An Automatic Vision-Based Plant Growth Measurement System for Leafy Vegetables

The measurement of plant features is a fundamental element of plant science research and related applications. The information related to plant features is especially useful for its applications in plant growth modelling and climate control in greenhouses or plant factory. Many methods have been applied in plant growth measurement. Traditional direct measurement methods are generally simple and reliable, but they are also time consuming and laborious. In contrast, vision-based methods are non-destructive and efficient methods to describe exterior plant features and plant growth. In this research, a stereo vision system which is composed of two off-the-shelf cameras with parallel optical axes was integrated with an image processing algorithm developed to monitor plant growth of Boston lettuce in a plant factory. The stereo vision system was mounted on a sliding rail to extend the field of view of the planting beds. Images were continuously recorded by the system to be used to determine plant features and construct panoramic images. The image processing algorithms calculating geometric features such as projected leaf area, plant height, plant volume, and equivalent diameters were developed and incorporated with the automatic measurement platform. Subsequently, the plant growth curves were deduced from plant feature data calculated. Results showed a promising performance of this automatic vision-based system in practice.