Article
Automatic Non-Destructive Growth Measurement of
Leafy Vegetables Based on Kinect
Yang Hu
1
, Le Wang
1
, Lirong Xiang
1
, Qian Wu
1
and Huanyu Jiang
1,2,
*
1
College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road,
Hangzhou 310058, China; yhu@zju.edu.cn (Y.H.); wangle5994@zju.edu.cn (L.W.); lrxiang@zju.edu.cn (L.X.);
wuqianhz@zju.edu.cn (Q.W.)
2
Key Laboratory of On Site Processing Equipment for Agricultural Products, Ministry of Agriculture,
Beijing 100125, China
* Correspondence: hyjiang@zju.edu.cn; Tel.: +86-571-8898-2140
Received: 29 January 2018; Accepted: 5 March 2018; Published: 7 March 2018
Abstract:
Non-destructive plant growth measurement is essential for plant growth and health
research. As a 3D sensor, Kinect v2 has huge potentials in agriculture applications, benefited from
its low price and strong robustness. The paper proposes a Kinect-based automatic system for
non-destructive growth measurement of leafy vegetables. The system used a turntable to acquire
multi-view point clouds of the measured plant. Then a series of suitable algorithms were applied to
obtain a fine 3D reconstruction for the plant, while measuring the key growth parameters including
relative/absolute height, total/projected leaf area and volume. In experiment, 63 pots of lettuce
in different growth stages were measured. The result shows that the Kinect-measured height and
projected area have fine linear relationship with reference measurements. While the measured total
area and volume both follow power law distributions with reference data. All these data have shown
good fitting goodness (R
2
= 0.9457–0.9914). In the study of biomass correlations, the Kinect-measured
volume was found to have a good power law relationship (R
2
= 0.9281) with fresh weight. In addition,
the system practicality was validated by performance and robustness analysis.
Keywords: plant growth measurement; Kinect v2; non-destructive; point cloud; 3D reconstruction
1. Introduction
Non-destructive plant growth measurement is the basis for many fields which focus on plant
growth and health research, including phenotyping and breeding, crop production forecast, fertilizer
and water management and other related applications. Height, leaf area, volume and biomass [
1
]
are the major growth parameters of commonly researched plants, especially for leafy vegetables.
Manual measurement for these parameters can be time-consuming and labor-intensive, thus the study
of automatic and non-destructive measurement technology is important and necessary. For many
years, a lot of studies have been carried out focusing on this issue, with different devices and methods.
With the development of sensors and computer technology, three-dimensional (3D) information
was involved to achieve better measuring accuracy and more detailed spatial morphology of plant.
Stereo vision is one of the most commonly used techniques for plant growth measurement [
2
–
6
].
The method usually has fine resolution and good measuring speed but its accuracy could not be so
reliable since it is sensitive to the texture of measured object. Structured light is another technique to
acquire 3D information and it has been successfully used in high-accurate plant growth monitoring [
7
]
and other related studies [
8
–
10
], but the equipment is either complicated or expensive, which could
limit its application. Time-of-flight (ToF) cameras were also introduced by some studies for 3D
plant measurement [
11
–
14
]. High measuring speed and strong robustness are the advantages of
these devices, whereas the major weakness is the existing high noise among 3D data. In addition,
Sensors 2018, 18, 806; doi:10.3390/s18030806 www.mdpi.com/journal/sensors
