The detection and recognition of unstructured roads in forest environments are critical for smart forestry technology. Forest roads lack effective reference objects and manual signs and have high degrees of nonlinearity and uncertainty, which pose severe challenges to forest engineering vehicles. This research aims to improve the automation and intelligence of forestry engineering and proposes an unstructured road detection and recognition method based on a combination of image processing and 2D lidar detection. This method uses the “improved SEEDS + Support Vector Machine (SVM)” strategy to quickly classify and recognize the road area in the image. Combined with the remapping of 2D lidar point cloud data on the image, the actual navigation requirements of forest unmanned navigation vehicles were fully considered, and road model construction based on the vehicle coordinate system was achieved. The algorithm was transplanted to a self-built intelligent navigation platform to verify its feasibility and effectiveness. The experimental results show that under low-speed conditions, the system can meet the real-time requirements of processing data at an average of 10 frames/s. For the centerline of the road model, the matching error between the image and lidar is no more than 0.119 m. The algorithm can provide effective support for the identification of unstructured roads in forest areas. This technology has important application value for forestry engineering vehicles in autonomous inspection and spraying, nursery stock harvesting, skidding, and transportation.

Traditional unmanned aerial vehicle (UAV) detection methods struggle with multi-scale variations during flight, complex backgrounds, and low accuracy, whereas existing deep learning detection methods have high accuracy but high dependence on equipment, making it difficult to detect small UAV targets efficiently. To address the above challenges, this paper proposes an improved lightweight high-precision model, YOLOv8-E (Enhanced YOLOv8), for the fast and accurate detection and identification of small UAVs in complex environments. First, a Sobel filter is introduced to enhance the C2f module to form the C2f-ESCFFM (Edge-Sensitive Cross-Stage Feature Fusion Module) module, which achieves higher computational efficiency and feature representation capacity while preserving detection accuracy as much as possible by fusing the SobelConv branch for edge extraction and the convolution branch to extract spatial information. Second, the neck network is based on the HSFPN (High-level Screening-feature Pyramid Network) architecture, and the CAA (Context Anchor Attention) mechanism is introduced to enhance the semantic parsing of low-level features to form a new CAHS-FPN (Context-Augmented Hierarchical Scale Feature Pyramid Network) network, enabling the fusion of deep and shallow features. This improves the feature representation capability of the model, allowing it to detect targets of different sizes efficiently. Finally, the optimized detail-enhanced convolution (DEConv) technique is introduced into the head network, forming the LSCOD (Lightweight Shared Convolutional Object Detector Head) module, enhancing the generalization ability of the model by integrating a priori information and adopting the strategy of shared convolution. This ensures that the model enhances its localization and classification performance without increasing parameters or computational costs, thus effectively improving the detection performance of small UAV targets. The experimental results show that compared with the baseline model, the YOLOv8-E model achieved (mean average precision at IoU = 0.5) an mAP@0.5 improvement of 6.3%, reaching 98.4%, whereas the model parameter scale was reduced by more than 50%. Overall, YOLOv8-E significantly reduces the demand for computational resources while ensuring high-precision detection.

The tractor–trailer wheeled robot (TTWR) is a typical modular mobile robot system. It is widely used in industry and agriculture transportation because of its simple structure, heavy load, high efficiency, strong adaptability, and flexibility. Because it is a nonlinear and underactuated system subjected to nonholonomic constraints, the complexity of the system and influence of the inner wheel difference pose great challenges to its trajectory prediction and path planning. To solve this problem, this paper proposes a trajectory prediction algorithm for an unpowered trailer for the TTWR system. In contrast to traditional single-path planning, the algorithm combines the motion characteristics of the Ackermann chassis tractor, analyzes the trailer motion law, and fully considers the lateral deviation of the trailer during the turning process. The algorithm can plan a reasonable cooperative path for the TTWR system. To verify the feasibility and effectiveness of the algorithm, the algorithm is transplanted to the TTWR intelligent experimental platform. A comparison of the simulation and experimental results shows that under the control of the preview tracking algorithm, the maximum error between the actual trajectory of the trailer and the trajectory predicted by the algorithm is generally no more than 9 cm, and the average error is 3.7 cm. This algorithm can provide an effective basis for TTWR system trajectory planning and path tracking. This algorithm is of great significance to TTWRs in warehousing logistics, freight forwarding, and skidding transportation.

