Search

Scene text detection is an important research field in computer vision, playing a crucial role in various application scenarios. However, existing scene text detection methods often fail to achieve satisfactory results when faced with text instances of different sizes, shapes, and complex backgrounds. To address the challenge of detecting diverse texts in natural scenes, this paper proposes a multi-scale natural scene text detection method based on attention feature extraction and cascaded feature fusion. This method combines global and local attention through an improved attention feature fusion module (DSAF) to capture text features of different scales, enhancing the network's perception of text regions and improving its feature extraction capabilities. Simultaneously, an improved cascaded feature fusion module (PFFM) is used to fully integrate the extracted feature maps, expanding the receptive field of features and enriching the expressive ability of the feature maps. Finally, to address the cascaded feature maps, a lightweight subspace attention module (SAM) is introduced to partition the concatenated feature maps into several sub-space feature maps, facilitating spatial information interaction among features of different scales. In this paper, comparative experiments are conducted on the ICDAR2015, Total-Text, and MSRA-TD500 datasets, and comparisons are made with some existing scene text detection methods. The results show that the proposed method achieves good performance in terms of accuracy, recall, and F-score, thus verifying its effectiveness and practicality. [ABSTRACT FROM AUTHOR]

Accurate identification of Seriola dumerili (SD) offers crucial technical support for aquaculture practices and behavioral research of this species. However, the task of discerning S. dumerili from complex underwater settings, fluctuating light conditions, and schools of fish presents a challenge. This paper proposes an intelligent recognition model based on the YOLOv8 network called SD-YOLOv8. By adding a small object detection layer and head, our model has a positive impact on the recognition capabilities for both close and distant instances of S. dumerili, significantly improving them. We construct a convenient S. dumerili dataset and introduce the deformable convolution network v2 (DCNv2) to enhance the information extraction process. Additionally, we employ the bottleneck attention module (BAM) and redesign the spatial pyramid pooling fusion (SPPF) for multidimensional feature extraction and fusion. The Inner-MPDIoU bounding box regression function adjusts the scale factor and evaluates geometric ratios to improve box positioning accuracy. The experimental results show that our SD-YOLOv8 model achieves higher accuracy and average precision, increasing from 89.2% to 93.2% and from 92.2% to 95.7%, respectively. Overall, our model enhances detection accuracy, providing a reliable foundation for the accurate detection of fishes. [ABSTRACT FROM AUTHOR]

Accurate and rapid response in complex driving scenarios is a challenging problem in autonomous driving. If a target is detected, the vehicle will not be able to react in time, resulting in fatal safety accidents. Therefore, the application of driver assistance systems requires a model that can accurately detect targets in complex scenes and respond quickly. In this paper, a lightweight feature extraction model, ShuffDet, is proposed to replace the CSPDark53 model used by YOLOX by improving the YOLOX algorithm. At the same time, an attention mechanism is introduced into the path aggregation feature pyramid network (PAFPN) to make the network focus more on important information in the network, thereby improving the accuracy of the model. This model, which combines two methods, is called ShuffYOLOX, and it can improve the accuracy of the model while keeping it lightweight. The performance of the ShuffYOLOX model on the KITTI dataset is tested in this paper, and the experimental results show that compared to the original network, the mean average precision (mAP) of the ShuffYOLOX model on the KITTI dataset reaches 92.20%. In addition, the number of parameters of the ShuffYOLOX model is reduced by 34.57%, the Gflops are reduced by 42.19%, and the FPS is increased by 65%. Therefore, the ShuffYOLOX model is very suitable for autonomous driving applications. [ABSTRACT FROM AUTHOR]

