본문 바로가기

Automatic Generation Method for Urban Change Detection Dataset

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
저널
IEEE ACCESS14 · pp.16984 · 2026
피인용
Web of Science 0Scopus 0
FWCI (Scopus)
0
JCR IF
JCR 2024 3.6
ISSN
2169-3536

저자

  1. 하진수제1저자Pusan Natl Univ, Dept Nanomechatron Engn, Pusan 46241, South Korea
  2. Kim, Byeong HakKorea Inst Ind Technol, Adv Mobil & Robot Syst Grp, Daegu 42994, South Korea
  3. 고대철Pusan Natl Univ, Dept Nanomechatron Engn, Pusan 46241, South Korea
  4. Won, Hong-In교신저자Korea Inst Ind Technol, Mfg AI Res Ctr, Incheon 31056, South Korea
  5. 장진석교신저자Korea Inst Ind Technol, Adv Mobil & Robot Components Grp, Daegu 42994, South Korea

초록

This study investigates an inpainting-based data generation approach for urban change detection and analyzes its impact on the model generalization performance. The proposed method constructs temporally consistent before and after image pairs by applying inpainting to existing images, thereby enabling seamless integration with existing change detection frameworks. Rather than replacing real-world datasets, the generated data were designed to increase the training diversity and mitigate dataset-specific biases. Comprehensive experiments were conducted using multiple representative change detection architectures across different datasets. The results show that incorporating the generated data alongside real training samples consistently improves cross-dataset generalization performance. In particular, models trained on S2Looking achieved up to a 14.0 percentage-point improvement in F1-score on the unseen WHU-CD dataset, depending on the model architecture. By contrast, training with the generated data alone leads to limited generalization when evaluated on real test sets. These findings indicate that inpainting-based synthetic data can serve as a complementary training resource for enhancing the robustness of urban change detection. Future work will focus on reducing the domain gap between synthetic and real data by extending the proposed framework beyond simple object removal to incorporate more diverse change scenarios that consider background context and temporal variations, such as seasonal appearance changes.

키워드

generalization performancegenerated datasetsinpaintingobject combinationUrban change detection

식별자

Scopus EID
2-s2.0-105028910907
WoS UID
001682702600037