Unbalanced Datasets Management for the Problem of Segmentation of Satellite Images

Скорочена інформація про документ
dc.contributor.authorOkhrimenko, Anton
dc.contributor.authorKussul, Nataliia
dc.date.accessioned2025-03-24T10:53:43Z
dc.date.available2025-03-24T10:53:43Z
dc.date.issued2024-10
dc.description.abstractUnbalanced datasets pose significant challenges in the segmentation of satellite images for crop classification tasks. This paper proposes a method to mitigate the bias of models trained on such datasets without the need for additional data collection. The approach involves using spatial weight masks to modify the loss function during model training, assigning higher or lower importance to pixels based on their reliability. The reliability of pixels is determined using algorithms like K-Nearest Neighbors (KNN), and the weight masks undergo various transformations, including morphological operations and Gaussian blur, to refine their texture and ensure smoother transitions between weight factors. Experiments conducted on a dataset of satellite imagery from the Kyiv region demonstrate notable improvements in overall accuracy and Intersection over Union (IoU) when using weight masks that favor normal pixels and apply morphological dilation and Gaussian blur. The proposed method proves particularly beneficial for underrepresented crop types. Additionally, the paper explores the incorporation of synthetic data generated by a Generative Adversarial Network (GAN) alongside real data, revealing slight improvements in recognizing less common crops. Comparative analysis shows that using weight masks offers similar accuracy gains to GAN-based augmentation while being more costeffective by eliminating the need for training an intermediary model and generating additional data. The results suggest that the proposed method of using spatial weight masks is a viable and efficient approach to managing unbalanced datasets in satellite image segmentation for crop classification tasks.
dc.format.extent6 p.
dc.identifier.citationOkhrimenko, A. Unbalanced Datasets Management for the Problem of Segmentation of Satellite Images / Anton Okhrimenko, Nataliia Kussul // 2024 IEEE Fourth International Conference on System Analysis & Intelligent Computing (SAIC), [Kyiv], 8-10 October 2024. - Kyiv, 2024. - 6 p.
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/73026
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeKyiv
dc.relation.ispartof2024 IEEE Fourth International Conference on System Analysis & Intelligent Computing (SAIC), 8-10 October, Kyiv, Ukraine
dc.subjectKNN
dc.subjectDataset Quality Assessment
dc.subjectImbalanced Datasets
dc.subjectHard Cases
dc.subjectCrop Classification
dc.subjectGenerative Adversarial Networks
dc.subjectTraining Data Generation
dc.subjectData Set Imbalance
dc.subjectU- Net
dc.titleUnbalanced Datasets Management for the Problem of Segmentation of Satellite Images
dc.typeArticle

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
SAIC2024_paper_19.pdf
Розмір:
736.57 KB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
8.98 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Матеріали конференцій, семінарів і т.п. (ММАД)