The detection algorithm commonly misses obscured pedestrians in traffic scenes with a high pedestrian density because mutual occlusion among pedestrians reduces the prediction box score of the concealed pedestrians. The paper uses the YOLOv7 algorithm as the baseline and makes the following three improvements by investigating the variables influencing the detection method's performance: First, the backbone network of the YOLOv7 algorithm is replaced with the lightweight feature extraction network Mobilenetv3 since the pedestrian detection algorithm frequently needs to be deployed in driverless mobile, which requires a fast operating speed of the algorithm; second, a high-resolution feature pyramid structure is suggested for the issue of missed detection of hidden pedestrians, which upscales the feature maps generated from the feature pyramid to increase the resolution of the output feature maps and introduces shallow feature maps to strengthen the distinctions between adjacent sub-features to enhance the network's ability to extract features for the visible area of hidden pedestrians and small-sized pedestrians in order to produce deeper features with greater differentiation for pedestrians; and the third is to suggest a detection head based on an attention mechanism that is employed to lower the confidence level of target neighboring sub-features, lower the quantity of redundant detection boxes, and lower the following NMS computation. The mAP of the suggested approach in this work achieves 89.75%, which is 9.5 percentage points better than the YOLOv7 detection algorithm, according to experiments on the CrowdHuman pedestrian-intensive dataset. The algorithm proposed in this paper can considerably increase the detection performance of the detection algorithm, particularly for obscured pedestrians and small-sized pedestrians in the dataset, according to the experimental effect plots. [ABSTRACT FROM AUTHOR]

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from the camera. For image feature extraction, the ResNet50 + FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and voxel fusion methods. After information fusion, the Coordinate and SimAM attention mechanisms extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm; the proposed algorithm improves the mAP value by 7.9% in the BEV view and 7.8% in the 3D view at IOU = 0.5 (cars) and IOU = 0.25 (pedestrians and cyclists). At IOU = 0.7 (cars) and IOU = 0.5 (pedestrians and cyclists), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms. [ABSTRACT FROM AUTHOR]

Text summarization is an information compression technology to extract important information from long text, which has become a challenging research direction in the field of natural language processing. At present, the text summary model based on deep learning has shown good results, but how to more effectively model the relationship between words, more accurately extract feature information and eliminate redundant information is still a problem of concern. This paper proposes a graph neural network model GA-GNN based on gated attention, which effectively improves the accuracy and readability of text summarization. First, the words are encoded using a concatenated sentence encoder to generate a deeper vector containing local and global semantic information. Secondly, the ability to extract key information features is improved by using gated attention units to eliminate local irrelevant information. Finally, the loss function is optimized from the three aspects of contrastive learning, confidence calculation of important sentences, and graph feature extraction to improve the robustness of the model. Experimental validation was conducted on a CNN/Daily Mail dataset and MR dataset, and the results showed that the model in this paper outperformed existing methods. [ABSTRACT FROM AUTHOR]

The human visual attention system plays an important role in infrared target recognition because it can quickly and accurately recognize infrared small targets and has good scene adaptability. This paper proposes an infrared small target detection method based on an attention mechanism, which consists of three modules: a bottom-up passive attention module, a top-down active attention module, and decision feedback equalization. In the top-down active attention module, given the Gaussian characteristics of infrared small targets, the idea of combining knowledge-experience Gaussian shape features is applied to implement feature extraction, and quaternion cosine transform is performed to achieve multi-dimensional fusion of Gaussian shape features, thereby achieving complementary fusion of multi-dimensional feature information. In the bottom-up passive attention module, considering that the difference in contrast and motion between the target and the background can attract attention easily, an optimal fast local contrast algorithm and improved circular pipeline filtering are adopted to find candidate target regions. Meanwhile, the multi-scale Laplacian of the Gaussian filter is adopted to estimate the optimal size of the infrared small target. The fast local contrast algorithm based on box filter acceleration and structure optimization is employed to extract local contrast features, and candidate target regions can be obtained by using an adaptive threshold. Besides, the mean gray, target size, Gaussian consistency, and circular region constraint are used in pipeline filtering to extract motion regions, and the false-alarm rate is reduced effectively. Finally, decision feedback equalization is adopted to obtain real targets. Experiments are conducted on some real infrared images involving complex backgrounds with sea, sky, and ground clutters, and the experimental results indicate that the proposed method can achieve better detection performance than conventional baseline methods, such as RLCM, ILCM, PQFT, MPCM, and ADMD. Also, mathematical proofs are provided to validate the proposed method. [ABSTRACT FROM AUTHOR]

