Automated fruit-picking equipment has the potential to significantly enhance the efficiency of picking. Accurate detection and localization of fruits are particularly crucial in this regard. However, current methods rely on expensive tools such as depth cameras and LiDAR. This study proposes a low-cost method based on monocular images to achieve target detection and depth estimation. To improve the detection accuracy of targets, especially small targets, an advanced YOLOv8s detection algorithm is introduced. This approach utilizes the BiFormer block, an attention mechanism for dynamic query-aware sparsity, as the backbone feature extractor. It also adds a small-target-detection layer in the Neck and employs EIoU Loss as the loss function. Furthermore, a fused depth estimation method is proposed, which incorporates high-resolution, low-resolution, and local high-frequency depth estimation to obtain depth information with both high-frequency details and low-frequency structure. Finally, the spatial 3D coordinates of the fruit are obtained by fusing the planar coordinates and depth information. The experimental results with citrus as the target result in an improved YOLOv8s network mAP of 88.45% and a recognition accuracy of 94.7%. The recognition of citrus in a natural environment was improved by 2.7% compared to the original model. In the detection range of 30 cm~60 cm, the depth-estimation results (MAE, RSME) are 0.53 and 0.53. In the illumination intensity range of 1000 lx to 5000 lx, the average depth estimation results (MAE, RSME) are 0.49 and 0.64. In the simulated fruit-picking scenario, the success rates of grasping at 30 cm and 45 cm were 80.6% and 85.1%, respectively. The method has the advantage of high-resolution depth estimation without constraints of camera parameters and fruit size that monocular geometric and binocular localization do not have, providing a feasible and low-cost localization method for fruit automation equipment.

The optimization of the sawing process for Pinus kesiya Royle ex Gordon, an important timber used in construction and furniture, especially through the adjustment of parameters such as wood moisture content, cutting speed, and feed speed, not only helps reduce energy consumption and noise but also improves surface processing quality, thereby promoting green and environmentally friendly production. Therefore, this study selects the wood moisture content, cutting speed, and feed speed during the Single Pass Crosscut process of Pinus kesiya as the preliminary experimental parameters. Based on the Transformer model, a cutting prediction model for Pinus kesiya is established to predict three cutting performance indicators: cutting power consumption, surface roughness, and cutting noise. Meanwhile, Bayesian optimization was used to search for the optimal parameter combination within the specified cutting process parameter ranges that minimizes the objective function for these cutting performance indicators. Finally, experimental verification based on the optimal parameter combination shows that the average coefficient of determination for the cutting performance indicators is 0.937, the average mean squared error is 0.076, and the average mean absolute error is 0.186, indicating good agreement between the predicted and measured values.

For the forestry Internet of Things (IoT) systems deployed in the wilderness, the energy consumption of sensor nodes and energy-saving mechanisms are of paramount importance. This study focuses on the energy consumption analysis of various sensors, node controls, and communication devices in the forestry IoT system. Through the design of sensor power shutdown strategies, node sleep strategies, and incremental transmission strategies, it aims to maximize energy savings and improve energy utilization efficiency. By implementing the incremental transmission strategy, data compression can be performed with minimal computational energy expenditure, reducing the number of data transmissions and conserving node energy. Experimental results demonstrate that, when utilizing a 1000mAh lithiumion battery, the implementation of energy-saving strategies enables the node to sustain operation for up to 400 hours, significantly extending the lifespan of the forestry IoT system. The results of this study can be applied to the actual deployment of forestry IoTs, effectively extending node life, and improving network reliability.