Data

Tools

Indexes

Applications

Experiments

Open Source Science

PawsomeTracker

https://github.com/yakir12/pawsometracker.jl

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: yakir12
  • License: mit
  • Language: Julia
  • Default Branch: main
  • Size: 164 KB
Statistics
  • Stars: 6
  • Watchers: 1
  • Forks: 0
  • Open Issues: 1
  • Releases: 9
Created over 1 year ago · Last pushed 10 months ago
Metadata Files
Readme License Citation

README.md

PawsomeTracker

Build Status Coverage Aqua

A simple, performant, and robust auto-tracker for videos of a single moving target. Uses a Difference of Gaussian (DoG) filter to track the target in the video file. Works with concurrency, videos that have a non-zero start-time, and pixel aspect ratios (i.e. SAR, DAR, etc) other than one.

API

Single video file

track(file; start, stop, target_width, start_location, window_size)

Use a Difference of Gaussian (DoG) filter to track a target in a video file. - start: start tracking after start seconds. Defaults to 0. - stop: stop tracking at stop seconds. Defaults to 86399.999 seconds (24 hours minus one millisecond). - target_width: the full width of the target (diameter, not radius). It is used as the FWHM of the center Gaussian in the DoG filter. Arbitrarily defaults to 25 pixels. - start_location: one of the following: 1. missing: the target will be detected in a large (half as large as the frame) window centered at the frame. 2. CartesianIndex{2}: the Cartesian index (into the image matrix) indicating where the target is at start. Note that when the aspect ratio of the video is not equal to one, this Cartesian index should be to the raw, unscaled, image frame. 3. NTuple{2}: (x, y) where x and y are the horizontal and vertical pixel-distances between the left-top corner of the video-frame and the target at start. Note that regardless of the aspect ratio of the video, this coordinate should be to the scaled image frame (what you'd see in a video player). Defaults to missing. - window_size: Defaults to to a good minimal size that depends on the target width (see fix_window_size for details). But can be one of the following: 1. NTuple{2}: a tuple (w, h) where w and h are the width and height of the window (region of interest) in which the algorithm will try to detect the target in the next frame. This should be larger than the target_width and relate to how fast the target moves between subsequent frames. 2. Int: both the width and height of the window (region of interest) in which the algorithm will try to detect the target in the next frame. This should be larger than the target_width and relate to how fast the target moves between subsequent frames. - darker_target: set to true if the target is darker than its background, and vice versa. Defaults to true. - fps: frames per second. Sets how many times the target's location is registered per second. Set to a low number for faster and sparser tracking, but adjust the window_size accordingly. Defaults to an arbitrary value of 24 frames per second. - diagnostic_file: specify a file path to save a diagnostic video showing a low-memory version of the tracking video with the path of the target superimposed on it. Defaults to nothing.

Returns a vector with the time-stamps per frame and a vector of Cartesian indices for the detection index per frame.

Multiple consecutive files (e.g. segmented video files)

track(files::AbstractVector; start::AbstractVector, stop::AbstractVector, target_width, start_location::AbstractVector, window_size)

Use a Difference of Gaussian (DoG) filter to track a target across multiple video files. start, stop, and start_location all must have the same number of elements as files does. If the second, third, etc elements in start_location are missing then the target is assumed to start where it ended in the previous video (as is the case in segmented videos).

Citing

See CITATION.bib for the relevant reference(s).

Owner

  • Name: Yakir Luc Gagnon
  • Login: yakir12
  • Kind: user
  • Location: Malmö Sweden
  • Company: Lund University

Citation (CITATION.bib) 

@misc{PawsomeTracker.jl,
	author  = {Yakir Gagnon <12.yakir@gmail.com> and contributors},
	title   = {PawsomeTracker.jl},
	url     = {https://github.com/yakir12/PawsomeTracker.jl},
	version = {v1.0.0-DEV},
	year    = {2024},
	month   = {12}
}

GitHub Events

Total
  • Create event: 23
  • Commit comment event: 4
  • Release event: 9
  • Issues event: 17
  • Watch event: 5
  • Delete event: 3
  • Issue comment event: 15
  • Push event: 70
  • Pull request event: 11
Last Year
  • Create event: 23
  • Commit comment event: 4
  • Release event: 9
  • Issues event: 17
  • Watch event: 5
  • Delete event: 3
  • Issue comment event: 15
  • Push event: 70
  • Pull request event: 11

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 8
  • Total pull requests: 9
  • Average time to close issues: 5 days
  • Average time to close pull requests: 2 days
  • Total issue authors: 1
  • Total pull request authors: 3
  • Average comments per issue: 0.63
  • Average comments per pull request: 0.33
  • Merged pull requests: 9
  • Bot issues: 0
  • Bot pull requests: 4
Past Year
  • Issues: 8
  • Pull requests: 9
  • Average time to close issues: 5 days
  • Average time to close pull requests: 2 days
  • Issue authors: 1
  • Pull request authors: 3
  • Average comments per issue: 0.63
  • Average comments per pull request: 0.33
  • Merged pull requests: 9
  • Bot issues: 0
  • Bot pull requests: 4
View more stats
Top Authors
Issue Authors
  • yakir12 (8)
  • JuliaTagBot (1)
Pull Request Authors
  • yakir12 (6)
  • dependabot[bot] (3)
  • github-actions[bot] (1)
Top Labels
Issue Labels
Pull Request Labels
dependencies (3) github_actions (1)

Packages

  • Total packages: 1
  • Total downloads: unknown
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 9
juliahub.com: PawsomeTracker
  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Downloads: 3.2%
Dependent repos count: 3.2%
Average: 7.6%
Dependent packages count: 16.3%
Last synced: 10 months ago

Dependencies

.github/workflows/CI.yml actions
  • actions/checkout v4 composite
  • julia-actions/cache v2 composite
  • julia-actions/julia-buildpkg v1 composite
  • julia-actions/julia-runtest v1 composite
  • julia-actions/setup-julia v2 composite
.github/workflows/CompatHelper.yml actions
.github/workflows/TagBot.yml actions
  • JuliaRegistries/TagBot v1 composite
.github/workflows/Register.yml actions
  • julia-actions/RegisterAction latest composite