Lane detection is a vital component of intelligent driving systems, offering indispensable functionality to keep the vehicle within its designated lane, thereby reducing the risk of lane departure. However, the complexity of the traffic environment, coupled with the rapid movement of vehicles, creates many challenges for detection tasks. Current lane detection methods suffer from issues such as low feature extraction capability, poor real-time detection, and inadequate robustness. Addressing these issues, this paper proposes a lane detection algorithm that combines an online re-parameterization ResNet with a hybrid attention mechanism. Firstly, we replaced standard convolution with online re-parameterization convolution, simplifying the convolutional operations during the inference phase and subsequently reducing the detection time. In an effort to enhance the performance of the model, a hybrid attention module is incorporated to enhance the ability to focus on elongated targets. Finally, a row anchor lane detection method is introduced to analyze the existence and location of lane lines row by row in the image and output the predicted lane positions. The experimental outcomes illustrate that the model achieves F1 scores of 96.84% and 75.60% on the publicly available TuSimple and CULane lane datasets, respectively. Moreover, the inference speed reaches a notable 304 frames per second (FPS). The overall performance outperforms other detection models and fulfills the requirements of real-time responsiveness and robustness for lane detection tasks. [ABSTRACT FROM AUTHOR]

To address the problems of gradient vanishing and limited feature extraction capability of traditional CNN spectrum sensing methods in deep network structures and to effectively avoid network degradation issues under deep network structures, this paper proposes a collaborative spectrum sensing method based on Residual Dense Network and attention mechanisms. This method involves stacking and normalizing the time-domain information of the signal, constructing a two-dimensional matrix, and mapping it to a grayscale image. The grayscale images are divided into training and testing sets, and the training set is used to train the neural network to extract deep features. Finally, the test set is fed into the well-trained neural network for spectrum sensing. Experimental results show that, under low signal-to-noise ratios, the proposed method demonstrates superior spectral sensing performance compared to traditional collaborative spectrum sensing methods. [ABSTRACT FROM AUTHOR]

Defect detection of track fasteners is a prerequisite for safe and reliable railroad operation. The traditional manual visual inspection method has been unable to meet the growing demand for railroad network inspection in China. To achieve the need for accurate, fast, and intelligent detection of rail fasteners, this paper proposes a rail fastener defect detection model based on improved YOLOv5s. Firstly, the convolutional block attention module (CBAM) is added to the Neck network of the YOLOv5s model to enhance the extraction of essential features by the model and suppress the information of minor features. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to realize the multi-scale feature fusion of the model. Finally, the K-means++ algorithm is used to re-cluster the dataset to obtain the anchor box suitable for the fastener dataset and improve the positioning ability of the model. The experimental results show that the improved model achieves an average mean precision (mAP) of 97.4%, a detection speed of 27.3 FPS, and a model memory occupancy of 15.5 M. Compared with the existing target detection model, the improved model has the advantages of high detection accuracy, fast detection speed, and small model memory occupation, which can provide technical support for edge deployment of rail fastener defect detection. [ABSTRACT FROM AUTHOR]

Camouflaged object detection (COD) aims to segment those camouflaged objects that blend perfectly into their surroundings. Due to the low boundary contrast between camouflaged objects and their surroundings, their detection poses a significant challenge. Despite the numerous excellent camouflaged object detection methods developed in recent years, issues such as boundary refinement and multi-level feature extraction and fusion still need further exploration. In this paper, we propose a novel multi-level feature integration network (MFNet) for camouflaged object detection. Firstly, we design an edge guidance module (EGM) to improve the COD performance by providing additional boundary semantic information by combining high-level semantic information and low-level spatial details to model the edges of camouflaged objects. Additionally, we propose a multi-level feature integration module (MFIM), which leverages the fine local information of low-level features and the rich global information of high-level features in adjacent three-level features to provide a supplementary feature representation for the current-level features, effectively integrating the full context semantic information. Finally, we propose a context aggregation refinement module (CARM) to efficiently aggregate and refine the cross-level features to obtain clear prediction maps. Our extensive experiments on three benchmark datasets show that the MFNet model is an effective COD model and outperforms other state-of-the-art models in all four evaluation metrics ( S α , E ϕ , F β w , and M A E ). [ABSTRACT FROM AUTHOR]

