東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back to Search results for [ null ]

Switch To: Labeled | MARC Mode | ISBD

An intelligent computer vision contr...

Lee, Min-Fan.

Linked to FindBook

Google Book

Amazon

博客來

An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot./
Author:	Lee, Min-Fan.
Description:	239 p.
Notes:	Source: Dissertation Abstracts International, Volume: 57-01, Section: B, page: 4880.
Contained By:	Dissertation Abstracts International57-01B.
Subject:	Engineering, Agricultural. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9613088

An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot.
Lee, Min-Fan.

An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot. - 239 p.

Source: Dissertation Abstracts International, Volume: 57-01, Section: B, page: 4880.

Thesis (Ph.D.)--Cornell University, 1996.

The performance of a grapevine pruning robot module was improved by adding a target tracking system which contains an altitude estimation process and compensation law. The grapevine pruning robot module's performance was measured under simulated field conditions.Subjects--Topical Terms:

1019504
Engineering, Agricultural.

An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot.
LDR:03330nam a2200325 4500 001 1968594
005 20141203122306.5
008 150210s1996 ||||||||||||||||| ||eng d
035 $a (MiAaPQ)AAI9613088
035 $a AAI9613088
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lee, Min-Fan. $3 2105775
245 1 3 $a An intelligent computer vision control and target tracking system design of an agricultural grapevine pruning robot.
300 $a 239 p.
500 $a Source: Dissertation Abstracts International, Volume: 57-01, Section: B, page: 4880.
502 $a Thesis (Ph.D.)--Cornell University, 1996.
520 $a The performance of a grapevine pruning robot module was improved by adding a target tracking system which contains an altitude estimation process and compensation law. The grapevine pruning robot module's performance was measured under simulated field conditions.
520 $a The design and construction of a motion simulator, the design of an electrohydraulic servo system to power the simulator, and the design of a digital fuzzy logic controller to control the simulator are presented. The purpose of the simulator is to duplicate the response of a carrier supporting a grapevine pruning robot module traveling along uneven vineyard terrain. The grapevine pruning robot is automatically positioned by finding the location of the vine's cordon (Gunkel and Throop, 1992).
520 $a The simulator offers four degrees-of-freedom, two rotational and two translational. The two rotational motions allow simulation of pitch and yaw of the carrier while the two translation motions simulate the movement of the carrier vertically up and down. The fuzzy logic controller allows computer control of the simulator's motion. This enables actual field data measurements of vineyard terrain roughness and slope to be programmed and duplicated by the simulator.
520 $a Node counting is an important step needed for the determination of pruning severity. Therefore a mathematical morphological detection algorithm was designed to determine the location and number of nodes. The advantage and disadvantage of using mathematical morphology will also be discussed. The main purpose of the approach is to enable the current block-pruning type robotic grapevine pruner to selectively-prune.
520 $a A pattern recognition algorithm is developed to update the block-pruning type grapevine pruner to selective-pruning type grapevine pruner. Two mathematical grayscale morphological operations were successfully implemented, open and close, to achieve the goal. All the images were preprocessed to be smoothed out. Two disk elements with radius 4 and radius 3 were used for the node finding and eight line structure elements with 0$\sp\circ$, 27$\sp\circ$, 45$\sp\circ$, 63$\sp\circ$, 90$\sp\circ$, 117$\sp\circ$, 135$\sp\circ$ and 153$\sp\circ$ were used for branch extraction. The rectangular structure element with width 20 and length 30 was used for post extraction. The pixel value of all the structure elements were uniformly set as 3.
590 $a School code: 0058.
650 4 $a Engineering, Agricultural. $3 1019504
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Artificial Intelligence. $3 769149
690 $a 0539
690 $a 0548
690 $a 0544
690 $a 0800
710 2 $a Cornell University. $3 530586
773 0 $t Dissertation Abstracts International $g 57-01B.
790 $a 0058
791 $a Ph.D.
792 $a 1996
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9613088