The presented dataset is a supplementary material to the paper [1] and it represents the X-Ray Energy Dispersive (EDS)/ Scanning Electron Microscopy (SEM) images of a shungite-mineral particle. Pansharpening is a procedure for enhancing the spatial resolution of a multispectral image, here the EDS individual bands, with a high-spatial panchromatic image, here the SEM image. Pansharpening techniques are usually tested with remote sensed data, but the procedures have been efficient in close-range MS-PAN pairs as well [3].

Categories:
127 Views

The Contest: Goals and Organization

The 2022 IEEE GRSS Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee, aims to promote research on semi-supervised learning. The overall objective is to build models that are able to leverage a large amount of unlabelled data while only requiring a small number of annotated training samples. The 2022 Data Fusion Contest will consist of two challenge tracks:

Track SLM:Semi-supervised Land Cover Mapping

Last Updated On: 
Mon, 03/07/2022 - 04:41

Sequential skeleton and average foot pressure data for normal and five pathological gaits (i.e., antalgic, lurching, steppage, stiff-legged, and Trendelenburg) were simultaneously collected. The skeleton data were collected by using Azure Kinect (Microsoft Corp. Redmond, WA, USA). The average foot pressure data were collected by GW1100 (GHIWell, Korea). 12 healthy subjects participated in data collection. They simulated the pathological gaits under strict supervision. A total of 1,440 data instances (12 people x 6 gait types x 20 walkings) were collected.

Categories:
918 Views

There is an industry gap for publicly available electric utility infrastructure imagery.  The Electric Power Research Institute (EPRI) is filling this gap to support public and private sector AI innovation.  This dataset consists of ~30,000 images of overhead Distribution infrastructure.  These images have been anonymized, reviewed, and .exif image-data scrubbed.  These images are unlabeled and do not contain annotations.  EPRI intends to label these data to support its own research activities.  As these labels are created, EPRI will periodically update this dataset with those data.

Instructions: 

These images are not labeled or annotated.  However, as these images are labeled, EPRI will update this dataset periodically.  If you have annotations you'd like to contribute, please send them, with a description of your labeling approach, to ai@epri.com.

 

Also, if you see anything in the imagery that looks concerning, please send the image and image number ai@epri.com

Categories:
883 Views

This dataset was acquired at the Radboud University Medical Center, Nijmegen, the Netherlands and enriched with landmarks by Fraunhofer MEVIS. It consists of nine datasets of consecutive sections, each containing four slides stained with H&E, CD8, CD45, Ki67, respectively.

Instructions: 

# HyReCo - Hybrid Re-stained and Consecutive Data

The **HyReCo** dataset contains whole slide images of consecutive and restained slides. There are nine different cases (29, 108, 361, 464, 533, 611, 628, 644, 679) with 4 consecutive slices each. They were stained with HE, CD8, KI67, CD45. Additionally, the HE slice was restained with PHH3. All versions were scanned and are available as whole slide images in the BigTIFF format.

There are annotations for each image in an additional CSV file. These files contain lists of point annotations that attempt to mark the same location in all images of a single case. Each line describes a point annotation in world coordinates (x,y,z). The unit is mm. The origin of the coordinate system is the upper left corner of the image.

The **HyReCo-Additional** dataset is structured in the same way, but does only contain restained image pairs of HE and PHH3. There are 54 different cases for this additional dataset with point annotations for each image.

## HyReCo file structure

HyReCo/

- CD45/
- 108.csv
- 108.tif
- 29.csv
- 29.tif
- 361.csv
- 361.tif
- 464.csv
- 464.tif
- 533.csv
- 533.tif
- 611.csv
- 611.tif
- 628.csv
- 628.tif
- 644.csv
- 644.tif
- 679.csv
- 679.tif
- CD8/
- 108.csv
- 108.tif
- 29.csv
- 29.tif
- 361.csv
- 361.tif
- 464.csv
- 464.tif
- 533.csv
- 533.tif
- 611.csv
- 611.tif
- 628.csv
- 628.tif
- 644.csv
- 644.tif
- 679.csv
- 679.tif
- HE/
- 108.csv
- 108.tif
- 29.csv
- 29.tif
- 361.csv
- 361.tif
- 464.csv
- 464.tif
- 533.csv
- 533.tif
- 611.csv
- 611.tif
- 628.csv
- 628.tif
- 644.csv
- 644.tif
- 679.csv
- 679.tif
- KI67/
- 108.csv
- 108.tif
- 29.csv
- 29.tif
- 361.csv
- 361.tif
- 464.csv
- 464.tif
- 533.csv
- 533.tif
- 611.csv
- 611.tif
- 628.csv
- 628.tif
- 644.csv
- 644.tif
- 679.csv
- 679.tif
- PHH3/
- 108.csv
- 108.tif
- 29.csv
- 29.tif
- 361.csv
- 361.tif
- 464.csv
- 464.tif
- 533.csv
- 533.tif
- 611.csv
- 611.tif
- 628.csv
- 628.tif
- 644.csv
- 644.tif
- 679.csv
- 679.tif

