In recent years, change detection (CD) using deep learning (DL) algorithms has been a very active research topic in the field of remote sensing (RS). Nevertheless, the CD algorithms developed so far are mainly focused on generating two-dimensional (2D) change maps where the planimetric extent of the areas affected by changes is identified without providing any information on the corresponding elevation variations. The aim of this work is, hence, to establish the basis for the development of DL algorithms able to automatically generate an elevation (3D) CD map along with a standard 2D CD map, using only bitemporal optical images as input, and thus without the need to rely directly on elevation data during the inference phase. Specifically, our work proposes a novel network, capable of solving the 2D and 3D CD tasks simultaneously, and a modified version of the 3DCD dataset, a freely available dataset designed precisely for this twofold task. The proposed architecture consists of a Transformer network based on a semantic tokenizer: the MultiTask Bitemporal Images Transformer (MTBIT). Encouraging results, obtained on the modified version of the 3DCD dataset by comparing the proposed architecture with other networks specifically designed to solve the 2D CD task, are shown. In particular, MTBIT achieves a metric accuracy (represented by the changed root mean squared error) equal to 6.46 m – the best performance among the compared architectures – with a limited number of parameters (13,1 M). The code and the 3DCD dataset are available at https://sites.google.com/uniroma1.it/3dchangedetection/home-page.

Inferring 3D change detection from bitemporal optical images / Marsocci, Valerio; Coletta, Virginia; Ravanelli, Roberta; Scardapane, Simone; Crespi, Mattia. - In: ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING. - ISSN 0924-2716. - 196:(2023), pp. 325-339. [10.1016/j.isprsjprs.2022.12.009]

Inferring 3D change detection from bitemporal optical images

Marsocci Valerio
Primo
;
Coletta Virginia
Secondo
;
Ravanelli Roberta;Scardapane Simone
Penultimo
;
Crespi Mattia
Ultimo
2023

Abstract

In recent years, change detection (CD) using deep learning (DL) algorithms has been a very active research topic in the field of remote sensing (RS). Nevertheless, the CD algorithms developed so far are mainly focused on generating two-dimensional (2D) change maps where the planimetric extent of the areas affected by changes is identified without providing any information on the corresponding elevation variations. The aim of this work is, hence, to establish the basis for the development of DL algorithms able to automatically generate an elevation (3D) CD map along with a standard 2D CD map, using only bitemporal optical images as input, and thus without the need to rely directly on elevation data during the inference phase. Specifically, our work proposes a novel network, capable of solving the 2D and 3D CD tasks simultaneously, and a modified version of the 3DCD dataset, a freely available dataset designed precisely for this twofold task. The proposed architecture consists of a Transformer network based on a semantic tokenizer: the MultiTask Bitemporal Images Transformer (MTBIT). Encouraging results, obtained on the modified version of the 3DCD dataset by comparing the proposed architecture with other networks specifically designed to solve the 2D CD task, are shown. In particular, MTBIT achieves a metric accuracy (represented by the changed root mean squared error) equal to 6.46 m – the best performance among the compared architectures – with a limited number of parameters (13,1 M). The code and the 3DCD dataset are available at https://sites.google.com/uniroma1.it/3dchangedetection/home-page.
2023
3D change detection; remote sensing; deep learning; elevation change detection; dataset
01 Pubblicazione su rivista::01a Articolo in rivista
Inferring 3D change detection from bitemporal optical images / Marsocci, Valerio; Coletta, Virginia; Ravanelli, Roberta; Scardapane, Simone; Crespi, Mattia. - In: ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING. - ISSN 0924-2716. - 196:(2023), pp. 325-339. [10.1016/j.isprsjprs.2022.12.009]
File allegati a questo prodotto
File Dimensione Formato  
Marsocci_Inferring-3D-change-detection_2023.pdf

embargo fino al 15/01/2025

Note: articolo
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 721.48 kB
Formato Adobe PDF
721.48 kB Adobe PDF   Contatta l'autore
Marsocci_Inferring-3D-change-detection_2023.pdf

solo gestori archivio

Note: articolo
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 6.09 MB
Formato Adobe PDF
6.09 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1665436
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 10
social impact