Image Based Tracking using FPGA

Project Title

Image Based Tracking using FPGA

Project Area of Specialization Artificial IntelligenceProject Summary

In this project we are using Image Processing algorithms for the purpose of Object Recognition and
tracking and implement the same using python. Object tracking can be performed on GPU by python  and later
can be transferred to FPGA for real time implementation. In today’s world most sensing applications
require some form of digital signal processing and these are implemented primarily on serial processors.
While the required output is achievable, it can be beneficial to take advantage of the parallelism, low
cost, and low power consumption offered by Field Programmable Gate arrays. Object detection is an
important technique in the area of image processing with wide applications. Object tracking is the
process of locating a moving object in real time using a camera. The algorithm analyses the video frames
and outputs the location of moving targets within the video frame. In order to perform this complex
embedded video processing on-chip, FPGA-based system is desirable due to the potential parallelism of
the algorithm. Basically A real-time and accurate method for detecting object and tracking will be achieved.

Project Objectives

• Controlling camera’s position using CSI connection so that the tracked object is positioned in the center of each video frame.
• Implementation of Mean shift tracking algorithm in FPGA.
• Sending requests from  Zybo Z7 to  camera..
• Connecting FPGA with processing system

Project Implementation Method

• Design Algorithms on python,
• Testing on MATLAB, 
• Final Testing on HLS Vivado

There are two major methods of implementation  of image base tracking using FPGA that we have adopted in this project which are: 

1- Target Identification and localization (Mean Shift tracking and skin color tracking algorithms(optional)

2- Filtering and data association (Particle filter and Kalman filter (optional))

Benefits of the Project

This project is

• Benificial for Security e.g Tracking vehicles and people in video surveillance systems,,
• Autonomous vehicles e.g park assist, road signs and pedestrians tracking,
• Military e.g  scout drones, aim assist.
• Real time object detection and tracking using sequences of image processing algorithms which is helpful for applications that need real time response.

Technical Details of Final Deliverable

Turret with camera & FPGA processing unit.

•  Monitoring using camera, It will be the input source.

• Background subtraction, image filtering, object detection

• Recognizing object of interest.

• Real Time Tracking of object  and hitting the object.

Final Deliverable of the Project HW/SW integrated systemCore Industry SecurityOther IndustriesCore Technology Artificial Intelligence(AI)Other Technologies RoboticsSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	56870
zybo z7 -20	Equipment	1	34870	34870
V2 8 megapixel	Equipment	1	4900	4900
geared DC Motor	Equipment	4	1900	7600
wooden structure	Equipment	1	4100	4100
Printing Book	Miscellaneous	1	3000	3000
Stationary	Miscellaneous	1	1000	1000
Wires	Equipment	60	10	600
Aurdino Uno	Equipment	1	800	800