Development of the algorithms and mechanism of a machine vision system for both summer and in-season weed mapping in broad acre no-till cropping lands /

Date

2014

Authors

Liu, Huajian,

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

thesis

Citation

Statement of Responsibility

Conference Name

Abstract

Weeds are among the most significant and costly agricultural threats in Australia especially for no-till cropping areas. More than half of the Australian cropping land is no-till. Weed control within continuous no-till cropping areas is becoming more difficult because herbicide treatment is the predominant weed control method in these areas. The weed populations have been found to be distributed heterogeneously in time and space within agricultural fields. However the commonly used weed control method in Australia is to uniformly spray the same type of herbicide regardless the spatial population of weeds. As a result, some prolific weeds are becoming more resistant to the regular herbicides used and therefore more powerful and more expensive options are being applied with increased application rates. Those weed control methods of using more powerful and heavier dose herbicide application have many negative effects including waste of herbicide, damage to the environment and increasing the threat of food safety.

School/Discipline

University of South Australia. School of Engineering.
School of Engineering.

Dissertation Note

Thesis (Masters by research(Mechanical and Manufacturing Engineering))--University of South Australia, 2014.

Provenance

Copyright 2014 Huajian Liu. This work is made available under the Creative Commons Attribution-NonCommercial-NoDerivs Australia 3.0 licence.

Description

1 ethesis (xiii, 193 leaves) :
illustrations (some colour), colour maps.
Includes bibliographical references (leaves 123-133)

Access Status

506 0#$fstar $2Unrestricted online access

Rights

License

Grant ID

Published Version

Call number

Persistent link to this record