Animal Detection and Tracking from Video Feeds

Image Processing

Project Details

Project Information

Project Title: Animal Detection and Tracking from Video Feeds

Category: Image Processing

Semester: Fall 2025

Course: CS619

Complexity: Complex

Supervisor Details

Project Description

 

Animal Detection and Tracking from Video Feeds

 

Project Domain

Image Processing

 

Introduction

 

Livestock monitoring is an important task in smart farming. Detecting and tracking animals in real-time video feeds can help farmers monitor herd behavior, prevent theft, and improve farm management. This project aims to develop an automated system that uses YOLO (You Only Look Once) for cow detection and DeepSORT for real-time tracking of each animal across frames. The system will provide smooth tracking outputs (tracklets) and maintain consistent IDs for cows. As an advanced extension, students may also integrate the Segment Anything Model (SAM) to segment cows at the pixel level, showing how modern AI techniques can enhance precision.

 

Functional Requirements

 

         Video Input

 

        The system shall accept video file uploads in common formats (MP4, AVI, MOV).

 

        The system shall support real-time webcam input.

 

         Cow Detection & Tracking

 

        The system shall detect cows in video frames.

 

        The system shall assign persistent unique IDs to detected cows.

 

        The system shall maintain ID consistency when cows are temporarily occluded.

 

         Display bounding boxes and IDs

 

     The system shall display bounding boxes around detected cows.

 

     The system shall display unique IDs near each detected cow.

 

         Display of Detection and Tracking Information

 

        The system shall display detection information, including the number of detected cows and the average confidence score, during video processing.

 

        The system shall display tracking performance indicators, including temporary ID switch es and frame rate (FPS), during video processing.

 

5. User Interface

 

            The system shall provide a user interface that enables users to upload videos or access a webcam f or efficient detection and tracking operations.

 

         Advanced Feature (Optional)

 

            The system shall generate pixel-level segmentation masks for detected cows.

 

 

 

 

Tools & Technologies

 

            Programming Language: Python

 

 

 

Page 25 of 167

 

            Libraries: Ultralytics YOLOv8, DeepSORT, OpenCV, NumPy, Matplotlib

 

            Optional (Bonus): Segment Anything Model (SAM)

            IDE: Spyder

 

            Dataset: Public cow dataset (e.g., MultiCamCows2024)

 

            Hardware:

            CPU system for training small YOLO models (slow).

 

            GPU (local or online, e.g., Google Colab/Kaggle) recommended for faster training and real-time inference.

 

            A working system that detects and tracks multiple cows in real time.

            Visualization of bounding boxes and unique IDs on each cow.

 

            (Bonus - Optional) Pixel-level segmentation of cows using SAM.

 

Supervisor:

 

Name: Noor Rahman

Email ID: noor.rahman@vu.edu.pk

 

MS Teams ID: mahsud-cs619@outlook.com

Languages

  • Python Language

Tools

  • Ultralytics YOLOv8, DeepSORT, OpenCV, NumPy, Matplotlib, Optional (Bonus): Segment Anything Model (SAM), IDE: Spyder, Dataset: Public cow dataset (e.g., MultiCamCows2024), Hardware: CPU system for training small YOLO models (slow) Tool

Project Schedules

No schedules available for this project.

Viva Review Submission

Review Information
Supervisor Behavior

Student Viva Reviews

No reviews available for this project.