With the rising global demand for aquatic products, aquaculture has become a cornerstone of food security and sustainability. This review comprehensively analyzes the application of deep learning in sustainable aquaculture, covering key areas such as fish detection and counting, growth prediction and health monitoring, intelligent feeding systems, water quality forecasting, and behavioral and stress analysis. The study discusses the suitability of deep learning architectures, including CNNs, RNNs, GANs, Transformers, and MobileNet, under complex aquatic environments characterized by poor image quality and severe occlusion. It highlights ongoing challenges related to data scarcity, real-time performance, model generalization, and cross-domain adaptability. Looking forward, the paper outlines future research directions including multimodal data fusion, edge computing, lightweight model design, synthetic data generation, and digital twin-based virtual farming platforms. Deep learning is poised to drive aquaculture toward greater intelligence, efficiency, and sustainability.

This study proposes ToRLNet, a lightweight tomato ripeness detector designed for real-time deployment in resource-constrained agricultural settings. Built on YOLOv12n, ToRLNet integrates three self-constructed modules (WaveFusionNet for frequency–spatial enhancement and feature extraction, ETomS for efficient context-aware encoding, and SFAConv for selective multi-scale downsampling) to address subtle inter-stage color transitions, small fruit instances, and cluttered canopies. We benchmark ToRLNet against lightweight and small-scale YOLO baselines (YOLOv8–YOLOv12) and conduct controlled ablations isolating each module’s contribution. ToRLNet attains Precision 90.27%, Recall 86.77%, F1-score 88.49%, mAP50 91.76%, and mAP 78.01% with only 6.9 GFLOPs, outperforming representative nano/small YOLO variants under comparable compute budgets. Ablation results show WaveFusionNet improves spectral–textural robustness, ETomS balances the precision–recall trade-off while reducing redundancy, and SFAConv preserves fine chromatic gradients and boundary structure during downsampling; their combination yields the most balanced performance. These findings demonstrate that ToRLNet delivers a favorable accuracy–efficiency trade-off and provides a practical foundation for on-board perception in automated harvesting, yield estimation, and greenhouse management.

High-throughput plant phenotyping (HTPP) is increasingly limited by the mismatch between the need for field-relevant, fine-grained phenotypic information and the restricted capability of conventional observation platforms under complex agricultural conditions. Ground mobile robots are emerging as the key carrier for resolving this gap because they combine close-range sensing, autonomous mobility, and physical interaction within real field environments. In this paper, a structured scoping review is presented using a closed-loop perception–decision–action pipeline as the organizing principle. Within this framework, recent advances are synthesized from the perspectives of multimodal fusion, localization-aware sensing, motion planning, deep-learning-based phenotypic analysis, active observation, robotic intervention, and edge deployment. The review further clarifies the complementary roles of Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), and air–ground collaboration in multiscale phenotyping workflows. Beyond summarizing technologies, the article provides three concrete deliverables: a structured taxonomy of mobile phenotyping systems; comparative tables covering sensing modalities, localization/navigation methods, and AI models; and a research agenda linking technical progress to field deployability. The synthesis highlights four persistent bottlenecks, namely environmental generalization, annotation scarcity, limited standardization and reproducibility, and the gap between advanced models and agricultural edge hardware. Overall, ground robots are identified not merely as sensing platforms, but as the central system architecture for advancing mobile phenotyping toward autonomous, fine-grained, and field-deployable operation.

High-throughput plant phenotyping is increasingly constrained by the mismatch between the demand for field-relevant, fine-grained phenotypic data and the limited capability of conventional observation platforms under complex agricultural conditions. In this context, mobile phenotyping systems, particularly ground robots, are emerging as a key technological pathway for bridging macro-scale monitoring and organ-level trait analysis. This review examines the development of mobile phenotyping platforms for high-throughput plant phenotyping, with emphasis on the evolving role of ground robots in field-based sensing, decision-making, and active interaction. We first compare the functional characteristics of unmanned aerial vehicles and unmanned ground vehicles and discuss their complementarity in multiscale phenotypic data acquisition. We then summarize recent advances in the core technical framework of mobile phenotyping robots, including multimodal perception, localization and mapping, motion planning, deep-learning-based phenotypic analysis, active observation, robotic intervention, and edge deployment. Major challenges are further discussed, particularly those related to environmental generalization, data annotation, standardization, reproducibility, and long-term field reliability. Finally, future directions are outlined from the perspectives of air–ground collaboration, multi-robot systems, foundation models, and embodied intelligence. This review highlights ground robots as a central carrier for advancing mobile phenotyping toward autonomous, fine-grained, and field-deployable systems.

This study presents a lightweight RGB vision-based express-parcel detection framework for complex logistics environments. An Express Parcel Recognition (EPR) dataset is first constructed from RGB images acquired through multi-source data collection, followed by unified re-annotation and Active Learning-based pseudo-labeling to reduce manual annotation effort while maintaining label consistency. Based on YOLOv11s, a lightweight detector termed EPR-YOLO is developed by integrating SFAConv and NGAM to strengthen multi-scale feature extraction and global semantic modeling from RGB visual inputs while controlling computational complexity. Quantization-Aware Training is further introduced to obtain an INT8-quantized model with reduced storage requirements and limited accuracy degradation, providing a basis for subsequent lightweight deployment. Comparative experiments, ablation studies, and independent test set evaluations demonstrate that EPR-YOLO achieves an mAP₅₀ of 71.654%, improving the YOLOv11s baseline by 0.854 percentage points while reducing the parameter count by 9.5%; the quantized model further retains most of the detection capability of its floating-point counterpart. In addition, a FastAPI-based Web application is implemented to support RGB image acquisition-based single-image and batch detection, result visualization, and online inference. The proposed framework therefore provides an integrated sensing-to-deployment solution covering RGB image-based parcel perception, dataset construction, lightweight model optimization, quantized deployment, and application-level validation for intelligent logistics systems.