Autonomous Parking System

1
Autonomous Parking System

• ECE 345 Senior Design Project
• Project 24
• Prof. Swenson
• TA Han Seok Kim

Johnson Liu Fumie Saito Xiaozhou Zhu
2
Pioneer 2
This robot is used in our experiment. It comes
from a lot of features. Using Visual C, we are
able to take pictures and control movement of the
robot.
3
Agenda

• Introduction and Relevence
• Hardware
• Image Processing
• Planar Homography Algorithm
• Robot Motion
• Error Analysis / Improvements
• Questions

4
What We Are Doing?

• Use GPS to guide the robot to the vicinity of the
  parking space.
• Use vision based control (image processing) to
  detect the parking sign.
• Use planar homography algorithm to maneuver the
  robot into the parking space.

5
Why Is This Important?

• Assists people with disabilities to guide their
  vehicles.
• Allows robot to autonomously explore
  bio-hazardous environments.

6
GPS

• GPS is a satellite based navigation.
• Without any other device, it produces about 15
  meters error.
• In our project, GPS is used to guide the robot to
  the unknown parking space.
• Garmin 12XL is chosen because it has a serial
  port and is easy to connect to DGPS.

7
NMEA(National Marine Electronics Association)

• It is used in world wide.
• Defines electrical signal requirements, data
  transmission protocol and time, and specific
  sentence formats.
• Use a 4800 baud serial data bus.
• We used following sentences.
• GPGGA(Global Positioning System Fix Data)
• PGRME(Garmin Estimated Error Information
  non-standard)

8
Example Sentence of GPGGA

• GPGGA,042246,4006.708,N,08813.869,W
• GPGGA Global Positioning System Fixed Data
• 042246 Global Time
• 4006.708 N North Latitude
• 08813.869 W West Longitude

9
Example Sentence of PGRME

• PGRME,6.4,M,14.2,M,6.4,M,
• PGRME Garmin Estimated Error Information
  non-standard
• 6.4,M Estimated horizontal position error (m)
  
• 14.2,M Estimated vertical position error (m)
• 6.4,M Estimated position error (m)

10
Longitude and Latitude From GPS
11
Estimated Error From GPS
12
DGPS

• DGPS, Differential Global Positioning System,
  improves the accuracy of the GPS system.
• DGPS is able to increase the accuracy by using a
  GPS receiver at a known location.
• In our experiment, we used the DGPS to guide the
  robot to the vicinity of the parking space.
• GBR23 is the one we used in our experiment.

13
Longitude and Latitude With DGPS
14
Estimated Error With DGPS
15
Switch Circuit

• GPS only has one input and one output. So, we
  have to divide signal in two ways, GPS to DGPS
• We used 555 Timer IC and 4 to 1 MUX to build a
  switch Circuit.

16
Schematic of Switch Circuit
17
Signal between GPS and PC
18
Image ProcessingGoals

• Isolate the parking pattern.

19
Image ProcessingGoals

• Find 4 corners on the parking pattern needed to
  compute R and T matrices.

20
Image Processing--Stages

• Monochrome Filter
• Median Filter
• Group Pixels
• Find Largest Group
• Find Corners

21
Image ProcessingMonochrome Filter

• Keeps only the pixels in the capture image with
  Rlt 25, Glt 25, and B lt 25 (black pixels).

Before
After
22
Image ProcessingMonochrome Filter

• Advantage
• Isolate the desired pattern from (most)
  background object.
• Disadvantage
• Cannot filter out all undesired background
  objects.

23
Image ProcessingMedian Filter

• Reduce some noise in the image.

Before
After
24
Image ProcessingMedian Filter

• Advantage
• Reduces noiseincreases signal to noise ratio.
• Disadvantage
• Decreases resolution.

25
Image ProcessingGroup Pixels

• Recognizes adjacent pixels as objects.

Before
After
26
Image ProcessingGroup Pixels

• Advantage
• Recognizes objects in the image.
• Disadvantage
• Cannot distinguish two overlapping objects.

27
Image ProcessingFind Largest Object

• Keeps the largest object groupedThe largest
  object should be the parking pattern.

Before
After
28
Image ProcessingFind Corners

• Find the coordinates of the 4 corners by applying
  a mask.
• (needed to compute R and T matrices).

29
Image ProcessingFind Corners

• Corner pixels overlap with mask by 1 pixel.

30
Image ProcessingFind Corners

• Internal pixels overlap with mask by more than 1
  pixel.

31
Image ProcessingFind Corners

• Limitations
• The image must have solid interior.

32
Image ProcessingExample 1
33
Image ProcessingExample 2
34
Planar HomographyCoordinate Transformation
35
Planar HomographyFinding Transformation Matrix H

• Transformation From One Coordinate System to
  Another Satisfies the Equation
• Simple Substitution Using Results in
• or
• Where R rotational transformation
• Where T translational transformation
• Where N Normal vector to the image plane

36
Planar HomographyFinding Transformation Matrix H

• Multiplying the equation by the skew-symmetric
  matrix (cross-product) will result in the
  familiar linear algebra form of
• Mathematical manipulations using the Kronecker
  product will result in
• Where
• And is the stacked H matrix
• This is identical to

37
Planar HomographyFinding Transformation Matrix H

• To find a unique solution to H, 4 Point
  Homography must be used, thus
• Where
• Where
• Solving the Null Space of will get

38
Planar HomographyFinding R and T

• Once we have the correct , we can use
  Singular Value Decomposition (SVD) to decompose
  into the R and T matrices.
• There are 4 solutions to R and T matrices
  eliminate based on positive depth constraint
• Using the general equations of R and T to solve
  for the angle( )between the two coordinate
  planes and the distance( L) between the robot and
  object.

39
Robot Motion
40
Robot Motion

• To prevent the robot from crashing into the
  parking sign, the robot is stopped when the image
  covers a certain fraction of the total camera
  screen.

41
Errors

• Accuracy is a must in vision. A few pixels off in
  one direction or another will result in error.
  For this reason, high resolution cameras are
  needed. (320243 pixels)
• 2 frames of reference are needed for this
  project. More frames more sources of error
• Symmetry and 3D reconstruction will only use 1
  frame, which eliminates error.

42
Improvements

• We were not able to connect the GPS to the serial
  port on the robot.
• The robot cannot locate and move to its parking
  space.
• We cannot command the robot to rotate or
  translate at constant velocities.

43
Cost Analysis
44
Questions?