Data

Tools

Indexes

Applications

Experiments

Open Source Science

openmht

Python module for multiple hypothesis tracking.

https://github.com/jonperdomo/openmht

Science Score: 67.0%

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
    Found .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: ieee.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.8%) to scientific vocabulary

Keywords

computer-vision python tracking
Last synced: 6 months ago · JSON representation ·

Repository

Python module for multiple hypothesis tracking.

Basic Info
  • Host: GitHub
  • Owner: jonperdomo
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 163 KB
Statistics
  • Stars: 69
  • Watchers: 2
  • Forks: 21
  • Open Issues: 4
  • Releases: 0
Topics
computer-vision python tracking
Created almost 8 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

openmht

unit tests

Python module for multiple hypothesis tracking. Based on the article:

C. Kim, F. Li, A. Ciptadi and J. M. Rehg, "Multiple Hypothesis Tracking Revisited," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 4696-4704, doi: 10.1109/ICCV.2015.533.

URL: https://ieeexplore.ieee.org/document/7410890

This implementation utilizes motion scoring only (no appearance scoring)

Installation

Install the latest version of Python 3

$ pip install openmht

To also plot tracks after completion, install matplotlib:

$ pip install matplotlib

Formatting the Input CSV File

Format the input CSV columns with frame number and pixel positions using the examples under SampleData/ as a reference. The U,V values represent the 2D positions of objects/detections in that frame. A value of None in the output CSV indicates a missed detection. The Track column indicates the final track ID for a detection.

MHT Parameters

Modify parameters by editing the params.txt input file. Please read the paper mentioned above to understand how these parameters can be updated to improve performance and accuracy:

Motion scoring parameters

| Parameter | Description | |---|---| | v | The image (frame) area in pixels (Default: 307200). | | dth | Gating area for new detections implemented as the threshold for the Mahalinobis distance d2 between the observation and prediction (Default=1000). |

Kalman filter parameters

| Parameter | Description | |---|---| | k | Gain or blending factor. Higher gain results in a greater influence of the measurement relative to the filter's prediction (Default=0). | | q | Initial estimate of the process noise covariance (Default=0.00001). | | r | Initial estimate of the measurement noise covariance (Default=0.01). | | pd | Probability of detection PD (Default=0.9). |

Track tree pruning parameters

| Parameter | Description | |---|---| | n | Look back N frames and prune all branches that diverge from the solution. A larger N yields a more accurate solution due to a larger window, but will take a longer time (Default=1). | | bth | If the number of branches exceeds the number Bth then prune the track tree to only retain the top Bth branches. | | nmiss | A track hypothesis is deleted if it reaches Nmiss consecutive frames of missing observations. |

Running the Program

OpenMHT takes in the input CSV detections and the parameter file, and saves to the provided output CSV file:

$ python -m openmht InputDetections.csv OutputDetections.csv ParameterFile.txt

A default parameter file is provided in this repository: params.txt

For generating track plots, add the --plot parameter (requires matplotlib):

$ python -m openmht ... --plot

Example Results

Results from running SampleData/SampleInput.csv:

Plot

OutputTracks

Data

InputOutput
| Frame | U | V | |--|--|--| 0|0.0703|0.3163 1|0.1071|0.3746 1|0.1325|0.1618 2|0.1694|0.4534 2|0.1809|0.1910 2|0.4205|0.0977 3|0.2200|0.5700 3|0.2408|0.2755 3|0.5081|0.1618 4|0.2938|0.6429 4|0.3007|0.3222 4|0.5703|0.2201 5|0.3445|0.7157 5|0.3767|0.4184 5|0.6555|0.2988 6|0.4297|0.8149 6|0.4459|0.4767 6|0.7247|0.3688 7|0.4850|0.8703 |Frame|Track|U|V| |--|--|--|--| 0|0|0.0703|0.3163 0|1|None|None 0|2|None|None 0|3|None|None 1|0|0.1071|0.3746 1|1|0.1325|0.1618 1|2|None|None 1|3|None|None 2|0|0.1694|0.4534 2|1|0.1809|0.191 2|2|0.4205|0.0977 2|3|None|None 3|0|0.22|0.57 3|1|0.2408|0.2755 3|2|0.5081|0.1618 3|3|None|None 4|0|0.2938|0.6429 4|1|0.3007|0.3222 4|2|0.5703|0.2201 4|3|None|None 5|0|0.3445|0.7157 5|1|0.3767|0.4184 5|2|0.6555|0.2988 5|3|None|None 6|0|None|None 6|1|0.4459|0.4767 6|2|0.7247|0.3688 6|3|0.4297|0.8149 7|0|None|None 7|1|None|None 7|2|None|None 7|3|0.485|0.8703

Owner

  • Name: Jonathan Perdomo
  • Login: jonperdomo
  • Kind: user
  • Location: Philadelphia, PA
  • Company: Drexel University

Biomedical PhD Candidate at Drexel University.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Perdomo"
  given-names: "Jonathan Elliot"
  orcid: "https://orcid.org/0000-0001-7145-7401"
title: "OpenMHT"
version: 1.0.0
doi: 10.5281/zenodo.5731342
date-released: 2021-11-27
url: "https://github.com/jonperdomo/openmht"

GitHub Events

Total
  • Watch event: 4
Last Year
  • Watch event: 4

Committers

Last synced: almost 3 years ago

All Time
  • Total Commits: 45
  • Total Committers: 2
  • Avg Commits per committer: 22.5
  • Development Distribution Score (DDS): 0.133
Top Committers
Name Email Commits
Jonathan Perdomo p****5@g****m 39
Jonathan Perdomo j****b@g****m 6

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 19
  • Total pull requests: 7
  • Average time to close issues: 6 months
  • Average time to close pull requests: about 3 hours
  • Total issue authors: 14
  • Total pull request authors: 3
  • Average comments per issue: 2.47
  • Average comments per pull request: 0.29
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • SiddharthDey (3)
  • qiuqicao77 (2)
  • CalenDario13 (2)
  • bsdis (1)
  • saber131421 (1)
  • caroltk (1)
  • billypeanut (1)
  • ijunglee (1)
  • crchinn (1)
  • jonperdomo (1)
  • hunterls97 (1)
  • zl930216 (1)
  • minho8849 (1)
  • HuMengjing (1)
Pull Request Authors
  • jonperdomo (3)
  • SiddharthDey (3)
  • Engineero (1)
Top Labels
Issue Labels
enhancement (1)
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 13 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 5
  • Total maintainers: 1
pypi.org: openmht

OpenMHT

  • Versions: 5
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 13 Last month
Rankings
Stargazers count: 8.9%
Forks count: 9.9%
Dependent packages count: 10.0%
Average: 20.3%
Dependent repos count: 21.7%
Downloads: 50.8%
Maintainers (1)
jonperdomo
Last synced: 6 months ago

Dependencies

.github/workflows/python-publish.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v3 composite
  • pypa/gh-action-pypi-publish 27b31702a0e7fc50959f5ad993c78deac1bdfc29 composite
setup.py pypi