Underwater images encounter a range of quality degradation issues caused by the differential scattering and absorption of light in water. To address these challenges, we introduce a WFAC method, a wavelet decomposition fusion method that combines global and local contrast for underwater image enhancement. Specifically, we begin with a color transfer compensation strategy to correct the colors in a degraded underwater image. Subsequently, we utilize the pixel gradient distribution to create a matrix weight map that dynamically adjusts the weight distribution in overly bright or dark areas of the color-corrected image, enhancing its global contrast. Simultaneously, we apply a rapid integration statistical strategy to adaptively fine-tune the local contrast of color-corrected images using the local mean and variance statistics. To combine the strengths of various enhanced images, we implement a wavelet decomposition fusion strategy to break down different scale components of globally and locally contrast-enhanced images and merge the benefits of varying scale images to obtain a high-quality underwater image. Comprehensive experimental assessments across three underwater image datasets demonstrate that our WFAC method efficiently recovers colors and boosts contrast in degraded underwater images. The code is publicly available at: https://www.researchgate.net/publication/386508762_2024WFAC.

Cattle behavior classification technology holds a crucial position within the realm of smart cattle farming. Addressing the requisites of cattle behavior classification in the agricultural sector, this paper presents a novel cattle behavior classification network tailored for intricate environments. This network amalgamates the capabilities of CNN and Bi-LSTM. Initially, a data collection method is devised within an authentic farm setting, followed by the delineation of eight fundamental cattle behaviors. The foundational step involves utilizing VGG16 as the cornerstone of the CNN network, thereby extracting spatial feature vectors from each video data sequence. Subsequently, these features are channeled into a Bi-LSTM classification model, adept at unearthing semantic insights from temporal data in both directions. This process ensures precise recognition and categorization of cattle behaviors. To validate the model’s efficacy, ablation experiments, generalization effect assessments, and comparative analyses under consistent experimental conditions are performed. These investigations, involving module replacements within the classification model and comprehensive analysis of ablation experiments, affirm the model’s effectiveness. The self-constructed dataset about cattle is subjected to evaluation using cross-entropy loss, assessing the model’s generalization efficacy across diverse subjects and viewing perspectives. Classification performance accuracy is quantified through the application of a confusion matrix. Furthermore, a set of comparison experiments is conducted, involving three pertinent deep learning models: MASK-RCNN, CNN-LSTM, and EfficientNet-LSTM. The outcomes of these experiments unequivocally substantiate the superiority of the proposed model. Empirical results underscore the CNN-Bi-LSTM model’s commendable performance metrics: achieving 94.3% accuracy, 94.2% precision, and 93.4% recall while navigating challenges such as varying light conditions, occlusions, and environmental influences. The objective of this study is to employ a fusion of CNN and Bi-LSTM to autonomously extract features from multimodal data, thereby addressing the challenge of classifying cattle behaviors within intricate scenes. By surpassing the constraints imposed by conventional methodologies and the analysis of single-sensor data, this approach seeks to enhance the precision and generalizability of cattle behavior classification. The consequential practical, economic, and societal implications for the agricultural sector are of considerable significance.

Cattle’s individual identification plays a crucial role in effectively managing large farms. To enhance agricultural efficiency, promote the digital transformation of animal husbandry, and improve animal welfare, it is essential to employ advanced identification technologies capable of real-time monitoring of cattle individual. This paper introduces a novel network called Open Pose Mask R-CNN (OP-Mask R-CNN) for individual cattle identification, which combines Open Pose with the Mask R-CNN network. Three key strategies are presented to improve the identification of individual cattle. First, optimize the number of convolutional layers in the Mask R-CNN backbone network, i.e., ResNet101. Second, introduce an Open Pose-based bovine skeleton feature extraction method. Finally, construct a fusion mechanism that combines the attention module, the convolutional block attention module (CBAM), the open pose module, and the ResNet101. Experimental results demonstrate that our proposed method achieves a 5.6% increase in recognition accuracy and improves recognition speed compared to the original Mask R-CNN model. This work strikes a balance between accuracy and complexity, facilitating the development of a lightweight bovine individual recognition technique.

Introduction: Detecting strawberry growth stages is crucial for optimizing production management. Precise monitoring enables farmers to adjust management strategies based on the specific growth needs of strawberries, thereby improving yield and quality. However, dense planting patterns and complex environments within greenhouses present challenges for accurately detecting growth stages. Traditional methods that rely on large-scale equipment are impractical in confined spaces. Thus, the development of lightweight detection technologies suitable for portable devices has become essential.Methods: This paper presents SGSNet, a lightweight deep learning model designed for the fast and accurate detection of various strawberry growth stages. A comprehensive dataset covering the entire strawberry growth cycle is constructed to serve as the foundation for model training and testing. An innovative lightweight convolutional neural network, named GrowthNet, is designed as the backbone of SGSNet, facilitating efficient feature extraction while significantly reducing model parameters and computational complexity. The DySample adaptive upsampling structure is employed to dynamically adjust sampling point locations, thereby enhancing the detection capability for objects at different scales. The RepNCSPELAN4 module is optimized with the iRMB lightweight attention mechanism to achieve efficient multi-scale feature fusion, significantly improving the accuracy of detecting small targets from long-distance images. Finally, the Inner-IoU optimization loss function is applied to accelerate model convergence and enhance detection accuracy.Results: Testing results indicate that SGSNet performs exceptionally well across key metrics, achieving 98.83% precision, 99.45% recall, 99.14% F1 score, 99.50% mAP@0.5, and a loss value of 0.3534. It surpasses popular models such as Faster R-CNN, YOLOv10, and RT-DETR. Furthermore, SGSNet has a computational cost of only 14.7 GFLOPs and a parameter count as low as 5.86 million, demonstrating an effective balance between high performance and resource efficiency.Discussion: Lightweight deep learning model SGSNet not only exceeds the mainstream model in detection accuracy, but also greatly reduces the need for computing resources and is suitable for portable devices. In the future, the model can be extended to detect the growth stage of other crops, further advancing smart agricultural management.

Underwater acoustic sensor networks (UASNs) provide new opportunities for exploring oceans and consequently improving our understanding of the underwater world. UASNs usually rely on hardware infrastructure with poor flexibility and versatility. Compared with wireless sensor networks, UASNs are quite expensive to manufacture and deploy. Due to the unique data format, protocols, and service constraints of various applications, UASNs are typically deployed in a redundant manner, which not only leads to waste but also causes serious interference due to the presence of multiple signals in the same underwater region. Software-defined networking (SDN) provides an innovative means of improving the flexibility of underwater systems. In this paper, we present an SDN-based UASN framework, followed by the design of a clustering method in which learning automata and degree-constrained connected dominating sets are employed. We then propose a load balancing mechanism involving multiple controllers, based on the consistent hashing algorithm. Finally, we describe a simulation program (called UASNs hypervisor) that we developed and implemented to assess the network survival time, bit-error rate, and computational complexity. The experimental results show that the UASN was improved significantly. This work provides important theoretical and technical support for the implementation of SDN-based UASNs.