Optical remote sensing salient object detection datasets

Citation Author(s):
Bocheng
Liang
Submitted by:
Bocheng Liang
Last updated:
Tue, 04/15/2025 - 09:01
DOI:
10.21227/fn4d-rv94
License:
Creative Commons Attribution
3 Views
Categories:
Image Processing
Keywords:
salient object detection, optical remote sensing image
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

The ORSSD dataset consists of 800 optical remote sensing images with corresponding pixel-level annotations, divided into a training set of 600 images and a test set of 200 images. The EORSSD dataset is an extension of ORSSD, adding 1200 ORSIs for a total of 2000 images, and is split into 1400 training images and 600 test images. The ORSI-4199 dataset includes 2000 training images and 2199 testing images, making it the most challenging optical RSI-SOD dataset.

Instructions: 

The ORSSD dataset consists of 800 optical remote sensing images with corresponding pixel-level annotations, divided into a training set of 600 images and a test set of 200 images. The EORSSD dataset is an extension of ORSSD, adding 1200 ORSIs for a total of 2000 images, and is split into 1400 training images and 600 test images. The ORSI-4199 dataset includes 2000 training images and 2199 testing images, making it the most challenging optical RSI-SOD dataset.

Dataset Files

    Files have not been uploaded for this dataset

     

    QUESTIONS?