As a key global food reserve, rice disease detection technology plays an important role in promoting food production, protecting ecological balance and supporting sustainable agricultural development. However, existing rice disease identification techniques face many challenges, such as low training efficiency, insufficient model accuracy, incompatibility with mobile devices, and the need for a large number of training datasets. This study aims to develop a rice disease detection model that is highly accurate, resource efficient, and suitable for mobile deployment to address the limitations of existing technologies. We propose the Transfer Layer iRMB-YOLOv8 (TLI-YOLO) model, which modifies some components of the YOLOv8 network structure based on transfer learning. The innovation of this method is mainly reflected in four key components. First, transfer learning is used to import the pretrained model weights into the TLI-YOLO model, which significantly reduces the dataset requirements and accelerates model convergence. Secondly, it innovatively integrates a new small object detection layer into the feature fusion layer, which enhances the detection ability by combining shallow and deep feature maps so as to learn small object features more effectively. Third, this study is the first to introduce the iRMB attention mechanism, which effectively integrates Inverted Residual Blocks and Transformers, and introduces deep separable convolution to maintain the spatial integrity of features, thus improving the efficiency of computational resources on mobile platforms. Finally, this study adopted the WIoUv3 loss function and added a dynamic non-monotonic aggregation mechanism to the standard IoU calculation to more accurately evaluate and penalize the difference between the predicted and actual bounding boxes, thus improving the robustness and generalization ability of the model. The final test shows that the TLI-YOLO model achieved 93.1% precision, 88% recall, 95% mAP, and a 90.48% F1 score on the custom dataset, with only 12.60 GFLOPS of computation. Compared with YOLOv8n, the precision improved by 7.8%, the recall rate improved by 7.2%, and mAP@.5 improved by 7.6%. In addition, the model demonstrated real-time detection capability on an Android device and achieved efficiency of 30 FPS, which meets the needs of on-site diagnosis. This approach provides important support for rice disease monitoring.

Mine ecological restoration is a critical process for promoting the sustainable development of resource-dependent regions, yet existing monitoring methods remain limited in accuracy and adaptability. To address challenges such as small-object recognition, insufficient multi-scale feature fusion, and blurred boundaries in UAV-based remote sensing imagery, this paper proposes an enhanced semantic segmentation model based on Segformer. Specifically, a multi-scale feature-enhanced feature pyramid network (MSFE-FPN) is introduced between the encoder and decoder to strengthen cross-level feature interaction. Additionally, a selective feature aggregation pyramid pooling module (SFA-PPM) is integrated into the deepest feature layer to improve global semantic perception, while an efficient local attention (ELA) module is embedded into lateral connections to enhance sensitivity to edge structures and small-scale targets. A high-resolution UAV image dataset, named the HUNAN Mine UAV Dataset (HNMUD), is constructed to evaluate model performance, and further validation is conducted on the public Aeroscapes dataset. Experimental results demonstrated that the proposed method exhibited strong performance in terms of segmentation accuracy and generalization ability, effectively supporting the image analysis needs of mine restoration scenes.

Despite the implementation of numerous interventions to enhance urban traffic safety, the estimation of the risk of traffic crashes resulting in life-threatening and economic costs remains a significant challenge. In light of the above, an online inference method for traffic crash risk based on the self-developed TAR-DETR and WOA-SA-SVM methods is proposed. The method’s robust data inference capabilities can be applied to autonomous mobile robots and vehicle systems, enabling real-time road condition prediction, continuous risk monitoring, and timely roadside assistance. First, a self-developed dataset for urban traffic object detection, named TAR-1, is created by extracting traffic information from major roads around Hainan University in China and incorporating Russian car crash news. Secondly, we develop an innovative Context-Guided Reconstruction Feature Network-based Urban Traffic Objects Detection Model (TAR-DETR). The model demonstrates a detection accuracy of 76.8% for urban traffic objects, which exceeds the performance of other state-of-the-art object detection models. The TAR-DETR model is employed in TAR-1 to extract urban traffic risk features, and the resulting feature dataset was designated as TAR-2. TAR-2 comprises six risk features and three categories. A new inference algorithm based on WOA-SA-SVM is proposed to optimize the parameters (C, g) of the SVM, thereby enhancing the accuracy and robustness of urban traffic crash risk inference. The algorithm is developed by combining the Whale Optimization Algorithm (WOA) and Simulated Annealing (SA), resulting in a Hybrid Bionic Intelligent Optimization Algorithm. The TAR-2 dataset is inputted into a Support Vector Machine (SVM) optimized using a hybrid algorithm and used to infer the risk of urban traffic crashes. The proposed WOA-SA-SVM method achieves an average accuracy of 80% in urban traffic crash risk inference.