The primary objective of this project was to develop a computer vision system that utilizes drone imagery to generate valuable information and insights for pineapple farmers in Africa. By providing accurate statistics and maps, the system aims to help farmers make informed decisions, optimize their farming practices, and ultimately increase their yield and livelihood.

Key Achievements:

The project leveraged a range of computer vision and machine learning techniques, including object detection, object classification, sliding window, image processing, geometric calibration, and feature prediction.

The system was built using popular libraries such as OpenCV, TensorFlow, PIL, NumPy, CUDA, cuDNN, and GeoTIFF.

The dataset used for training and testing the model was carefully curated and split into two subgroups: 70% for training and 30% for testing.

The model was trained using the faster-rcnn-resnet101 architecture, with a total of 3,186 images and 3 label classes.

The training process involved 160,000 epochs to ensure optimal performance.

Results:

By combining cutting-edge computer vision techniques with drone technology, this project demonstrates the potential to revolutionize pineapple farming in Africa. The developed system empowers farmers with actionable insights, enabling them to make data-driven decisions and optimize their farming practices for increased productivity and profitability.