852 - 4861
Main Authors: Fare Garnot, Vivien Sainte, Landrieu, Loic
Format: Conference Proceeding
Language:English
Published: IEEE 01.10.2021
Subjects:
Computer vision
Economics
Feature extraction
grouping and shape
Image segmentation
Satellites
Segmentation
Semantics
Time series analysis
Vision + other modalities
Vision applications and systems
ISSN:2380-7504
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 spatiotemporal 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.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00483