References

Tools and Frameworks

1. LabelImg

   • An open-source graphical image annotation tool used for annotating the extracted frames.

   • GitHub Repository: https://github.com/tzutalin/labelImg

2. TensorFlow and TensorFlow Lite

   • TensorFlow was used for building and training the object detection model. TensorFlow Lite enabled the model's deployment for real-time detection and counting.

   • TensorFlow Official Website: https://www.tensorflow.org/

3. OpenCV

   • OpenCV was used extensively for extracting video frames and preprocessing image data.

   • Documentation: https://opencv.org/

4. Google Colab and Google Colab Pro

   • Google Colab and its premium version were used for training the model, leveraging GPU resources for faster computation.

   • Website: https://colab.research.google.com/

5. Python Programming Language

   • Python served as the core programming language due to its rich libraries for machine learning, computer vision, and data manipulation.

   • Python Official Website: https://www.python.org/

6. Pandas Library

   • Used for data analysis and manipulation, especially for exporting rabbit counts to CSV files.

   • Documentation: https://pandas.pydata.org/

7. NumPy Library

   • Utilized for handling numerical operations and managing image data as arrays.

   • Documentation: https://numpy.org/

---

Research Papers and Algorithms

1. YOLO (You Only Look Once) Algorithm

   • Although not directly implemented, the principles of YOLOv5 were referenced during the project's initial phases for understanding object detection techniques.

   • Reference: Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

   • Website: https://pjreddie.com/darknet/yolo/

2. ImageNet Classification

   • Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems (NIPS).

   • Provided foundational knowledge for deep learning-based object detection.

3. EfficientNet

   • Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Explored during transfer learning and model scaling.

   • Paper: https://arxiv.org/abs/1905.11946

4. Faster R-CNN

   • Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Used as a reference for understanding small object detection techniques.

   • Paper: https://arxiv.org/abs/1506.01497

---

Experimentation and Deployment Tools

1. Microsoft Azure

   • Used to create a virtual machine for building the Windows application in the absence of native Windows hardware.

   • Website: https://azure.microsoft.com/

2. Seafile

   • The university’s Seafile server facilitated handling large datasets of video footage, aiding in uploading and downloading terabytes of data.

   • Website: https://www.seafile.com/

---

Miscellaneous

1. YouTube

   • Various tutorials and troubleshooting videos were referenced throughout the project's development stages.

   • Website: https://www.youtube.com/