Investigating the characteristics of fluorescence features on sweet peppers using UV light excitation

Sweet peppers are popular worldwide due to their nutrition and taste. Conventional vegetable tracing methods have been trialed, but the application of such labels or tags can be laborious and expensive, making their commercial application impractical. What is needed is a label-free method that can identify features unique to each individual fruit. Our research team has noted that sweet peppers have unique textural fluorescence features when observed under UV light that could potentially be used as a label-free signature for identification of individual fruit as it travels through the postharvest supply chain. The objective of this research was to assess the feature of these sweet pepper features for identification purposes. The macroscopic and microscopic images were taken to characterize the fluorescence. The results indicate that all sweet peppers possess dot-like fluorescence features on their surface. Furthermore, it was observed that 93.60% of these features exhibited changes in fluorescence intensity within the cuticle layer during the growth of a pepper. These features on the macro-image are visible under 365 nm UV light, but challenging to be seen under white LEDs and to be classified from the fluorescence spectrum under 365 nm light. This research reported the fluorescence feature on the sweet pepper, which is invisible under white light. The results show that the uniqueness of fluorescent features on the surface of sweet peppers has the potential to become a traceability technology due to the presence of its unique physical modality.

Change-Point Detection for Multi-Way Tensor-Based Frameworks

Graph-based change-point detection methods are often applied due to their advantages for using high-dimensional data. Most applications focus on extracting effective information of objects while ignoring their main features. However, in some applications, one may be interested in detecting objects with different features, such as color. Therefore, we propose a general graph-based change-point detection method under the multi-way tensor framework, aimed at detecting objects with different features that change in the distribution of one or more slices. Furthermore, considering that recorded tensor sequences may be vulnerable to natural disturbances, such as lighting in images or videos, we propose an improved method incorporating histogram equalization techniques to improve detection efficiency. Finally, through simulations and real data analysis, we show that the proposed methods achieve higher efficiency in detecting change-points.

Automatic Transplanting Equipment for Chain Pot Seedlings in Shaft Tillage Cultivation

The study aims to develop automatic transplanting equipment for chain pot seedlings. We intend to practice the shaft tillage cultivation using an autonomous farming robot. We had developed an autonomous working vehicle and automatic transplanting equipment for plug seedlings used in shaft tillage cultivation. To reinforce the robot system’s versatility, we developed transplanting equipment for the chain pot seedlings. We experimentally investigated the transplanting performance. Approximately 84% of the seedlings were automatically transplanted using the developed equipment. Since the equipment was performed well in the failure samples, we assumed that the cause of such failures was attributed to seedling quality. In addition, we measured the power consumption of the equipment used to build an electrical power supply system. Consequently, we calculated the power requirements for each process. Compared with the plug seedling equipment developed in the previous study, the chain pot seedlings’ power requirement was lower because the conveying actions of seedlings were different. In the next stage of our research, to construct a fully automatic system, we will consider the seedling raising method in which seedlings can become uniformly high-quality and investigate the plant establishment performance using the developed equipment.

Robotic Forklift for Stacking Multiple Pallets with RGB-D Cameras

We propose a robotic forklift system for stacking multiple mesh pallets. The stacking of mesh pallets is an essential task for the shipping and storage of loads. However, stacking, the placement of pallet feet on pallet edges, is a complex problem owing to the small sizes of the feet and edges, leading to a complexity in the detection and the need for high accuracy in adjusting the pallets. To detect the pallets accurately, we utilize multiple RGB-D (RGB Depth) cameras that produce dense depth data under the limitations of the sensor position. However, the depth data contain noise. Hence, we implement a region growing-based algorithm to extract the pallet feet and edges without removing them. In addition, we design the control law based on path following control for the forklift to adjust the position and orientation of two pallets. To evaluate the performance of the proposed system, we conducted an experiment assuming a real task. The experimental results demonstrated that the proposed system can achieve a stacking operation with a real forklift and mesh pallets.

Tomato Recognition for Harvesting Robots Considering Overlapping Leaves and Stems

In recent years, the declining and aging population of farmers has become a serious problem. Smart agriculture has been promoted to solve these problems. It is a type of agriculture that utilizes robotics, and information and communication technology to promote labor saving, precision, and realization of high-quality production. In this research, we focused on robots that can harvest tomatoes. Tomatoes are delicate vegetables with a thin skin and a relatively large yield. During automatic harvesting of tomatoes, to ensure the operation of the harvesting arm, an input by image processing is crucial to determine the color of the tomatoes at the time of harvesting. Research on robot image processing technology is indispensable for accurate operation of the arm. In an environment where tomatoes are harvested, obstacles such as leaves, stems, and unripe tomatoes should be taken into consideration. Therefore, in this research, we propose a method of image processing to provide an appropriate route for the arm to ensure easy harvesting, considering the surrounding obstacles.