A wheat seedling detection model based on efficient feature extraction and coordinate attention mechanism

Multi-view 3D reconstruction aims to discover 3D characteristics based on visual information captured across multiple viewpoints. Transformer networks have shown remarkable success in various computer vision tasks, including multi-view 3D reconstruction. However, the reconstruction of accurate 3D shapes faces challenges when trying to efficiently extract and merge features across views. The existing frameworks struggled to capture the subtle relationships between the views, resulting in a poor reconstruction. To address this issue, we present a new framework, WGA-SWIN, for 3D reconstruction using multi-view objects. Our method introduces a Window Grouping Attention (WGA) mechanism that uses group tokens from different views for each window attention operation, enabling efficient inter-view and intra-view feature extraction. Diversity among various groups in a model contributes to the richness of feature learning, which results in advanced and dependable feature learning, resulting in more comprehensive and robust representations. Within the encoder swin transformer blocks, we integrated WGA to utilize both hierarchical design and shifted window attention mechanisms for efficient multi-view feature extraction. In addition, we developed a progressive hierarchical decoder that combines swin transformer blocks with 3D convolutions to utilize voxel representation, resulting in a high resolution for obtaining high-quality 3D reconstructions with fine structural details. The experimental results on the benchmark datasets ShapeNet and Pix3D demonstrate that our work achieves state-of-the-art (SOTA) performance, outperforming existing methods in both single-view and multi-view 3D reconstruction, beyond the capabilities of current technologies. We lead by 0.95% and 1.07% in both IoU and F-Scores respectively, which demonstrates the robustness of our method.

Texture is an important feature to describe images. Though lots of work has been done for efficient texture feature extraction from rectangular images, no much effort has been made in texture feature extraction from arbitrary-shaped regions in region-based image retrieval (RBIR) system. In this paper, we present an efficient texture feature extraction algorithm for arbitrary-shaped regions. This algorithm first extends an arbitrary-shaped region into a rectangular area onto which block transformation can be applied. Based on the projection-onto-convex-sets (POCS) theory, a set of coefficients best describing the original region are finally obtained, from which texture feature of the region can be extracted. Via intensive experiments, we select a set of parameters proper for image retrieval purpose. Experimental results on real-world image database demonstrate the effectiveness of the proposed algorithm for image retrieval purpose.

Human action recognition is essential in many real-world scenarios, such as video surveillance, human–computer interaction, and behavior analysis. Despite the progress in deep learning, issues such as occlusion, distraction from the background, and motion pattern variability still exist, thus restricting the generalization ability of current models. Most methods are based only on spatial or temporal features and cannot efficiently capture both in one framework, causing lower accuracy in realistic situations. In response to these shortcomings, a multilevel feature extraction approach was proposed by integrating spatial and temporal features to improve the action recognition precision. The method captures RGB frames, optical flow, spatial saliency maps, and temporal saliency maps to enable an overall inspection of video streams. Efficient feature extraction was achieved by applying a pre-trained Inception V3 model and then bidirectional gated recurrent units (Bi-GRUs) to include sequential modeling. An attention mechanism was also included to boost the classification process by focusing on key temporal segments. UCF101 and HMDB51 benchmark datasets evaluated the efficiency of the strategy. The model’s accuracy was 98.13% on UCF101 and 81.45% on HMDB51, which validated the superior discrimination ability of the model in processing heterogeneous human actions. These results confirm that the provided framework is an efficient and discriminative action recognition approach, thus suitable for applications requiring extensive motion analysis and real-time deployment.

Real-time object detection is critical for unmanned aerial vehicles (UAVs) performing various tasks. However, efficiently deploying detection models on UAV platforms with limited storage and computational resources remains a significant challenge. To address this issue, we propose ELNet, an efficient and lightweight object detection model based on YOLOv12n. First, based on an analysis of UAV image characteristics, we strategically remove two A2C2f modules from YOLOv12n and adjust the size and number of detection heads. Second, we propose a novel lightweight detection head, EPGHead, to alleviate the computational burden introduced by adding the large-scale detection head. In addition, since YOLOv12n employs standard convolution for downsampling, which is inefficient for extracting UAV image features, we design a novel downsampling module, EDown, to further reduce model size and enable more efficient feature extraction. Finally, to improve detection in UAV imagery with dense, small, and scale-varying objects, we propose DIMB-C3k2, an enhanced module built upon C3k2, which boosts feature extraction under complex conditions. Compared with YOLOv12n, ELNet achieves an 88.5% reduction in parameter count and a 52.3% decrease in FLOPs, while increasing mAP50 by 1.2% on the VisDrone dataset and 0.8% on the HIT-UAV dataset, reaching 94.7% mAP50 on HIT-UAV. Furthermore, the model achieves a frame rate of 682 FPS, highlighting its superior computational efficiency without sacrificing detection accuracy.

