Cabbage Trunk Detection

Project overview

Cabbage images were annotated for a computer vision dataset focused on detecting cabbage trunks. The work involved identifying visible cabbage trunks and creating accurate bounding box annotations around them to generate high-quality training data for an AI-based object detection model.

Work performed

• Reviewed and organised the image dataset before annotation began.
• Identified visible cabbage trunks in each image.
• Created accurate bounding boxes around the cabbage trunks.
• Maintained consistent labelling using the Cabbage Trunk class.
• Partially visible trunks were annotated wherever applicable.
• Quality checks were carried out and inaccurate or missed annotations were corrected.
• Bounding boxes were confirmed as suitable for object detection model training.

What made it hard

• Detecting trunks partially hidden by cabbage leaves.
• Trunk sizes and viewing angles varied across the dataset.
• Small or partially visible trunks still needed accurate annotation.
• Keeping bounding boxes tight around irregular trunk shapes took care.
• Shadows, soil and surrounding vegetation obscured the target.

Result

A high-quality cabbage trunk detection dataset was completed with accurate bounding box annotations. The dataset was prepared for training a computer vision model capable of detecting cabbage trunks automatically in agricultural images.

Final deliverable

Accurate bounding box annotations for cabbage trunks were delivered with consistent labelling and annotation quality maintained throughout the dataset. The final output met the project requirements and was ready for AI model training and development.