Indore Dharmesh Tree Detection

Project overview

Outdoor and agricultural images from the Indore Dharmesh area were annotated for a computer vision dataset focused on detecting trees. Visible trees were identified and accurate annotations created to generate high-quality training data for an AI-based object detection model.

The main objective was to prepare a reliable dataset for automatically detecting trees in real-world outdoor environments.

Work performed

• Reviewed and organised the image dataset before annotation.
• Visible trees were identified in each image.
• Accurate bounding boxes were created around individual trees.
• Labelling remained consistent throughout using the Tree class.
• Partially visible trees were annotated where applicable.
• Trees were carefully distinguished from surrounding vegetation and other objects.
• Varying tree sizes, distances and viewing angles were handled throughout.
• Quality checks were performed, and inaccurate or incomplete annotations were corrected.
• Annotations were confirmed consistent and suitable for object detection model training.

What made it hard

• Detecting trees at different distances and sizes.
• Partially visible or occluded trees had to be annotated accurately.
• Overlapping tree canopies made individual trees difficult to isolate.
• Trees whose branches or foliage were closely connected were hard to separate.
• Complex backgrounds contained buildings, roads, crops and other vegetation.
• Varying lighting conditions and camera angles affected tree visibility.
• Accurate bounding boxes around irregular tree shapes had to be maintained.

Result

A high-quality tree detection dataset was completed with accurate and consistent bounding box annotations. The dataset was prepared for training a computer vision model capable of automatically detecting trees in real-world outdoor environments.

Final deliverable

Accurate and consistent bounding box annotations for the Tree class were delivered throughout the dataset. The final output was prepared according to project requirements and was ready for AI model training and automated tree detection applications.