This paper proposes an efficient window-based semi-automatic feature extraction technique which uses simulated annealing for minimizing the energy of an active contour within a specified image region. The energy is computed based on a chamfer image, in which pixel values are a function of distance to image edges. A user places a number of control points close to the feature of interest. B-spline fitted to these points provides an initial approximation of the contour. A window containing both the initial contour and the feature of interest is considered. The contour with minimum energy inside the window provides the final delineation. Comparison of the performance of the proposed algorithm with traditional snake, a popular feature extraction technique based on energy minimization, demonstrates the superiority of the SAFE technique.

Dataset classification: An efficient feature extraction approach for grammatical facial expression recognition

Background. Modern machine vision systems largely rely on convolutional neural networks, which demonstrate high performance in image analysis due to their ability to extract hierarchical feature representations. Improvement in recognition quality is commonly achieved by increasing network depth and the number of parameters; however, this approach is associated with higher computational costs, increased sensitivity to noise, and reduced robustness to variations in scale and illumination. This circumstance highlights the need for architectural solutions that enable more efficient feature extraction without a significant increase in computational complexity. A promising direction involves the use of multiscale convolutional operations that capture both local and global image context, as well as the integration of attention mechanisms that provide adaptive concentration of computational resources on the most informative regions and features. Purpose. To formulate an architectural approach to the design of convolutional neural networks based on the combination of multiscale convolutional processing and attention mechanisms, aimed at improving the efficiency of machine vision algorithms while maintaining an acceptable level of computational cost. Materials and methods. The article examines three convolutional neural network architectures, including a baseline CNN, a multiscale CNN, and an extended model incorporating an attention mechanism. Operations of two dimensional convolution, batch normalization, and nonlinear activation are analyzed, along with methods for aggregating features obtained at different spatial scales. An analytical assessment of computational complexity is performed with consideration of the number of parameters, network depth, and the volume of operations during the forward pass. Results. The application of multiscale convolutional processing expands the receptive field of the network and improves robustness to variations in object size through simultaneous analysis of features at different levels of detail. The integration of attention mechanisms provides adaptive redistribution of feature weights, reduces the influence of noise and irrelevant components, and enhances the selectivity of image analysis.

Wide-Area Motion Imagery (WAMI) feature extraction is important for applications such as target tracking, traffic management and accident discovery. With the increasing amount of WAMI collections and feature extraction from the data, a scalable framework is needed to handle the large amount of information. Cloud computing is one of the approaches recently applied in large scale or big data. In this paper, MapReduce in Hadoop is investigated for large scale feature extraction tasks for WAMI. Specifically, a large dataset of WAMI images is divided into several splits. Each split has a small subset of WAMI images. The feature extractions of WAMI images in each split are distributed to slave nodes in the Hadoop system. Feature extraction of each image is performed individually in the assigned slave node. Finally, the feature extraction results are sent to the Hadoop File System (HDFS) to aggregate the feature information over the collected imagery. Experiments of feature extraction with and without MapReduce are conducted to illustrate the effectiveness of our proposed Cloud-Enabled WAMI Exploitation (CAWE) approach.

In order to solve the problem of excessive model parameters and low real‐time performance in driver distraction driving detection tasks, this work proposes a detection model based on cascaded convolutional network and attention mechanism. The model adopts a two‐stage architecture. In the first stage, the pre‐trained MobileNet is used as the backbone network for basic feature extraction to achieve efficient image feature extraction and significantly reduce the computational complexity. In the second stage, the basic features extracted in the first stage are enhanced by combining the Cascaded ResNet structure with the spatial attention mechanism, so as to improve the capture ability of key features. Finally, the features extracted in the two stages are fused to complete the driver's distraction behavior recognition. The experimental results on the public datasets American University in Cairo (AUC) Distracted Driver and StateFarm Distracted Driver (SFD) show that the proposed model achieves the recognition accuracy of 95.72% and 99.87%, respectively, which is significantly better than the existing mainstream methods while maintaining a low number of parameters. The model has low parameter quantity, high detection accuracy and high real‐time performance.

Facial expression recognition (FER) in uncontrolled, in-the-wild settings is a challenging task due to variations in pose, illumination, occlusion, and background clutter. The state-of-the-art methods on FER employ fixed size pooling in attention networks, resulting in suboptimal robustness in unconstrained environments. In this work, a novel Multi-Scale Attention Network (MSAN) is integrated with the YOLOv8 backbone architecture for expression classification. The YOLOv8 backbone provides efficient feature extraction with a lightweight, detection-oriented architecture, enabling real-time processing and strong spatial feature representation. The Convolutional Block Attention Mechanism (CBAM) is employed in the proposed work. The standard convolutional blocks in YOLOv8 backbone are replaced with MSAN, wherein the fixed-size pooling in the spatial attention mechanism of CBAM is replaced with a Pyramid Pooling Mechanism (PPM). The PPM employs adaptive average pooling at multiple resolutions to capture multi-scale contextual information, which is subsequently fused into a unified feature representation. This enables the spatial attention mechanism in MSAN to capture both global facial context and local region-level cues simultaneously, leading to superior robustness to scale variations, partial occlusions, and diverse expression variations. The work is evaluated on benchmark wild datasets including RAF-DB, FER2013, and AffectNet, with all experiments performed using 5-fold cross-validation. Experimental results demonstrate that the multi-scale attention network with PPM in YOLOv8 backbone achieved improvement in classification accuracy and robustness when compared with the state-of-the-art methods for expression classification in the wild. These findings highlight the effectiveness of integrating MSAN into lightweight detection-based backbones for real-world FER applications.

