GSoC 2025 Project Ideas

Please ask questions through issues on the respective project's repo.

Tags available @henrykironde, @bw4sz, @ethanwhite,

• Preferred names (Henry, Ben, Ethan)
• Preferred_greeting (Hi|Hello|Dear|Thanks|Thank you [First_name])

The code of conduct should be your first read.

---

Proposal 1: Efficient Detection of Unique Images from Overlapping Images

Rationale:

Develop a workflow to compute unique image detections from overlapping images using either the weecology/DoubleCounting repository or the open-forest-observatory/geograypher repository. This project will focus on implementing an efficient algorithm for removing double counting among overlapping images.

Approach:

• Choose a suitable repository either weecology/DoubleCounting or open-forest-observatory/geographer for implementing the unique image detections workflow.
• Develop an efficient algorithm for removing double counting among overlapping images.
• Evaluate the performance of the workflow on various datasets.

Expected Outcomes:

• A workflow for computing unique image detections from overlapping images.
• Documentation on using the workflow.

Source Code: DeepForest

Degree of Difficulty:

• Intermediate, long (350 hours)

Skills:

• Deep learning
• Git/GitHub
• Machine learning
• Software testing
• Python and Python package deployment

Mentors:

• @bw4sz
• @henrysenyondo
• @ethanwhite

---

Proposal 2: Developing an Active Learning Module for DeepForest

Rationale:

Implement an active learning module for DeepForest, allowing users to select new images for model training based on current model scores. This project will focus on integrating the BOEM repository's active learning code into DeepForest, enabling more efficient model training and improved accuracy.

Approach:

• Integrate the BOEM repository's active learning code into DeepForest.
• Develop a user-friendly interface for selecting new images based on model scores.
• Evaluate the effectiveness of the active learning module in improving model accuracy.

Expected Outcomes:

• An active learning module for DeepForest using BOEM.
• Documentation on using the active learning module.

Source Code: DeepForest

Degree of Difficulty:

• Intermediate, long (350 hours)

Skills:

• Deep learning
• Git/GitHub
• Active learning
• Python and Python package deployment

Mentors:

• @bw4sz
• @henrysenyondo
• @ethanwhite

---

Proposal 3: The Airborne Wildlife benchmark dataset.

https://github.com/landing-ai/vision-agent?tab=readme-ov-file

Rationale:

There are hundreds of airborne wildlife datasets out there, most are unavailable, in many different formats and organizations and cannot be used for machine learning model training. We have identified hundreds of datasets and will work with partners to collect, standardize and training a general airborne animal detector.

Approach:

• Download and organize datasets from previously identified sources
• Clone the MillionTrees repo https://milliontrees.idtrees.org/en/latest/ to create a MillionAnimals benchmark. The organization, evaluation and structure is already well defined.
• Develop baseline models for a single general animal detector across taxa and backgrounds for screening of images, much as camera traps has https://github.com/agentmorris/MegaDetector. This work may be in partnership with https://github.com/microsoft/CameraTraps, depending on the readiness and state of the repo.
• Connect and document both MillionTrees and MillionAnimals with DeepForest for reproducible model training.

Expected Outcomes:

• An agent-interaction module for DeepForest using VisionAgent.
• Documentation on using the agent module.

Source Code: DeepForest

Degree of Difficulty:

• Intermediate, long (350 hours)

Skills:

• Deep learning
• Git/GitHub
• Active learning
• Python and Python package deployment

Mentors:

• @bw4sz
• @henrysenyondo
• @ethanwhite

---