Thistle & Johnsongrass Detection

Project overview

Agricultural images were annotated for a computer vision dataset focused on detecting thistle and johnsongrass weeds growing within corn fields. Target weeds were identified and accurate annotations created to generate high-quality training data for an AI-based object detection model.

Work performed

• Reviewed and organised the agricultural image dataset before annotation.
• Identified visible thistle and johnsongrass plants among the corn crops.
• Created accurate bounding boxes around each target weed.
• Maintained consistent labelling using the Thistle and Johnsongrass classes.
• Partially visible weeds were annotated wherever applicable.
• Distinguished target weeds carefully from corn plants and surrounding vegetation.
• Carried out quality checks to find and correct inaccurate, missing or poorly positioned annotations.
• Ensured the annotations suited training an object detection model.

What made it hard

• Distinguishing thistle and johnsongrass from corn plants and other surrounding vegetation.
• Small or partially visible weeds were easy to miss.
• Weeds overlapped or hidden by corn leaves were difficult to annotate.
• Dense agricultural environments produced complex backgrounds.
• Keeping bounding boxes accurate around irregularly shaped plants.
• Growth stages, lighting conditions and image quality varied across the dataset.

Result

A high-quality agricultural weed detection dataset was completed with accurate bounding box annotations for thistle and johnsongrass. The dataset was prepared for training a computer vision model capable of automatically detecting these weeds in corn fields.

Final deliverable

Delivered accurate and consistent bounding box annotations for thistle and johnsongrass throughout the dataset. The final annotations matched the project requirements and were ready for AI model training and agricultural weed detection applications.