From Gaming to High Throughput Phenotyping: Use of an X-Box Camera to Model Soybean 3D Structure and Morphological Traits.

High throughput phenotyping in agriculture has drawn increasing interest in recent years to alleviate the phenotyping bottleneck of many breeding programs around the world. A number of different types of sensing devices, including ultrasonic sensors and light detection and ranging scanner (LIDAR), have been deployed in high throughput phenotyping to measure plant height, stand density, leaf area and canopy structure. However, the information obtained from ultrasonic sensors is limited, and the high prices of LIDAR systems are prohibitive for many programs. This study explores the low-cost X-Box gaming platform, Kinect sensor, as a novel tool for plant phenotyping. The advantage of the Kinect sensor is the ability to capture RGB and depth images that can be converted to point cloud images, which are further processed and combined to form a single and complete 3D model of the plant. In turn, 3D models can used to extract a range of information on plant and canopy architecture, such as plant height, leaf area, canopy coverage, and aboveground plant biomass, providing valuable information to accelerate the breeding process.