## HyReCo-Additiona file structure

HyReCo-Additional/

- HE/
- 108.csv
- 108.tif
- 128.csv
- 128.tif
- 147.csv
- 147.tif
- 155.csv
- 155.tif
- 157.csv
- 157.tif
- 158.csv
- 158.tif
- 168.csv
- 168.tif
- 172.csv
- 172.tif
- 208.csv
- 208.tif
- 237.csv
- 237.tif
- 241.csv
- 241.tif
- 244.csv
- 244.tif
- 245.csv
- 245.tif
- 260.csv
- 260.tif
- 264.csv
- 264.tif
- 272.csv
- 272.tif
- 281.csv
- 281.tif
- 296.csv
- 296.tif
- 29.csv
- 29.tif
- 313.csv
- 313.tif
- 315.csv
- 315.tif
- 31.csv
- 31.tif
- 320.csv
- 320.tif
- 343.csv
- 343.tif
- 349.csv
- 349.tif
- 359.csv
- 359.tif
- 361.csv
- 361.tif
- 364.csv
- 364.tif
- 385.csv
- 385.tif
- 397.csv
- 397.tif
- 399.csv
- 399.tif
- 400.csv
- 400.tif
- 405.csv
- 405.tif
- 409.csv
- 409.tif
- 43.csv
- 43.tif
- 446.csv
- 446.tif
- 449.csv
- 449.tif
- 457.csv
- 457.tif
- 464.csv
- 464.tif
- 485.csv
- 485.tif
- 500.csv
- 500.tif
- 504.csv
- 504.tif
- 506.csv
- 506.tif
- 514.csv
- 514.tif
- 529.csv
- 529.tif
- 541.csv
- 541.tif
- 61.csv
- 61.tif
- 64.csv
- 64.tif
- 663.csv
- 663.tif
- 67.csv
- 67.tif
- 705.csv
- 705.tif
- 79.csv
- 79.tif
- 82.csv
- 82.tif
- 8.csv
- 8.tif
- PHH3/
- 108.csv
- 108.tif
- 128.csv
- 128.tif
- 147.csv
- 147.tif
- 155.csv
- 155.tif
- 157.csv
- 157.tif
- 158.csv
- 158.tif
- 168.csv
- 168.tif
- 172.csv
- 172.tif
- 208.csv
- 208.tif
- 237.csv
- 237.tif
- 241.csv
- 241.tif
- 244.csv
- 244.tif
- 245.csv
- 245.tif
- 260.csv
- 260.tif
- 264.csv
- 264.tif
- 272.csv
- 272.tif
- 281.csv
- 281.tif
- 296.csv
- 296.tif
- 29.csv
- 29.tif
- 313.csv
- 313.tif
- 315.csv
- 315.tif
- 31.csv
- 31.tif
- 320.csv
- 320.tif
- 343.csv
- 343.tif
- 349.csv
- 349.tif
- 359.csv
- 359.tif
- 361.csv
- 361.tif
- 364.csv
- 364.tif
- 385.csv
- 385.tif
- 397.csv
- 397.tif
- 399.csv
- 399.tif
- 400.csv
- 400.tif
- 405.csv
- 405.tif
- 409.csv
- 409.tif
- 43.csv
- 43.tif
- 446.csv
- 446.tif
- 449.csv
- 449.tif
- 457.csv
- 457.tif
- 464.csv
- 464.tif
- 485.csv
- 485.tif
- 500.csv
- 500.tif
- 504.csv
- 504.tif
- 506.csv
- 506.tif
- 514.csv
- 514.tif
- 529.csv
- 529.tif
- 541.csv
- 541.tif
- 61.csv
- 61.tif
- 64.csv
- 64.tif
- 663.csv
- 663.tif
- 67.csv
- 67.tif
- 705.csv
- 705.tif
- 79.csv
- 79.tif
- 82.csv
- 82.tif
- 8.csv
- 8.tif

Categories:
142 Views

We present here an annotated thermal dataset which is linked to the dataset present in https://ieee-dataport.org/open-access/thermal-visual-paired-dataset

To our knowledge, this is the only public dataset at present, which has multi class annotation on thermal images, comprised of 5 different classes.

This database was hand annotated over a period of 130 work hours.

