Determination of Maize Seed Purity Based on Multi-Step Clustering

2018 ◽  
Vol 34 (4) ◽  
pp. 659-665
Author(s):  
Shuangxi Liu ◽  
Hongjian Zhang ◽  
Zhen Wang ◽  
Chunqing Zhang ◽  
Yan Li ◽  
...  
Keyword(s):  
Binocular Vision ◽  
Vision System ◽  
Recognition Rate ◽  
Model Parameters ◽  
Experimental Sample ◽  
Maize Seed ◽  
Maize Seeds ◽  
Clustering Model ◽  
Binocular Vision System

Abstract. Electrophoresis has been widely used to determine maize seed purity; however, the associated time and complexity hinder its application for maize seeds. Equipment to estimate seed purity was designed to improve the efficiency of identification of circulating maize seeds, and a multi-step clustering method was created for the determination of seed purity. The main components included a host computer, a black box, a seed transmission belt with grooves, a binocular vision system, and an under-controller. First, image information of the crown and the non-embryo side of every maize seed was collected using the binocular vision system while seeds underwent intermittent movement on the transmission belt. Second, multi-area color characteristics, which included red, green, and blue (RGB), hue, saturation, intensity (HSI), and lightness-a-b (Lab) color model parameters of maize seeds were extracted and optimized to generate 25-dimensional purity identification vectors. Finally, a multi-step clustering model was used to determine seed purity. The original center of K-mean clustering was established based on the results of self-organizing map (SOM) clustering; subsequently, maize seed purity parameters were obtained by combining the results of the second and the first clustering analyses. A result was achieved by testing three groups of samples, including 'ZHENGDAN 958' mixed with 'XIANYU 335', 'XIANYU 335' mixed with its male parent, and 'XIANYU 335' mixed with its female parent. The result showed that the correct recognition rate of 'XIANYU 335' mixed with 'ZHENGDAN 958' that had no genetic relationship could reach 100% under the condition of the experimental sample, and the accuracy of identification between 'XIANYU 335' and their respective male and female parents was 96.7% and 88.7%. This recognition rate met with the technical requirements of field inspection and provided a reliable scientific basis for the rapid determination of maize seed purity. Keywords: Identification, Maize seed, Multi-step clustering, Purity, Rapid.

Binocular vision-based 3-D trajectory following for autonomous robotic manipulation

Robotica ◽  
2007 ◽  
Vol 25 (5) ◽  
pp. 615-626 ◽  
Author(s):  
Wen-Chung Chang
Keyword(s):  
Binocular Vision ◽  
Visual Servoing ◽  
Vision System ◽  
A Priori ◽  
Robotic Manipulator ◽  
Robotic Manipulation ◽  
Control Approach ◽  
Trajectory Following ◽  
Image Planes ◽  
Binocular Vision System

SUMMARYRobotic manipulators that have interacted with uncalibrated environments typically have limited positioning and tracking capabilities, if control tasks cannot be appropriately encoded using available features in the environments. Specifically, to perform 3-D trajectory following operations employing binocular vision, it seems necessary to have a priori knowledge on pointwise correspondence information between two image planes. However, such an assumption cannot be made for any smooth 3-D trajectories. This paper describes how one might enhance autonomous robotic manipulation for 3-D trajectory following tasks using eye-to-hand binocular visual servoing. Based on a novel encoded error, an image-based feedback control law is proposed without assuming pointwise binocular correspondence information. The proposed control approach can guarantee task precision by employing only an approximately calibrated binocular vision system. The goal of the autonomous task is to drive a tool mounted on the end-effector of the robotic manipulator to follow a visually determined smooth 3-D target trajectory in desired speed with precision. The proposed control architecture is suitable for applications that require precise 3-D positioning and tracking in unknown environments. Our approach is successfully validated in a real task environment by performing experiments with an industrial robotic manipulator.

scholarly journals Precise calibration of binocular vision system used for vision measurement

2014 ◽  
Vol 22 (8) ◽  
pp. 9134 ◽  
Author(s):  
Yi Cui ◽  
Fuqiang Zhou ◽  
Yexin Wang ◽  
Liu Liu ◽  
He Gao
Keyword(s):  
Binocular Vision ◽  
Vision System ◽  
Vision Measurement ◽  
Binocular Vision System
Sign in / Sign up

Export Citation Format

Share Document