Due to global warming, changes in plant phenology such as an early leaf spreading period in spring, a late abscission period in autumn, and growing season extension are commonly seen. Here, near-earth remote sensing images were used to monitor the canopy phenology of Populus tomentosa B301 in planted forests under full drip irrigation, full furrow irrigation, and no irrigation (rain fed). Experiments were conducted to collect phenological data across a growing season. Continuous canopy images were used to calculate different vegetation indices; the key phenological period was determined via the double logistic model and the curvature method. The effects of irrigation methods and precipitation in the rainy season on tree growth changes and key phenological periods were analyzed. The results showed that: (1) The green chromatic coordinate (GCC) conformed to the vegetation index of the tree species canopy phenological study. (2) During the phenological period throughout the year, the GCC reaching peak time (MOE) of the canopy phenology of Populus tomentosa B301 was the same in the three methods, while the time of shedding at the end of the growing season without irrigation (preset point 1) was 8 days longer than with full drip irrigation (preset point 3), and 7 days faster than with full furrow irrigation (preset point 5). (3) In the preliminary rainy season, different irrigation volumes induced different growth changes and phenological periods of the trees, resulting in different data of vegetation indicators under different growth conditions. (4) During the rainy season, the precipitation had different effects on cultivating P. tomentosa B301 using the three methods, that is, high precipitation could increase the growth rate of the fully irrigated area, otherwise the growth rate of this tree species was increased in full drip irrigation areas. Precipitation was lower and irregular, and the growth rate of this species was faster than the other two irrigation methods in the non-irrigated area, which was more adaptable to external environmental changes. The internal growth mechanism of the phenological changes in different areas of the planted forests was influenced by the different cultivation methods. Moreover, the collected phenological data provide a basis for the study of plant phenology with large data sets and deepens our understanding of the phenology of planted forests in response to climate change.

Traditional unmanned aerial vehicle (UAV) detection and tracking methods have long faced the twin challenges of high cost and poor efficiency. In real-world battlefield environments with complex backgrounds, occlusions, and varying speeds, existing techniques struggle to track small UAVs accurately and stably. To tackle these issues, this paper presents an enhanced YOLOv8N-Drone-based algorithm for improved target tracking of small UAVs. Firstly, a novel module named C2f-DSFEM (Depthwise-Separable and Sobel Feature Enhancement Module) is designed, integrating Sobel convolution with depthwise separable convolution across layers. Edge detail extraction and multi-scale feature representation are synchronized through a bidirectional feature enhancement mechanism, and the discriminability of target features in complex backgrounds is thus significantly enhanced. For the feature confusion problem, the improved lightweight Context Anchored Attention (CAA) mechanism is integrated into the Neck network, which effectively improves the system’s adaptability to complex scenes. By employing a position-aware weight allocation strategy, this approach enables adaptive suppression of background interference and precise focus on the target region, thereby improving localization accuracy. At the level of loss function optimization, the traditional classification loss is replaced by the focal loss (Focal Loss). This mechanism effectively suppresses the contribution of easy-to-classify samples through a dynamic weight adjustment strategy, while significantly increasing the priority of difficult samples in the training process. The class imbalance that exists between the positive and negative samples is then significantly mitigated. Experimental results show the enhanced YOLOv8 boosts mean average precision (Map@0.5) by 12.3%, hitting 99.2%. In terms of tracking performance, the proposed YOLOv8 N-Drone algorithm achieves a 19.2% improvement in Multiple Object Tracking Accuracy (MOTA) under complex multi-scenario conditions. Additionally, the IDF1 score increases by 6.8%, and the number of ID switches is reduced by 85.2%, indicating significant improvements in both accuracy and stability of UAV tracking. Compared to other mainstream algorithms, the proposed improved method demonstrates significant advantages in tracking performance, offering a more effective and reliable solution for small-target tracking tasks in UAV applications.

The design and industrial innovation of intelligent agricultural machinery and equipment for saline alkali land are important means for comprehensive management and capacity improvement of saline alkali land. The autonomous and unmanned agricultural tractor is the inevitable trend of the development of intelligent machinery and equipment in saline alkali land. As an underactuated system with non-holonomic constraints, the independent trajectory planning and lateral stability control of the tractor-trailer system (TTS) face challenges in saline alkali land. In this study, based on the nonlinear underactuation characteristics of the TTS and the law of passive trailer steering, a dual-trajectory collaborative control model was designed. By solving the TTS kinematic/dynamic state space, a nonlinear leading system that can generate the reference pose of a tractor-trailer was constructed. Based on the intrinsic property of the lateral deviation of the TTS, a collaborative trajectory prediction algorithm that satisfies the time domain and system constraints is proposed. Combining the dual-trajectory independent offset and lateral stability parameter of the TTS, an energy function optimization control parameter was constructed to balance the system trajectory tracking performance and lateral control stability. The experimental results showed good agreement between the predicted trailer trajectory and the collaborative control trajectory, with an average lateral error not exceeding 0.1 m and an average course angle error not exceeding 0.054 rad. This ensures that the dynamic controller designed around the tractor-trailer underactuation system can guarantee the smoothness of the trailer trajectory and the controlling stability of the tractor in saline alkali land.