JUHE API Marketplace
DATASET
Open Source Community

danaroth/salinas

The nfcorpus dataset is a medical information retrieval collection comprising 5,371 documents, each with a document ID, URL, title, and abstract. It was introduced by Vera Boteva et al. at ECIR 2016 and serves as the basis for several related splits (e.g., `nfcorpus_dev`, `nfcorpus_test`).

Updated 11/9/2023
hugging_face

Description

Dataset Description

This scene was captured by a 224‑band AVIRIS sensor over California's Salinas Valley, providing high spatial resolution (3.7 m per pixel). The coverage includes 512 rows and 217 columns. As with the Indian Pines scene, 20 water‑absorption bands were discarded: bands [108‑112], [154‑167], and 224. The image is available solely as sensor radiance data and includes vegetation, bare soil, and vineyards. The Salinas ground truth contains 16 classes.

A small sub‑scene, referred to as Salinas‑A, is also commonly used. It spans 86 × 83 pixels at row/column coordinates [591‑676, 158‑240] and includes six classes.

Features

The ground‑truth classes and sample counts for the full Salinas scene are listed below:

#ClassSample Count
1Broccoli_green_weeds_12009
2Broccoli_green_weeds_23726
3Fallow1976
4Fallow_rough_plow1394
5Fallow_smooth2678
6Stubble3959
7Celery3579
8Grapes_untrained11271
9Soil_vinyard_develop6203
10Corn_senesced_green_weeds3278
11Lettuce_romaine_4wk1068
12Lettuce_romaine_5wk1927
13Lettuce_romaine_6wk916
14Lettuce_romaine_7wk1070
15Vinyard_untrained7268
16Vinyard_vertical_trellis1807

The ground‑truth classes and sample counts for the Salinas‑A sub‑scene are:

#ClassSample Count
1Broccoli_green_weeds_1391
2Corn_senesced_green_weeds1343
3Lettuce_romaine_4wk616
4Lettuce_romaine_5wk1525
5Lettuce_romaine_6wk674
6Lettuce_romaine_7wk799

Quick Look

Salinas Sample spectral bands of the Salinas dataset.

Salinas gt Ground truth of the Salinas dataset.

SalinasA Sample spectral bands of the Salinas‑A dataset.

SalinasA gt Ground truth of the Salinas‑A dataset.

Acknowledgments

The dataset was originally collected by Manuel Graña, Miguel‑Angel Veganzones, and Borja Ayerdi.

Original dataset link:

https://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes

AI studio

Generate PPTs instantly with Nano Banana Pro.

Generate PPT Now

Access Dataset

Login to Access

Please login to view download links and access full dataset details.

Topics

Hyperspectral Remote Sensing
Land Cover Classification

Source

Organization: hugging_face

Created: Unknown

Power Your Data Analysis with Premium AI Models

Supporting GPT-5, Claude-4, DeepSeek v3, Gemini and more.

Enjoy a free trial and save 20%+ compared to official pricing.