Smart agriculture has the potential to solve labor shortages and improve production efficiency and prices at the time of shipment. Predicting tomato yields during the cultivation period is crucial for planning shipment volumes and costs in advance. We propose technology that utilizes an AI camera to enable producers to predict yields more accurately, and we verify the effectiveness of the developed system through experimental validation. Specifically, an AI-recognition camera was developed, utilizing You Only Look Once (YOLO) to detect individual tomatoes. The detected tomatoes are analyzed for size using point cloud data. Moreover, the AI-recognition camera performs to classify ripeness based on hue. This technology can achieve accurate ripeness classification without being dependent on the brightness of the greenhouse. To evaluate this AI classification camera, the predicted yield obtained from the camera was compared with the actual harvested yield in the field. The analysis showed an error rate of 6.85%, demonstrating sufficient accuracy for practical implementation. By introducing this system, efficient yield prediction can be achieved, leading to reduced labor costs, stable tomato supply, improved quality, and optimized market distribution. As a result, it is expected to contribute to the benefits of both shippers and consumers.

The re-entry capsule tracking system is proposed as a shared/dual-use technology with commercial products. This system has portability, and is not affected by the condition of installed equipment in the capsule. In this paper, the detection performance is described about the tracking area assumed from Hayabusa's achievement. By the experiment using the prototype radar, this system was confirmed to be able to detect more than 90% of the area.

In the Hayabusa2 re-entry capsule recovery operation, marine radars were used to estimate the landing point of the capsule. These radars were commercial products for ships and were used with some modifications for this operation. The radars tracked the instrument module containing the asteroid samples for 18 min, along with other equipment. The maximum observed distance was 31.55 km, and the tracking was accurate up to 240 m near the instrument module landing point. This paper describes the marine radar system, reports the tracking results of the operation, discusses the considerations made for future missions. One consideration is to estimate the altitude by using multiple search radars in order to more accurately predict the landing point. Another is to estimate the radar cross-section of the instrument module during descent. This paper demonstrates that the altitude can be estimated by the search radars, and the radar cross-section fluctuated by approx. 10 times depending on the elevation angle relative to the radar. The results of this paper suggest the possibility of cooperative search by using multiple small radars. This feature may contribute to reductions in mission costs and to expanding the choice of landing areas.

The re-entry capsule tracking radar is considered based on the long-range detection experiment results of the small flight object. In the experiment, the object with the radar cross section of 0.159m² could be detected up to 17.5 km. In the consideration based on the results, the possibility of the over 20 km detection is shown by achieving assumed output power, and the automatic tracking is examined to save the operation cost. By these considerations, the feasibility of the re-entry capsule tracking system as a shared/dual-use technology with commercial products is increased.