Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


case1274975598.pdf (1.35 MB)

ETD Abstract Container

Abstract Header

Identification & Segmentation of Lawn Grass Based on Color & Visual Texture Classifiers

Schepelmann, Alexander
http://rave.ohiolink.edu/etdc/view?acc_num=case1274975598

Abstract Details

2010, Master of Sciences (Engineering), Case Western Reserve University, EMC - Mechanical Engineering.
CWRU Cutter is an autonomous lawnmower which can reflexively avoid obstacles. While LIDAR was previously used by the robot to determine obstacle locations, the sensor’s price makes its inclusion in commercial versions prohibitively expensive. Cameras can provide similar information at drastically reduced cost, but useful information must first be extracted from incoming images. This can be computationally expensive. Additionally, vision-based methods can be highly sensitive to changing lighting conditions. This thesis presents a method to identify grass based on color and visual texture classifiers for use in an outdoor environment. Neighborhood-based color measurements are calculated using the HSL color model and texture measurements are based on edge-detection and quantified via computationally inexpensive first and second order statistics. Individual measurements are then combined to create a binary representation of mowable terrain in an image. Performance is quantified by measuring recognition performance on a set of sample neighborhoods that contains common backyard obstacles.
Roger D. Quinn, PhD (Committee Chair)
Francis Merat, PhD (Committee Member)
Michael S. Branicky, ScD (Committee Member)
79 p.
Computer Science; Engineering; Mechanical Engineering; Robots
Computer vision; texture; grass identification; autonomous vehicles; autonomous lawnmower; robotics

Recommended Citations

Citations

  • Schepelmann, A. (2010). Identification & Segmentation of Lawn Grass Based on Color & Visual Texture Classifiers [Master's thesis, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1274975598

    APA Style (7th edition)

  • Schepelmann, Alexander. Identification & Segmentation of Lawn Grass Based on Color & Visual Texture Classifiers. 2010. Case Western Reserve University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=case1274975598.

    MLA Style (8th edition)

  • Schepelmann, Alexander. "Identification & Segmentation of Lawn Grass Based on Color & Visual Texture Classifiers." Master's thesis, Case Western Reserve University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=case1274975598

    Chicago Manual of Style (17th edition)

case1274975598
3,861
© 2010, all rights reserved.
This open access ETD is published by Case Western Reserve University School of Graduate Studies and OhioLINK.