In order to realize the real-time and accurate detection of potted flowers on benches, in this paper we propose a method based on the ZED 2 stereo camera and the YOLO V4-Tiny deep learning algorithm for potted flower detection and location. First, an automatic detection model of flowers was established based on the YOLO V4-Tiny convolutional neural network (CNN) model, and the center points on the pixel plane of the flowers were obtained according to the prediction box. Then, the real-time 3D point cloud information obtained by the ZED 2 camera was used to calculate the actual position of the flowers. The test results showed that the mean average precision (MAP) and recall rate of the training model was 89.72% and 80%, respectively, and the real-time average detection frame rate of the model deployed under Jetson TX2 was 16 FPS. The results of the occlusion experiment showed that when the canopy overlap ratio between the two flowers is more than 10%, the recognition accuracy will be affected. The mean absolute error of the flower center location based on 3D point cloud information of the ZED 2 camera was 18.1 mm, and the maximum locating error of the flower center was 25.8 mm under different light radiation conditions. The method in this paper establishes the relationship between the detection target of flowers and the actual spatial location, which has reference significance for the machinery and automatic management of potted flowers on benches.

Lettuce is an important vegetable in horticulture, but information about the interactive effects of light and temperature on its photosynthetic characteristics was inadequate. This work investigated the effects of three temperatures (15/10 (T15), 23/18 (T23), and 30/23 °C (T30)) and five light treatments (100 (P100), 200 (P200), 350 (P350), 500 (P500), and 600 μmol·m⁻²·s⁻¹ (P600)) on the light–response curves, chlorophyll content, and yield of lettuce. The results showed that the maximum photosynthetic rate, light saturation point, chlorophyll content, and yield of lettuce were all the highest at T23 compared with T15 and T30 under different light intensities. Under the same temperature conditions, the photosynthesis capacity and yield of lettuce in the P350 and P500 treatments at T15, P350, P500, and P600 treatments at T23 and P500, and P600 treatments at T30 were larger than other light treatments. The results suggested that temperature play had a more pronounced influence on photosynthesis and yield in lettuce, but the appropriate levels of light intensity improved its potential photosynthetic capacity and yield under different temperature conditions.

Light and temperature are two crucial factors affecting plant growth. Light intensities vary considerably with season and weather conditions. Reasonable light regulation at different temperatures is a key issue in environmental regulation. In this study, we determined the effects of light intensity and temperature on crop growth and development. Furthermore, we determined an optimal light value and a suitable light range at different temperatures for producing the lettuce Lactuca sativa L. Artificial climate chamber experiments were conducted at five light intensities (100, 200, 350, 500, and 600 μmol·m ⁻² ·s ⁻¹ ), as well as at low (15 °C/10 °C), medium (23 °C/18 °C), and high (30 °C/25 °C) temperatures. In these experiments, we investigated the photosynthetic rate; chlorophyll fluorescence parameters; total N, P, and K uptake; and growth of lettuce plants. The results indicated that at a low temperature, the values of effective quantum yield of photosystem II photochemistry (Φ _PSII ), net photosynthetic rate ( P _n ), stomatal conductance ( g _S ), and transpiration rate ( T _r ) —as well as those of N, K, and P uptake—were the highest at 350 μmol·m ⁻² ·s ⁻¹ , followed by 500 μmol·m ⁻² ·s ⁻¹ , which resulted in higher values for leaf number (LN), leaf area (LA), dry weight (DW), and fresh weight (FW). At the medium temperature, the values of Φ _PSII , P _n , g _S , and T _r , as well as those of N, K, and P uptake were higher at 350, 500, and 600 μmol·m ⁻² ·s ⁻¹ than at other light intensities, resulting in high values for LN, LA, DW, and FW of lettuce plants. The LN, LA, and FW of lettuce plants were the highest at 500 μmol·m ⁻² ·s ⁻¹ , whereas DW was the highest at 600 μmol·m ⁻² ·s ⁻¹ . At a high temperature, lettuce plants exhibited the highest values of F _v / F _m, Φ _PSII , P _n , g _S , and T _r , as well as those of N, K, and P uptake for the 500 μmol·m ⁻² ·s ⁻¹ treatment; whereas LN, LA, FW, and DW were the highest at 600 μmol·m ⁻² ·s ⁻¹ . In addition, the values of F _v / F _m indicated that lettuce plants were under stress under the following combinations: 600 μmol·m ⁻² ·s ⁻¹ at the low temperature, 100 μmol·m ⁻² ·s ⁻¹ at the medium temperature, and 100–350 μmol·m ⁻² ·s ⁻¹ at the high temperature. Based on these results, an optimal regulation strategy for light intensity at different temperature environments was proposed for lettuce cultivars similar to L. sativa L. in some regions, such as the subtropical regions of China. Specifically, for low temperatures, light intensities of 350 to 500 μmol·m ⁻² ·s ⁻¹ are recommended for production, and an intensity of 350 μmol·m ⁻² ·s ⁻¹ provides optimal supplementary light during early spring and winter in greenhouses. For medium temperatures, light intensities of 350 to 600 μmol·m ⁻² ·s ⁻¹ are recommended, and 500 μmol·m ⁻² ·s ⁻¹ is the optimal value during the middle of spring and autumn. For high temperatures, light intensities of 500 to 600 μmol·m ⁻² ·s ⁻¹ are recommended, and 600 μmol·m ⁻² ·s ⁻¹ is the optimal value of light intensity during late spring and early autumn.

Composting is a biochemical as well as a heterogeneous process, and the turning operation is important to maintain aerobic conditions and improve the efficiency of the composting process. Therefore, the turning frequency is an important factor for the precise control of the composting reactor. It is necessary to determine the changes in the physical and chemical parameters of the composting process and to simulate them. Pretreated vinegar residue and wool washing sludge were mixed at a mass ratio of 6:4 for the composting process. The composting reactor’s temperature, CO₂, CH₄, and organic matter content were collected during the composting process. According to the principles of composting, a kinetic model of composting based on the change in CO₂ gas concentration and heat balance in the composting reactor is developed, which provides a theoretical basis for the subsequent control of the composting reactor. The comparison of the model predictions to the measured results of the composting reactor shows that the SSE, R², and RMSE for the organic matter content simulation are 8.122, 0.943, and 1.274 g/kg, respectively, and the SSE, R², and RMSE for the temperature simulation are 29.54, 0.959, and 2.71 °C, respectively. Based on the prediction of the temperature in the reactor based on the composting kinetics model, the process control for the turning operation is proposed to achieve precise control of the composting process. The results show that the duration of high temperature in a composting reactor is prolonged for 2 days, the degradation rate of organic matter occurs at a more rapid speed, and the operation efficiency of the production line can be improved by more than 10%. This indicates that the decision-making method based on the composting kinetics model can improve the composting efficiency.