Skip to main content
zenodoopen

Atmospheric Turbulence Dataset.

<h2><strong>This dataset comprises 38 video sequences that contain various levels of atmospheric turbulence.</strong></h2> <h3>Paul Hill, The University of Bristol</h3> <div>Please contact Paul Hill for any further information&nbsp;</div> <div>Paul.Hill@bristol.ac.uk</div> <h3>Sequences</h3> <ul> <li>The sequences were captured to give a range of</li> <li>Distances</li> <li>Turbulence levels</li> <li>Content (mainly aligning with discussed content of interest e.g. vehicles, buildings, roads etc.)</li> <li>The camera used was a Cannon R5, with a Canon 100-400mm zoom lens</li> <li>The sequences were captured over a period of three days in different locations</li> </ul> <h3>Preprocessing</h3> <ul> <li>All the sequences were cropped in time to.&nbsp;</li> <li>Get manageable / easily processable sequences of length of approximately 20 seconds</li> <li>To remove unwanted artefacts (hands in front of lenses, people walking through the shot etc.)</li> <li>Cropped referred (in the Excel file) that they were spatially cropped from higher resolution sequences (to focus on more interesting / coherent content)</li> </ul> <div>&nbsp;</div> <h3>Sequence Descriptions</h3> <div> <ul> <li>The included Excel file: Heathaze_datasets_descriptions_2024.xlsx gives a detailed descriptiong each sequence.</li> </ul> </div> <div>Directory Structure</div> <div>.</div> <div>├── CLEAR1 &nbsp; # Static PNG image results of the CLEAR1 method</div> <div>├── CLEAR2 &nbsp; # Example AVI CLEAR2 sliding window processed sequences</div> <div>├── Original_Seqs &nbsp;# All Original Sequences in MP4 format</div> <div>&nbsp;│ &nbsp; └── PNGs &nbsp; &nbsp; &nbsp; # The raw original sequences in directories named after the MP4 seq files.&nbsp;</div> <div>&nbsp;</div> <ul> <li>CLEAR1: Region and Pixel refer to the pixel by pixel and region-based fusion defined in the original CLEAR paper:&nbsp;Anantrasirichai et al. "Atmospheric &nbsp;Turbulence Mitigation Using Complex Wavelet-Based Fusion," Image Processing, IEEE Transactions on , vol.22, no.6, pp.2398-2408, June 2013 &nbsp;&nbsp;</li> <li>CLEAR2: The outputs of an example CLEAR2 method output on the input sequences:&nbsp;Anantrasirichai et al. &nbsp;Atmospheric turbulence mitigation for sequences with moving objects using recursive image fusion", ICIP, pp. 2895-2899 2018.</li> <li>Original_Seqs: The PNGs are numbered in temporal order in each directory (named as per the MP4 seq files).</li> </ul> <p>&nbsp;</p>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
16
Reuse readiness
8
Engagement
0