Designs of a customized active 3D scanning system for food processing applications

Commercialized RGB-D and LiDAR cameras have been widely applied in food and agricultural engineering fields. However, the general-use 3D cameras cannot ensure high resolution 3D imaging because of their imaging principles. The accuracy of their generated height map ranges from 1cm – 10cm in the actual measurements, which cannot meet the requirement of accurate object height estimation in the food processing lines, especially for visualizing sub-centimeter food product shape variations. This research customized an active 3D scanning system, which utilized the line scanning method to ensure the scanning speed compared to the dot scanning and to minimize the cross talk in the frame scanning. Different from some industrial level 3D line scanning cameras, the system avoided synchronizing the imaging acquisition and processing line conveyor movement. Instead, to implement the 3D imaging for a static object, a programmable rotational mirror was integrated in the system to reflect the line laser for covering the scanning of the entire field of view. In our experimental setup, for a 5-cm calibration phantom, the standard derivation of height estimation from the system is 0.15mm in a 1m photographic distance, which is superior to commercialized RGB-D cameras including Intel RealSense and Kinect. The customized system can also automatically generate well-registered color and depth image pairs and its idea can easily fit into different food and agricultural applications.