Wild Animal Detection

Project overview

Wildlife images were annotated for a computer vision dataset focused on detecting wild animals in natural and outdoor environments. The work involved identifying visible animals and creating accurate annotations to generate high-quality training data for an AI-based object detection model.

The main objective was to prepare a reliable dataset capable of helping an AI model automatically detect animals in real-world wildlife environments.

Work performed

• Reviewed and organised the wildlife image dataset before annotation.
• Identified visible animals in each image.
• Created accurate bounding boxes around individual animals.
• Labelling was kept consistent under the Animal class.
• Partially visible animals were annotated where applicable.
• Animals were carefully distinguished from vegetation, rocks, shadows and other background objects.
• Handled animals appearing at different distances, sizes and viewing angles.
• Performed quality checks and corrected inaccurate, missing or poorly positioned annotations.
• Ensured the annotations were consistent and suitable for object detection model training.

What made it hard

• Detecting animals within dense natural environments.
• Identifying small or distant animals inside an image.
• Handling animals partly hidden behind vegetation or other objects.
• Separating animals from background elements such as rocks, trees and shadows.
• Varied animal poses and orientations complicated bounding box placement.
• Lighting conditions and image quality affected how visible each animal was.
• Keeping bounding boxes tight and accurate around animals demanded careful attention to detail.

Result

A high-quality wild animal dataset was completed with accurate and consistent bounding box annotations for the Animal class. The dataset was prepared for training a computer vision model capable of automatically detecting wild animals in natural environments.

Final deliverable

Accurate and consistent bounding box annotations for the Animal class were delivered across the dataset. The final output was prepared to the project requirements and was ready for AI model training and automated wildlife monitoring and animal detection applications.