To enhance agricultural productivity through the accurate detection of pests under the constrained resources of mobile devices, we introduce LP-YOLO, a bespoke lightweight object detection framework optimized for mobile-based insect pest identification. Initially, we devise lightweight components, namely LP_Unit and LP_DownSample, to serve as direct substitutes for the majority of modules within YOLOv8. Subsequently, we develop an innovative attention mechanism, denoted as ECSA (Efficient Channel and Spatial Attention), which is integrated into the network to forge LP-YOLO(l). Moreover, assessing the trade-offs between parameter reduction and computational efficiency, considering both the backbone and head components of the network, we use structured pruning methods for the pruning process, culminating in the creation of LP-YOLO(s). Through a comprehensive series of evaluations on the IP102 dataset, the efficacy of LP-YOLO as a lightweight object detection model is validated. By incorporating fine-tuning techniques during training, LP-YOLO(s)n demonstrates a marginal mAP decrease of only 0.8% compared to YOLOv8n. However, it achieves a significant reduction in parameter count by 70.2% and a remarkable 40.7% increase in FPS, underscoring its efficiency and performance.

To enhance the efficiency of automatic cherry tomato harvesting in precision agriculture, an improved YOLOv8n algorithm was proposed for fast and accurate recognition in natural environments. The improvements are as follows: first, the ADown down-sampling module replaces part of the original network backbone’s standard convolution, enabling the model to capture higher-level image features for more accurate target detection, while also reducing model complexity by cutting the number of parameters. Secondly, the model’s neck adopts a Slim-Neck (GSConv+VoV-GSCSP) instead of traditional convolution with C2f. It replaces this combination with the more efficient CSConv and swaps the C2f module for VoV-GSCSP. Finally, the model also introduces the EMA attention mechanism, implemented at the P5 layer, which enhances the feature representation capability, enabling the network to extract detailed target features more accurately. This study trained the object-detection algorithm on a self-built cherry tomato dataset before and after improvement and compared it with early deep learning models and YOLO series algorithms. The experimental results show that the improved model increases accuracy by 3.18%, recall by 1.43%, the F1 score by 2.30%, mAP50 by 1.57%, and mAP50-95 by 1.37%. Additionally, the number of parameters is reduced to 2.52 M, and the model size is reduced to 5.08 MB, which outperforms other related models compared to the previous version. The experiment demonstrates the technology’s broad potential for embedded systems and mobile devices. The improved model offers efficient, accurate support for automated cherry tomato harvesting.

This paper presents an enhanced YOLOX-based algorithm for pest detection, adopting a nature-inspired approach for refining its methodology. To tackle the limited availability of image data pertaining to pests and diseases, the paper incorporates Mosaic and Mixup technologies for effective image preprocessing. Furthermore, a novel training strategy is proposed to enhance the overall quality of the results. The existing architecture is enriched by integrating shallow information, while the CLT module is devised to facilitate cross-layer fusion and extract essential feature information. This advancement enables improved object detection across various scales. Additionally, the paper optimizes the original PFPN structure by eliminating the convolutional layer preceding upsampling, enhancing the C3 module, and integrating the convolutional attention model (CBAM) to identify salient regions within complex scenes. The performance of the proposed CLT-YOLOX model is extensively evaluated using the IP102 dataset, demonstrating its effectiveness. Notably, the model exhibits significant improvements compared to the original AP evaluation index, with an increase of 2.2% in average precision (mAP) and 1.8% in AP₇₅. Furthermore, favorable results are achieved in the COCOmAP index, particularly in the AP_small category where there is a 2.2% improvement in performance.

Plant diseases significantly undermine agricultural productivity. This study introduces an improved YOLOv10n model named WD-YOLO (Weighted and Double-scale YOLO), an advanced architecture for efficient plant disease detection. The PlantDoc dataset was initially enhanced using data augmentation techniques. Subsequently, we developed the DSConv module—a novel convolutional structure employing double-scale weighted convolutions that dynamically adjust to different scale perceptions and optimize attention allocation. This module replaces the conventional Conv module in YOLOv10. Furthermore, the WTConcat module was introduced, dynamically merging weighted concatenation with a channel attention mechanism to replace the Concat module in YOLOv10. The training of WD-YOLO incorporated knowledge distillation techniques using YOLOv10l as a teacher model to refine and compress the architectural learning. Empirical results reveal that WD-YOLO achieved an mAP50 of 65.4%, outperforming YOLOv10n by 9.1% without data augmentation and YOLOv10l by 2.3%, despite having significantly fewer parameters (9.3 times less than YOLOv10l), demonstrating substantial gains in detection efficiency and model compactness.

Camera rotation estimation is a key component in video stabilization and motion analysis. In many practical scenarios, inertial measurements are unavailable or temporally unreliable, while classical geometric pipelines degrade under blur, low texture, and low illumination. This paper investigates whether substantially downsampled optical flow can retain sufficient structure for accurate frame-to-frame rotation regression. We present VisualRNet, a lightweight rotation-specific visual regression framework trained with cross-modal IMU supervision. Our design uses coordinate-aware feature encoding, depthwise separable convolutions, lightweight attention, and a compact 6D rotation head to model the spatial structure of rotational flow fields. On Deep-FVS, VisualRNet achieves a mean rotation error of 0.3151° on the test set. The VisualRNet regression head contains 7.7 K parameters, 0.002 GFLOPs, and runs at 729 FPS, while the full pipeline with the FastFlowNetv2 frontend contains 1.374 M parameters, 7.194 GFLOPs, and runs at approximately 113 FPS. A cross-camera adaptation experiment on TUM VI further indicates that the learned motion representation can be aligned to a new camera system with limited calibration data. These results support low-resolution optical flow as a practical input for visual rotation estimation and suggest particular value in stabilization-oriented and cost-sensitive applications where approximate rotational trend matters more than full scene geometry.