Development of a Custom YOLO Model for Mussel Detection and Tracking
Budget: $10 – $30 USD
I am looking for a developer to train a custom YOLO model (YOLOv8, YOLOv11, or the newer YOLOv12/v26) specialized in detecting and tracking objects in real-time video. The primary focus is the mussel, and the model must distinguish between two specific classes: "mussel" (individual lost mussels) and "group" (clusters).
Project Requirements:
* Real-time Performance: The model will be used with a live camera feed. It must maintain at least 15 FPS on a standard NVIDIA GPU, prioritizing accuracy without sacrificing the fluid processing required for live monitoring.
* Counting & Tracking: The system must count every lost mussel per frame and maintain consistent IDs (Object Tracking) to follow individual movements over time.
* High Confidence: It must identify both classes (mussel, group) with high precision and recall.
What I will provide:
* A comprehensive dataset of over 5,000 images for labeling and training.
Deliverables:
1. Final Weights & Inference Script: Compatible with PyTorch or the Ultralytics CLI.
2. Training Documentation: A notebook or script detailing all hyperparameters used.
3. Performance Report: Metrics including Precision, Recall, mAP, and a sample video showing the tracking output.
4. README: Clear instructions to reproduce the inference and results on my end.
Once the model demonstrates accurate counts and stable ID tracking across consecutive frames, the project will be considered complete.
Project Requirements:
* Real-time Performance: The model will be used with a live camera feed. It must maintain at least 15 FPS on a standard NVIDIA GPU, prioritizing accuracy without sacrificing the fluid processing required for live monitoring.
* Counting & Tracking: The system must count every lost mussel per frame and maintain consistent IDs (Object Tracking) to follow individual movements over time.
* High Confidence: It must identify both classes (mussel, group) with high precision and recall.
What I will provide:
* A comprehensive dataset of over 5,000 images for labeling and training.
Deliverables:
1. Final Weights & Inference Script: Compatible with PyTorch or the Ultralytics CLI.
2. Training Documentation: A notebook or script detailing all hyperparameters used.
3. Performance Report: Metrics including Precision, Recall, mAP, and a sample video showing the tracking output.
4. README: Clear instructions to reproduce the inference and results on my end.
Once the model demonstrates accurate counts and stable ID tracking across consecutive frames, the project will be considered complete.
Related categories:
C Programming
Python
C# Programming
Machine Learning (ML)
C++ Programming
Computer Vision
Deep Learning
YOLO