Corn plant sensing using real‐time stereo vision

Abstract

Though some two-dimensional (2D) machine vision-based systems for early-growthstage corn plant sensing exist, some of their shortcomings are difficult to overcome. The greatest challenge comes from separating individual corn plants with overlapped plant canopies. With 2D machine vision, variation in outdoor lighting conditions and weeds in the background also pose difficulties in corn plant identification. Adding the depth dimension has the potential to improve the performance of such a sensing system. A new corn plant sensing system using a real-time stereo vision system was investigated in this research. Top-view depth images of corn plant canopy were acquired. By processing the depth images, the algorithm effectively updated the plant skeleton structures and finally recognized individual corn plants and detected their center positions. The stereo vision system was tested over corn plants of V2-V3 growth stages in both laboratory and field conditions. Experimental results showed that the stereo vision system was capable of detecting both separated and overlapped corn plants. During the field test, 96.7% of the corn plants were correctly detected, and plant center positions were estimated with maximum distance errors of 5 and 1 cm for 74.6% and 62.3% of detections, respectively. C 2009 Wiley Periodicals, Inc.

Leaf segmentation in plant phenotyping: a collation study

“…Several authors have dealt with the segmentation of a live plant from background to measure growth using unsupervised [17,25] and semi-supervised methods [36], but not of individual leaves. The use of color in combination with depth images or multiple images for supervised or unsupervised plant segmentation is also common practice [4,10,29,46,49,51,52,57].…”

Plant Localization and Discrimination using 2D+3D Computer Vision for Robotic Intra-row Weed Control

“…In several studies (J. Li, 2014;Jin & Tang, 2009;Nakarmi & Tang, 2012), 3D sensors were applied in agricultural applications which provided a good performance. The advantages of 3D sensors for plant discrimination and localization are obvious: 3D sensors can provide fundamental depth information, making it is much easier to obtain the 3D structural and morphological data of the plants.…”

Plant Recognition through the Fusion of 2D and 3D Images for Robotic Weeding

“…Here, 3D sensors promise to give the required information to perform plant discrimination, selflocalization, mapping, etc. It is becoming popular to apply 3D computer vision in agriculture applications like (Li J. , 2014), (Jin & Tang, 2009) and (Nakarmi & Tang, 2012). The advantages of 3D sensors for plant discrimination and localization are obvious: It is much easier to get the 3D structural and morphological data of the plants.…”

“…In the work of (Jin & Tang, 2009), a real-time corn sensing system was developed using stereo vision. However, due to their passive operation mode, it is hard for both to provide reliable data for accurate sensing.…”

“…As a result, plant morphology and structural based features are utilized in our research. Plant structural based feature classification is suitable for plants like corns (Jin & Tang, 2009), as a reason of the obvious tree-shape. However, it is not commonly used, because the features need to be extracted from a relative comprehensive 3D model.…”