Since light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images; that is, the underwater polarization images are fused with intensity images using the deep learning method. To construct a training dataset, we establish an experimental setup to obtain underwater polarization images and perform appropriate transformations to expand the dataset. Next, an end-to-end learning framework based on unsupervised learning and guided by an attention mechanism is constructed for fusing polarization and light intensity images. The loss function and weight parameters are elaborated. The produced dataset is used to train the network under different loss weight parameters, and the fused images are evaluated based on different image evaluation metrics. The results show that the fused underwater images are more detailed. Compared with light intensity images, the information entropy and standard deviation of the proposed method increase by 24.48% and 139%. The image processing results are better than other fusion-based methods. In addition, the improved U-net network structure is used to extract features for image segmentation. The results show that the target segmentation based on the proposed method is feasible under turbid water. The proposed method does not require manual adjustment of weight parameters, has faster operation speed, and has strong robustness and self-adaptability, which is important for research in vision fields, such as ocean detection and underwater target recognition. [ABSTRACT FROM AUTHOR]

Individual identification of pigs is a critical component of intelligent pig farming. Traditional pig ear-tagging requires significant human resources and suffers from issues such as difficulty in recognition and low accuracy. This paper proposes the YOLOv5-KCB algorithm for non-invasive identification of individual pigs. Specifically, the algorithm utilizes two datasets—pig faces and pig necks—which are divided into nine categories. Following data augmentation, the total sample size was augmented to 19,680. The distance metric used for K-means clustering is changed from the original algorithm to 1-IOU, which improves the adaptability of the model's target anchor boxes. Furthermore, the algorithm introduces SE, CBAM, and CA attention mechanisms, with the CA attention mechanism being selected for its superior performance in feature extraction. Finally, CARAFE, ASFF, and BiFPN are used for feature fusion, with BiFPN selected for its superior performance in improving the detection ability of the algorithm. The experimental results indicate that the YOLOv5-KCB algorithm achieved the highest accuracy rates in pig individual recognition, surpassing all other improved algorithms in average accuracy rate (IOU = 0.5). The accuracy rate of pig head and neck recognition was 98.4%, while the accuracy rate for pig face recognition was 95.1%, representing an improvement of 4.8% and 13.8% over the original YOLOv5 algorithm. Notably, the average accuracy rate of identifying pig head and neck was consistently higher than pig face recognition across all algorithms, with YOLOv5-KCB demonstrating an impressive 2.9% improvement. These results emphasize the potential for utilizing the YOLOv5-KCB algorithm for precise individual pig identification, facilitating subsequent intelligent management practices. [ABSTRACT FROM AUTHOR]

Accurate diagnosis of pear tree nutrient deficiency symptoms is vital for the timely adoption of fertilization and treatment. This study proposes a novel method on the fused feature multi-head attention recording network with image depth and shallow feature fusion for diagnosing nutrient deficiency symptoms in pear leaves. First, the shallow features of nutrient-deficient pear leaf images are extracted using manual feature extraction methods, and the depth features are extracted by the deep network model. Second, the shallow features are fused with the depth features using serial fusion. In addition, the fused features are trained using three classification algorithms, F-Net, FC-Net, and FA-Net, proposed in this paper. Finally, we compare the performance of single feature-based and fusion feature-based identification algorithms in the nutrient-deficient pear leaf diagnostic task. The best classification performance is achieved by fusing the depth features output from the ConvNeXt-Base deep network model with shallow features using the proposed FA-Net network, which improved the average accuracy by 15.34 and 10.19 percentage points, respectively, compared with the original ConvNeXt-Base model and the shallow feature-based recognition model. The result can accurately recognize pear leaf deficiency images by providing a theoretical foundation for identifying plant nutrient-deficient leaves. [ABSTRACT FROM AUTHOR]

The grade of wheat quality depends on the proportion of unsound kernels. Therefore, the rapid detection of unsound wheat kernels is important for wheat rating and evaluation. However, in practice, unsound kernels are hand-picked, which makes the process time-consuming and inefficient. Meanwhile, methods based on traditional image processing cannot divide adherent particles well. To solve the above problems, this paper proposed an unsound wheat kernel recognition algorithm based on an improved mask RCNN. First, we changed the feature pyramid network (FPN) to a bottom-up pyramid network to strengthen the low-level information. Then, an attention mechanism (AM) module was added between the feature extraction network and the pyramid network to improve the detection accuracy for small targets. Finally, the regional proposal network (RPN) was optimized to improve the prediction performance. Experiments showed that the improved mask RCNN algorithm could identify the unsound kernels more quickly and accurately while handling adhesion problems well. The precision and recall were 86% and 91%, respectively, and the inference time on the test set with about 200 targets for each image was 7.83 s. Additionally, we compared the improved model with other existing segmentation models, and experiments showed that our model achieved higher accuracy and performance than the other models, laying the foundation for wheat grading. [ABSTRACT FROM AUTHOR]