Instructions: 

We manually annotate all images using the VGG Image Annotator (VIA) [Dutta, Abhishek, Ankush Gupta, and Andrew Zissermann. "VGG image annotator (VIA)." URL: http://www.robots.ox.ac.uk/~vgg/software/via (2016).] for the creation of the box.

 

We use the standard annotation format provided. 

 

'sonel_annotation.csv' uses the image present in the folder named 'sonel'.

Similarly, the files 'flir_annotation.csv' and 'flir_old_annotation.csv' are based on the images present in the fodlers 'flir' and 'flir_old'

 

The images can be found as a part of our older work which is presented as an open database [Suranjan Goswami, Nand Kumar Yadav, Satish Kumar Singh. "Thermal Visual Paired Dataset." doi: 10.21227/jjba-6220]

 

The data is classified into 5 different classes

 

Class:Abbreviation:Key 

modern infrastructure: inf:5

crowd: cro:4

human:hum:3

animal:ani:2

nature:nat:1

 

In each file, which is presented as an excel file, the data columns are as follows:

filename, file size, file attribute, region count, region id, region shape attributes and region attributes.

 

region count shows the number of regions present in each image, region attribute presents the details of the rectangle which contains the said attribute and the region attributes presents the attribute name.

These can be directly input into VIA after loading the corresponding database images to see the outlined annotations.

 

Since the annotation presented by VIA might not be easily usable by all data readers, we have modified the same to be easily processed as the numbers files

 

These are 'sonel_annotation-numbers.csv', 'flir_annotation-numbers.csv' and 'flir_old_annotation-numbers.csv' .

Here, the class abbreviations are replaced by their corresponding number key as provided above.

 

Please note that the database we have used contains both registered and unregistered images as a part of the database. 

All registered thermal images that have been annotated only, not the unregistered ones as our work required registered thermal images.

 

This is a one way registration: that is, the annotation done on the thermal images should reflect on the optical images. 

We have not included the optical annotation method here, wherein we use DETR to annotate the registered optical images and use the corresponding mapping to create the 2 way annotation.

 

We also include 3 ZIP files with the images and their corresponding annotations both manually and done with DETR.

All annotations are labelled as NAME, X_START coordinate, Y_START coordinate, WIDTH, HEIGHT, CLASS for the individual manual annotations.

FOr the DETR annotations, they correspond to NAME, X_START coordinate, Y_START coordinate, X_END coordinate, Y_END coordinate, CLASS.

 

This database is presented as a part of our work "Novel Deep Learning Method for Thermal to Annotated Thermal-Optical Fused Images"

Categories:
469 Views

<p>This is the image dataset for satellite image processing&nbsp; which is a collection therml infrared and multispectral images .</p>

Instructions: 

Dataset images
Thermal infrared images and multispectral images
image size:512x512
format:
image:.tiff
file :.h5

Categories:
1230 Views

WITH the advancement in sensor technology, huge amounts of data are being collected from various satellites. Hence, the task of target-based data retrieval and acquisition has become exceedingly challenging. Existing satellites essentially scan a vast overlapping region of the Earth using various sensing techniques, like multi-spectral, hyperspectral, Synthetic Aperture Radar (SAR), video, and compressed sensing, to name a few.

Instructions: 

A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images

Email the authors at ushasi@iitb.ac.in for any query.

 

Classes in this dataset:

Airplane

Baseball Diamond

Buildings

Freeway

Golf Course

Harbor

Intersection

Mobile home park

Overpass

Parking lot

River

Runway

Storage tank

Tennis court

Paper

The paper is also available on ArXiv: A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images

 

Feel free to cite the author, if the work is any help to you:

 

``` @InProceedings{Chaudhuri_2020_EoC, author = {Chaudhuri, Ushasi and Banerjee, Biplab and Bhattacharya, Avik and Datcu, Mihai}, title = {A Zero-Shot Sketch-based Inter-Modal Object Retrieval Scheme for Remote Sensing Images}, booktitle = {http://arxiv.org/abs/2008.05225}, month = {Aug}, year = {2020} }

 

Categories:
651 Views

WITH the advancement in sensor technology, huge amounts of data are being collected from various satellites. Hence, the task of target-based data retrieval and acquisition has become exceedingly challenging. Existing satellites essentially scan a vast overlapping region of the Earth using various sensing techniques, like multi-spectral, hyperspectral, Synthetic Aperture Radar (SAR), video, and compressed sensing, to name a few.

Categories:
267 Views

WITH the advancement in sensor technology, huge amounts of data are being collected from various satellites. Hence, the task of target-based data retrieval and acquisition has become exceedingly challenging. Existing satellites essentially scan a vast overlapping region of the Earth using various sensing techniques, like multi-spectral, hyperspectral, Synthetic Aperture Radar (SAR), video, and compressed sensing, to name a few.

Categories:
177 Views

Pages