This preview shows page 1-2-3-4-5-6-7-51-52-53-54-55-56-57-58-102-103-104-105-106-107-108 out of 108 pages.
Michigan State University ECE 480 Design Team 3 December 10, 2010 FPGA Implementation of Driver Assistance Camera Algorithms Final Report Fatoumata Dembele Chad Eckles Pascha Grant Tom Ganley Emmett Kuhn Jeff Olsen Project Sponsor Xilinx Sponsor Representatives Mr. Paul K. Zoratti & Mr. Kevin Klopfenstein Facilitator Dr. Ramakrishna MukkamalaExecutive Summary P a g e | 2 Executive Summary Passenger safety is the primary concern and focus of automobile manufacturers today. In addition to the passive safety equipment, including seatbelts and primary airbags, technology based active safety mechanisms are being incorporated more than ever and may be soon required by law. Current trends are suggesting that the government will require automobile manufacturers to include a multitude of technology based safety equipment including ultrasonic sensors and back-up cameras. Historically, back-up cameras in vehicles gave the driver an unaltered view from behind the vehicle; however, with the sponsorship of Xilinx, Michigan State University‟s ECE 480‟s Design Team 3 has designed and implemented an algorithm that is the first step to visually alerting the driver of objects seen in the back-up camera. This algorithm performs edge detection on a live video feed which is the basic building block necessary for further object detection. The team has also implemented a skin detection algorithm that can be used in conjunction with the edge detection to draw the driver‟s attention to possible human objects. In doing so, the driver will be less likely to overlook objects that may create a safety hazard. Implementation of the algorithm utilizes Xilinx‟s Spartan-3A Field Programmable Gate Array (FPGA) development board and video processing kit. Design Team 3 has established a concrete platform that future teams given this project will easily be able to build upon.Acknowledgement P a g e | 3 Acknowledgement Michigan State University‟s ECE 480 Design Team 3 would like to give a special thanks to those who helped contribute to the success of the driver assistance camera algorithm: Xilinx: Mr. Paul K. Zoratti, for his guidance of the design process Xilinx: Mr. Kevin Klopfenstein, for his willingness to go above and beyond his role Michigan State University, ECE Department: Dr. Ramakrishna Mukkamala, for his weekly advice and support of the project Michigan State University, ECE Technical Services: Mrs. Roxanne Peacock, for her assistance in part ordering Michigan State University, ECE Department: Mr. Michael Shanblatt, for his direction and his sharing of lifelong career skills Michigan State University, ECE Department: Dr. Anil K. Jain’s Research Group, for their advice on object detection implementationTable of Contents P a g e | 4 Table of Contents Chapter 1: Introduction and Background ........................................................................................ 6 1.1 Introduction .......................................................................................................................... 6 1.2 Background .......................................................................................................................... 7 Chapter 2: Exploring the Solution Space and Selecting a Specific Approach ............................. 10 2.1 Design Specifications......................................................................................................... 10 2.2 FAST Diagram ................................................................................................................... 11 2.3 Conceptual Design ............................................................................................................. 11 2.3.1 Sobel and Canny Edge Detection Methods ......................................................... 11 2.4 Feasibility and Decision Matrix ......................................................................................... 13 2.5 Proposed Design Solution .................................................................................................. 14 2.6 Gantt Chart ......................................................................................................................... 15 2.7 Budget ................................................................................................................................ 16 Chapter 3: Technical Description of Work Performed ................................................................. 18 3.1 Hardware Design ............................................................................................................... 18 3.2 Software Design ................................................................................................................. 38 3.2.1 Main Menu .......................................................................................................... 38 3.2.2 Edge Detection Menu .......................................................................................... 39 3.2.3 Object Detection Implementation ....................................................................... 42 3.2.4 Software Design .................................................................................................. 43 3.2.5 Software Implementation .................................................................................... 46 Chapter 4: Test Data with Proof of Functional Design................................................................. 49 4.1 Testing Edge Detection ...................................................................................................... 49 4.2 Testing Human Detection .................................................................................................. 54 4.3 Testing Object Detection ................................................................................................... 56 Chapter 5: Final Cost, Schedule, Summary and Conclusion ........................................................ 58 Appendix 1: Technical Roles, Responsibilities, and Work Accomplished .................................. 60 A1.1 Fatoumata Dembele - Webmaster .................................................................................. 60 A1.2 Chad Eckles – Lab Coordinator ..................................................................................... 61 A1.3 Pascha Grant – Documentation Preparation...................................................................
View Full Document
Unlocking...