Corn diseases are one of the significant constraints to high–quality corn production, and accurate identification of corn diseases is of great importance for precise disease control. Corn anthracnose and brown spot are typical diseases of corn, and the early symptoms of the two diseases are similar, which can be easily misidentified by the naked eye. In this paper, to address the above problems, a three–dimensional–two–dimensional (3D–2D) hybrid convolutional neural network (CNN) model combining a band selection module is proposed based on hyperspectral image data, which combines band selection, attention mechanism, spatial–spectral feature extraction, and classification into a unified optimization process. The model first inputs hyperspectral images to both the band selection module and the attention mechanism module and then sums the outputs of the two modules as inputs to a 3D–2D hybrid CNN, resulting in a Y–shaped architecture named Y–Net. The results show that the spectral bands selected by the band selection module of Y–Net achieve more reliable classification performance than traditional feature selection methods. Y–Net obtained the best classification accuracy compared to support vector machines, one–dimensional (1D) CNNs, and two–dimensional (2D) CNNs. After the network pruned the trained Y–Net, the model size was reduced to one–third of the original size, and the accuracy rate reached 98.34%. The study results can provide new ideas and references for disease identification of corn and other crops. [ABSTRACT FROM AUTHOR]

The accuracy of insulators and their defect identification by UAVs (unmanned aerial vehicles) in transmission-line inspection needs to be further improved, and the model size of the detection algorithm is significantly reduced to make it more suitable for edge-end deployment. In this paper, the algorithm uses a lightweight GhostNet module to reconstruct the backbone feature extraction network of the YOLOv4 model and employs depthwise separable convolution in the feature fusion layer. The model is lighter on the premise of ensuring the effect of image information extraction. Meanwhile, the ECA-Net channel attention mechanism is embedded into the feature extraction layer and PANet (Path Aggregation Network) to improve the recognition accuracy of the model for small targets. The experimental results show that the size of the improved model is reduced from 244 MB to 42 MB, which is only 17.3% of the original model. At the same time, the mAp of the improved model is 0.77% higher than that of the original model, reaching 95.4%. Moreover, the mAP compared with YOLOv5-s and YOLOX-s, respectively, is improved by 1.98% and 1.29%. Finally, the improved model is deployed into Jetson Xavier NX and run at a speed of 8.8 FPS, which is 4.3 FPS faster than the original model. [ABSTRACT FROM AUTHOR]

Vehicle detection and tracking technology plays an important role in intelligent transportation management and control systems. This paper proposes a novel vehicle detection and tracking method for small target vehicles to achieve high detection and tracking accuracy based on the attention mechanism. We first develop a new vehicle detection model (YOLOv5-NAM) by adding the normalization-based attention module (NAM) to the classical YOLOv5s model. By exploiting the YOLOv5-NAM model as the vehicle detector, we then propose a real-time small target vehicle tracking method (JDE-YN), where the feature extraction process is embedded in the prediction head for joint training. Finally, we present extensive experimental results to verify our method on the UA-DETRAC dataset and to demonstrate that the method can effectively detect small target vehicles in real time. It is shown that compared with the original YOLOv5s model, the mAP value of the YOLOv5-NAM vehicle detection model is improved by 1.6%, while the MOTA value of the JDE-YN method improved by 0.9% compared with the original JDE method. [ABSTRACT FROM AUTHOR]

Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model. [ABSTRACT FROM AUTHOR]