In this paper, we propose an automatic image comment algorithm the state-of-the-art algorithm of image description. We employ an encoder-decoder model to extract the image feature in a deep learning style. In addition, an attention mechanism is added into the deep model for more efficient feature extraction. The model is trained and parameterized with the image comment dataset proposed in this paper. After training, the obtained deep model can generate comments automatically for a given image. In the experiment part, we evaluate the proposed method using both subjective way and objective way. We found that the proposed method can generate reasonable comments from the perspective of human beings. Meanwhile, the model was adjusted to achieve the best effect based on evaluation indexes such as BLEU and CIDEr.

The Internet of Things (IoT) with advanced machine learning techniques presents significant potential for agricultural applications, particularly in the domain of crop disease detection. Paddy, a staple food for millions, is highly susceptible to various diseases that can drastically affect yield and quality. Early and accurate disease detection is crucial for effective management and mitigation. Traditional methods are often labor-intensive and less reliable, underscoring the need for automated, accurate, and scalable solutions. The primary challenge lies in developing a robust system capable of accurately identifying diseases in paddy leaves using IoT-collected data. This task is complicated by the variability in disease manifestation and environmental conditions, which can affect the quality and consistency of the collected data. Efficient feature extraction and classification techniques are essential to address these issues and ensure high accuracy. This study proposes a novel approach combining Particle Swarm Optimization (PSO) for feature extraction with Deep Belief Networks (DBNs) for classification. IoT devices capture high-resolution images of paddy leaves, which are then processed in the cloud. PSO is employed to optimize the feature extraction process by selecting the most relevant features from the image data. These optimized features are fed into a DBN, which is trained to classify the images into healthy or diseased categories. The use of cloud computing ensures the scalability and computational efficiency of the system. The proposed method demonstrates significant improvements in accuracy and processing speed. The PSO-based feature extraction enhances the relevance of features, reducing the dimensionality and improving the DBN''s performance. Experimental results show an accuracy rate of 96.3%, with a reduction in processing time by 35% compared to traditional methods. The system''s precision and recall rates are 95.8% and 94.7%, respectively, highlighting its effectiveness in real-world applications.

formula omitted]-SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry

Industrial water withdrawal prediction is the cornerstone of water resources monitoring and early warning, as well as a key task in implementing rigid constraints on water resources. Although many factors may influence water withdrawal, they are difficult to obtain. Extracting the features in the historical water withdrawal data itself is a more convenient alternative way to achieve accurate prediction. However, due to the lack of significant regularity and periodicity in industrial water data, feature extraction is challenging. In this paper, a multi-head attention encoder (MAEN) model consisting of multi-head attention mechanisms and feed-forward neural networks is proposed to enable more convenient and accurate forecasting. The multi-head attention mechanism allows to focus on different parts of the data simultaneously, detecting complex dependencies, and extracting key features from historical data to enable more efficient feature extraction. Applied to water withdrawal data from real factories, the proposed model outperforms common time series prediction models including artificial neural network, long short-term memory, and gate recurrent unit. Compared to the best-performing comparison model, MAEN shows a reduction of mean squared error by 3.2% for 1 day ahead predictions, and 8.9% for 7 days ahead predictions, illustrating its superior performance in industrial water withdrawal prediction.

Camera shake and object movement are the two prime causes of blurred images. Efficient feature extraction is crucial for deblurring. Although the existing methods have achieved remarkable achievements in the deblurring task, there is still room for improvement in effects. In this paper, we propose an efficient architecture called the feature catcher network(FCN). In this multi-stage FCN architecture, the following design allows us to achieve improvements in performance. Firstly, we propose to apply different calculated trust ratios to the output results of different stages before calculating losses and then carry out the cumulative evaluation to update parameters for backpropagation. Secondly, we have improved Transformer to create a query-key mechanism that is effect-friendly to the deblurring task. Thirdly, we propose a multi-stage attention block to make up for the loss of information in high-level feature extraction. And the enhanced feature extraction block is employed to capture detailed information to ensure a greater degree of image recovery. Fourthly, besides considering detailed features and high-level features at the same stage, we also construct residual supplements for blurry images in the raw information mechanism. The experimental results on several datasets demonstrate that our model(FCN) outperforms state-of-the-art methods in terms of deblurring effect. The code and models will be available at https://github.com/XinyueZhangqdu/FCN.