The Outcome of the 2021 IEEE GRSS Data Fusion Contest—Track MSD: Multitemporal Semantic Change Detection

Abstract

We present here the scientific outcomes of the 2021 Data Fusion Contest (DFC2021) organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. DFC2021 was dedicated to research on geospatial artificial intelligence (AI) for social good with a global objective of modeling the state and changes of artificial and natural environments from multimodal and multitemporal remotely sensed data towards sustainable developments. DFC2021 included two challenge tracks: "Detection of settlements without electricity" and "Multitemporal semantic change detection". This paper mainly focuses on the outcome of the multitemporal semantic change detection track. We describe in this paper the DFC2021 dataset that remains available for further evaluation of corresponding approaches and report the results of the bestperforming methods during the contest.

Report on the 2023 IEEE GRSS Data Fusion Contest: Large-Scale Fine-Grained Building Classification for Semantic Urban Reconstruction [Technical Committees]

“…The ultimate goal of the competition is to develop accurate building extraction and classification models using multimodal data, including optical and synthetic aperture radar (SAR) images. This contest was designed as a benchmarking competition following previous editions [12], [13], [14], [15], [16], [17], [18]. DFC23 featured the following two tracks running in parallel: 1) " sequence of points that delineates the building's contours) or run-length encoding, one fine-grained category with confidence for each instance, and one optional bounding box.…”

SinoLC-1: the first 1 m resolution national-scale land-cover map of China created with a deep learning framework and open-access data

“…Over the past 40 years, numerous satellite missions have been launched to improve the knowledge of Earth's resources and monitor natural phenomena. With the continuous updating of airborne and spaceborne platforms, the spatial resolution of the available remote-sensing images has undergone rapid increments of change (Tong et al, 2020;Li et al, 2022b). Moreover, studies on land-cover mapping methods have achieved great progress.…”

Simultaneous Update of High-Resolution Land-Cover Mapping Attempt: Wuhan and the Surrounding Satellite Cities Cartography Using L2HNet

“…This problem is common in deep learning based HR land-cover mapping. In Li et al's study [17], [18], change detection is a geospatial application for social good, and its development is then limited by the slow development of remote sensing image tagging technology and outdated classification labels. They proposed a change cross-detection approach for Multitemporal Semantic Change Detection with weak, noisy, and LR labels based on label improvements and multi-model fusion.…”

“…As society's demand for HR land-cover mapping grows, the low to high task has advanced [17], [18]. In Dong et al's study, they proposed a solution that could produce 3meter resolution land-cover maps across the country without involving human effort, a major breakthrough in the lowto-high task [33].…”