The attitude sensor of the aircraft can give feedback on the perceived flight attitude information to the input of the flight controller to realize the closed-loop control of the flight attitude. Therefore, the fault diagnosis of attitude sensors is crucial for the flight safety of aircraft, in view of the situation that the existing diagnosis methods fail to give consideration to both the diagnosis rate and the diagnosis accuracy. In this paper, a fast and high-precision fault diagnosis strategy for aircraft sensor is proposed. Specifically, the aircraft's dynamics model and the attitude sensor's fault model are built. The SENet attention mechanism is used to allocate weights for the collected time-domain fault signals and transformed time-frequency signals, and then inject the fused feature signals with weights into the RepVGG based on the convolutional neural network structure for deep feature mining and classification. Experimental results show that the proposed method can achieve good precision speed tradeoff. [ABSTRACT FROM AUTHOR]

To solve the problem of inadequate feature extraction by the model due to factors such as occlusion and illumination in person re-identification tasks, this paper proposed a model with a joint cross-consistency learning and multi-feature fusion person re-identification. The attention mechanism and the mixed pooling module were first embedded in the residual network so that the model adaptively focuses on the more valid information in the person images. Secondly, the dataset was randomly divided into two categories according to the camera perspective, and a feature classifier was trained for the two types of datasets respectively. Then, two classifiers with specific knowledge were used to guide the model to extract features unrelated to the camera perspective for the two types of datasets so that the obtained image features were endowed with domain invariance by the model, and the differences in the perspective, attitude, background, and other related information of different images were alleviated. Then, the multi-level features were fused through the feature pyramid to concern the more critical information of the image. Finally, a combination of Cosine Softmax loss, triplet loss, and cluster center loss was proposed to train the model to address the differences of multiple losses in the optimization space. The first accuracy of the proposed model reached 95.9% and 89.7% on the datasets Market-1501 and DukeMTMC-reID, respectively. The results indicated that the proposed model has good feature extraction capability. [ABSTRACT FROM AUTHOR]

Infrared pedestrian detection has important theoretical research value and a wide range of application scenarios. Because of its special imaging method, infrared images can be used for pedestrian detection at night and in severe weather conditions. However, the lack of pedestrian feature information in infrared images and the small scale of pedestrian objects makes it difficult for detection networks to extract feature information and accurately detect small-scale pedestrians. To address these issues, this paper proposes an infrared pedestrian detection network based on YOLOv5, named IPD-Net. Firstly, an adaptive feature extraction module (AFEM) is designed in the backbone network section, in which a residual structure with stepwise selective kernel was included to enable the model to better extract feature information under different sizes of the receptive field. Secondly, a coordinate attention feature pyramid network (CA-FPN) is designed to enhance the deep feature map with location information through the coordinate attention module, so that the network gains better capability of object localization. Finally, shallow information is introduced into the feature fusion network to improve the detection accuracy of weak and small objects. Experimental results on the large infrared image dataset ZUT show that the mean Average Precision (mAP50) of our model is improved by 3.6% compared to that of YOLOv5s. In addition, IPD-Net shows various degrees of accuracy improvement compared to other excellent methods. [ABSTRACT FROM AUTHOR]

Rails play a vital role in the bearing and guidance of high-speed trains, and the normal condition of rail components is the guarantee of the operation and maintenance safety. Fasteners are critical components for fixing the rails, so it is particularly important to detect whether they are in a normal state or not. The current rail-fastener detection models have some drawbacks, including poor generalization ability, large model volume and low detection efficiency. In view of this, an improved YoLoX-Nano rail-fastener-defect-detection method is proposed in this paper. The CA attention mechanism is added to the three output feature maps of CSPDarknet and the enhanced feature extraction part of the Path Aggregation Feature Pyramid Network (PAFPN); the Adaptively Spatial Feature Fusion (ASFF) is added after the PAFPN output feature map, which enables the semantic information of the high-level features and the fine-grained features of the bottom layer to be further enhanced. The improved YoLoX-Nano model has improved the AP value by 27.42% on fractured fasteners, 15.88% on displacement fasteners and 12.96% on normal fasteners. Moreover, the mAP value is improved by 18.75%, and it is 14.75% higher than the two-stage model Faster-RCNN on mAP. In addition, compared with YoLov7-tiny, the improved YoLoX-Nano model achieves 13.56% improvement on mAP. Although the improved model increases a certain amount of calculation, the detection speed of the improved model has been increased by 30.54 fps and by 32.33 fps when compared with that of the Single-Shot Multi-Box Detector (SSD) model and the You Only Look Once v3 (YoLov3) model, reaching 54.35 fps. The improved YoLoX-Nano model enables accurate and rapid identification of the defects of rail fasteners, which can meet the needs of real-time detection. Furthermore, it has advantages in lightweight deployment of terminals for rail-fastener detection, thus providing some reference for image recognition and detection in other fields. [ABSTRACT FROM AUTHOR]

