EcoAssist Versions Save

Simplify camera trap image analysis with ML species recognition models based around the MegaDetector model

v5.3

2 weeks ago

Adjusted code for the new NZ species identification model.

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v5.2...v5.3

v5.2

1 month ago

Added DeepFaune v1.1 model to the list of classifiers.

What's Changed

Add DeepFaune v1.1 by @PetervanLunteren in https://github.com/PetervanLunteren/EcoAssist/pull/38

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v5.0...v5.2

v5.1

2 months ago

Moved PyQt5 dependency to PySide6 for Unix systems to avoid HomeBrew dependency and extra install.

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v.5.0...v5.1

v5.0

2 months ago

new window: simple mode
saves user settings
incorporated Namibian species model
automatic model download
switch between virtual environments

What's Changed

Update to v5.0 by @PetervanLunteren in https://github.com/PetervanLunteren/EcoAssist/pull/34

New Contributors

@PetervanLunteren made their first contribution in https://github.com/PetervanLunteren/EcoAssist/pull/34

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.4...v.5.0

v.5.0

2 months ago

new window: simple mode
saves user settings
incorporated Namibian species model
automatic model download
switch between virtual environments

What's Changed

Update to v5.0 by @PetervanLunteren in https://github.com/PetervanLunteren/EcoAssist/pull/34

New Contributors

@PetervanLunteren made their first contribution in https://github.com/PetervanLunteren/EcoAssist/pull/34

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.4...v.5.0

v4.4

5 months ago

In previous versions of EcoAssist (v3.0 > v4.3) it was possible to train your own object detection models based on MegaDetector to detect your target species. Although this did work, it wasn't the best approach to develop a species recognition model. It required lots of training data, processing power, time, electricity and wasn't very accurate. Advancing insights revealed that better results can be obtained by using a object classification model to be used in conjunction with the results of MegaDetector. The animals will then be located by MegaDetector, and further classified by your custom model. EcoAssist > v4.2 does support the deployment of a classification model to be used in conjunction with MegaDetector, but training such a model is more complicated and hasn't been incorporated into EcoAssist (yet).

Further:

new logo
fixed scroll issues
moved documentation to https://addaxdatascience.com/ecoassist/

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.3...v4.4

v4.3

6 months ago

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.2...v4.3

v4.2

6 months ago

Annotation in xml to be able to store more information
human in the loop feature
minor fixes

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.1...v4.2

v4.1

8 months ago

Added human-in-the-loop functionality to verify detections and create training data. Possibility to select an image subset based on specific classes, confidence ranges, and selection methods.

What's Changed

Automatic localization of git and conda during Windows installation by @BobbyCephy in https://github.com/PetervanLunteren/EcoAssist/pull/11
Copied Exif data from source image during post processing by @ehallein in https://github.com/PetervanLunteren/EcoAssist/pull/14

New Contributors

@BobbyCephy made their first contribution in https://github.com/PetervanLunteren/EcoAssist/pull/11

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v4.0...v4.1

v4.0

11 months ago

Added functionality to train object detection models and fixed bugs.

What's Changed

Fixed a CUDA out of memory bug by @ehallein in https://github.com/PetervanLunteren/EcoAssist/pull/7

Full Changelog: https://github.com/PetervanLunteren/EcoAssist/compare/v3.0...v4.0