Low-illumination images exhibit low brightness, blurry details, and color casts, which present us an unnatural visual experience and further have a negative effect on other visual applications. Data-driven approaches show tremendous potential for lighting up the image brightness while preserving its visual naturalness. However, these methods introduce hand-crafted holes and noise enlargement or over/under enhancement and color deviation. For mitigating these challenging issues, this paper presents a frequency division and multiscale learning network named FDMLNet, including two subnets, DetNet and StruNet. This design first applies the guided filter to separate the high and low frequencies of authentic images, then DetNet and StruNet are, respectively, developed to process them, to fully explore their information at different frequencies. In StruNet, a feasible feature extraction module (FFEM), grouped by multiscale learning block (MSL) and a dual-branch channel attention mechanism (DCAM), is injected to promote its multiscale representation ability. In addition, three FFEMs are connected in a new dense connectivity meant to utilize multilevel features. Extensive quantitative and qualitative experiments on public benchmarks demonstrate that our FDMLNet outperforms state-of-the-art approaches benefiting from its stronger multiscale feature expression and extraction ability. [ABSTRACT FROM AUTHOR]

Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research. [ABSTRACT FROM AUTHOR]

In view of the existence of remote sensing images with large variations in spatial resolution, small and dense objects, and the inability to determine the direction of motion, all these components make object detection from remote sensing images very challenging. In this paper, we propose a single-stage detection network based on YOLOv5. This method introduces the MS Transformer module at the end of the feature extraction network of the original network to enhance the feature extraction capability of the network model and integrates the Convolutional Block Attention Model (CBAM) to find the attention area in dense scenes. In addition, the YOLOv5 target detection network is improved by incorporating a rotation angle approach from the a priori frame design and the bounding box regression formulation to make it suitable for rotating frame-based detection scenarios. Finally, the weighted combination of the two difficult sample mining methods is used to improve the focal loss function, so as to improve the detection accuracy. The average accuracy of the test results of the improved algorithm on the DOTA data set is 77.01%, which is higher than the previous detection algorithm. Compared with the average detection accuracy of YOLOv5, the average detection accuracy is improved by 8.83%. The experimental results show that the algorithm has higher detection accuracy than other algorithms in remote sensing scenes. [ABSTRACT FROM AUTHOR]

Change detection (CD) is a particularly important task in the field of remote sensing image processing. It is of practical importance for people when making decisions about transitional situations on the Earth's surface. The existing CD methods focus on the design of feature extraction network, ignoring the strategy fusion and attention enhancement of the extracted features, which will lead to the problems of incomplete boundary of changed area and missing detection of small targets in the final output change map. To overcome the above problems, we proposed a hierarchical attention residual nested U-Net (HARNU-Net) for remote sensing image CD. First, the backbone network is composed of a Siamese network and nested U-Net. We remold the convolution block in nested U-Net and proposed ACON-Relu residual convolution block (A-R), which reduces the missed detection rate of the backbone network in small change areas. Second, this paper proposed the adjacent feature fusion module (AFFM). Based on the adjacency fusion strategy, the module effectively integrates the details and semantic information of multi-level features, so as to realize the feature complementarity and spatial mutual enhancement between adjacent features. Finally, the hierarchical attention residual module (HARM) is proposed, which locally filters and enhances the features in a more fine-grained space to output a much better change map. Adequate experiments on three challenging benchmark public datasets, CDD, LEVIR-CD and BCDD, show that our method outperforms several other state-of-the-art methods and performs excellent in F1, IOU and visual image quality. [ABSTRACT FROM AUTHOR]

Nowadays, faces in videos can be easily replaced with the development of deep learning, and these manipulated videos are realistic and cannot be distinguished by human eyes. Some people maliciously use the technology to attack others, especially celebrities and politicians, causing destructive social impacts. Therefore, it is imperative to design an accurate method for detecting face manipulation. However, most of the existing methods adopt single convolutional neural network as the feature extraction module, causing the extracted features to be inconsistent with the human visual mechanism. Moreover, the rich details and semantic information cannot be reflected with single feature, limiting the detection performance. Therefore, this paper tackles the above problems by proposing a novel face manipulation detection method based on a supervised multi-feature fusion attention network (SMFAN). Specifically, the capsule network is used for face manipulation detection, and the SMFAN is added to the original capsule network to extract details of the fake face image. Further, the focal loss is used to realize hard example mining. Finally, the experimental results on the public dataset FaceForensics++ show that the proposed method has better performance. [ABSTRACT FROM AUTHOR]

In recent years, self-supervised monocular depth estimation has gained popularity among researchers because it uses only a single camera at a much lower cost than the direct use of laser sensors to acquire depth. Although monocular self-supervised methods can obtain dense depths, the estimation accuracy needs to be further improved for better applications in scenarios such as autonomous driving and robot perception. In this paper, we innovatively combine soft attention and hard attention with two new ideas to improve self-supervised monocular depth estimation: (1) a soft attention module and (2) a hard attention strategy. We integrate the soft attention module in the model architecture to enhance feature extraction in both spatial and channel dimensions, adding only a small number of parameters. Unlike traditional fusion approaches, we use the hard attention strategy to enhance the fusion of generated multi-scale depth predictions. Further experiments demonstrate that our method can achieve the best self-supervised performance both on the standard KITTI benchmark and the Make3D dataset. [ABSTRACT FROM AUTHOR]

In production, due to natural conditions or process peculiarities, a single product often may exhibit more than one type of defect. The accurate identification of all defects has an important guiding significance and practical value to improve the planting and production processes. Concerning the surface defect classification task, convolutional neural networks can be implemented as a powerful instrument. However, a typical convolutional neural network tends to consider an image as an inseparable entity and a single instance when extracting features; moreover, it may overlook semantic correlations between different labels. To address these limitations, in the present paper, we proposed a feature-wise attention-based relation network (FAR-Net) for multilabel jujube defect classification. The network included four different modules designed for (1) image feature extraction, (2) label-wise feature aggregation, (3) feature activation and deactivation, and (4) correlation learning among labels. To evaluate the proposed method, a unique multilabel jujube defect dataset was constructed as a benchmark for the multilabel classification task of the jujube defect images. The results of experiments show that owing to the relation learning mechanism, the average precision of the three main composite defects in the dataset increases by 5.77%, 4.07%, and 3.50%, respectively, compared to the backbone of our network, namely Inception v3, which indicated that the proposed FAR-Net effectively facilitated the learning of correlation between labels and eventually, improved the multilabel classification accuracy. [ABSTRACT FROM AUTHOR]

In recent years, increasing image data comes from various sensors, and object detection plays a vital role in image understanding. For object detection in complex scenes, more detailed information in the image should be obtained to improve the accuracy of detection task. In this paper, we propose an object detection algorithm by jointing semantic segmentation (SSOD) for images. First, we construct a feature extraction network that integrates the hourglass structure network with the attention mechanism layer to extract and fuse multi-scale features to generate high-level features with rich semantic information. Second, the semantic segmentation task is used as an auxiliary task to allow the algorithm to perform multi-task learning. Finally, multi-scale features are used to predict the location and category of the object. The experimental results show that our algorithm substantially enhances object detection performance and consistently outperforms other three comparison algorithms, and the detection speed can reach real-time, which can be used for real-time detection. [ABSTRACT FROM AUTHOR]

Deep learning approaches have been recently applied to traffic prediction because of their ability to extract features of traffic data. While convolutional neural networks may improve the predictive accuracy by transiting traffic data to images and extracting features in the images, the convolutional results can be improved by using the global-level representation that is a direct way to extract features. The time intervals are not considered as aspects of convolutional neural networks for traffic prediction. The attention mechanism may adaptively select a sequence of regions and only process the selected regions to better extract features when aspects are considered. In this paper, we propose the attention mechanism over the convolutional result for traffic prediction. The proposed method is based on multiple links. The time interval is considered as the aspect of attention mechanism. Based on the dataset provided by Highways England, the experimental results show that the proposed method can achieve better accuracy than the baseline methods. [ABSTRACT FROM AUTHOR]