Multi-scale Information Research Articles

Establishing effective learning bridge cross multi-scale feature maps for object detection and semantic segmentation

ABSTRACT In the field of image object detection and semantic segmentation, improving the accuracy of object identification and segmentation is a primary goal. To achieve this, leveraging the potential of multi-scale information through feature map refinement and fusion has been widely recognized. However, existing feature fusion methods either design more complex feature pyramid networks, replace existing detectors, or incrementally introduce feature fusion modules, overlooking the effective approach of enhancing spatial information in deep feature maps. We propose a novel pluggable feature fusion paradigm termed ‘Effective Learning Bridge’. Our research introduces an efficient and adaptive learning mechanism that builds learning bridges between feature maps at different scales within the feature pyramid, thereby enhancing the spatial information of objects in deep feature maps. This mechanism is specifically designed for multi-scale feature maps and can be seamlessly integrated into any network incorporating feature maps. By altering the model’s backpropagation path, we successfully improve learning efficiency, which in turn enhances the accuracy of object detection and segmentation. Our proposed paradigm and method were extensively evaluated through experiments on SIMD, HRSID, and WHDLD datasets and benchmark models. The results unequivocally demonstrate the effectiveness of our approach in significantly improving the accuracy of object detection and semantic segmentation, as well as the overall learning efficiency of the model.

AEFF-SSC: an attention-enhanced feature fusion for 3D semantic scene completion

Abstract Three-dimensional (3D) occupancy perception technology aims to enable autonomous vehicles to observe and understand dense 3D environments. Estimating the complete geometry and semantics of a scene solely from visual images is challenging. However, humans can easily conceive the complete form of objects based on partial key information and their own experience. This ability is crucial for recognizing and interpreting the surrounding environment. To equip 3D occupancy perception systems with a similar capability, a 3D semantic scene completion method called AEFF-SSC is proposed. This method deeply explores boundary and multi-scale information in voxels, aiming to reconstruct 3D geometry more accurately. We have specifically designed an attention-enhanced feature fusion module that effectively fuses image feature information from different scales and focuses on feature boundary information, thereby more efficiently extracting voxel features. Additionally, we introduce a semantic segmentation module driven by a 3D attention-UNet network. This module combines a 3D U-Net network with a 3D attention mechanism. Through feature fusion and feature weighting, it aids in restoring 3D spatial information and significantly improves the accuracy of segmentation results. Experimental verification on the SemanticKITTI dataset demonstrates that AEFF-SSC significantly outperforms other existing methods in terms of both geometry and semantics. Specifically, within a 12.8 m × 12.8 m area ahead, our geometric occupancy accuracy has achieved a significant improvement of 71.58%, and at the same time, the semantic segmentation accuracy has also increased remarkably by 54.20%.

Attenuative Unified U-Net with Conditional PatchMatch Algorithm for Edge Preserving Salient Object Detection

The rise of Deep Neural Networks (DNNs) has significantly boosted salient object detection in computer vision tasks. However, downsampling methods like striding and pooling often introduce bluish artifacts near edges, hindering detection accuracy. To address this, the "Attenuative Unified U-Net with Conditional PatchMatch Algorithm" is proposed. The method employs Gaussian smoothing for noise reduction and depth refinement in preprocessing. In existing methods, the Edge-preserving salient object detection struggles with cluttered backgrounds and connected objects, like a bird on a rock, making it difficult to accurately distinguish edges and salient regions due to shared boundaries. Hence, an Attenuative Unified Backpropagated Entropy UNet is proposed, which integrates an Attention Mechanism that enhance feature map spatial weight assignment, emphasizing features or regions that are judged most relevant for edge and salient region detection. Then, the Cascaded Laplace pyramid is incorporated into the Unified U-Net’s design for multi-scale information processing, capturing contextual details effectively. The Backpropagated Entropy Loss Function is then created to ensure accurate and confident fused image output. The depth map, edge map, and salient area map are combined in the U-Net’s final output layer to create an overall fused image. Next, to addresses depth discontinuity problem a noteworthy novel idea the Conditional PatchMatch Random Field Algorithm (CPMRF), which combines PatchMatch efficiency and CRFs’ contextual modeling. PatchMatch iteratively propagates matches from neighboring patches to find similar patches in the remaining portion of the image and Conditional Random Field (CRF) is the next step, which improves the PatchMatch results by taking into account the connections between the matched patches and their neighboring areas. Hence, the experimental outcomes of the proposed model effectively show the improved detection of edge in salient object detection with better accuracy, precision, recall, MaxF, and F1 score with minimized MAE.

Research on Cattle Behavior Recognition and Multi-Object Tracking Algorithm Based on YOLO-BoT.

In smart ranch management, cattle behavior recognition and tracking play a crucial role in evaluating animal welfare. To address the issues of missed and false detections caused by inter-cow occlusions and infrastructure obstructions in the barn environment, this paper proposes a multi-object tracking method called YOLO-BoT. Built upon YOLOv8, the method first integrates dynamic convolution (DyConv) to enable adaptive weight adjustments, enhancing detection accuracy in complex environments. The C2f-iRMB structure is then employed to improve feature extraction efficiency, ensuring the capture of essential features even under occlusions or lighting variations. Additionally, the Adown downsampling module is incorporated to strengthen multi-scale information fusion, and a dynamic head (DyHead) is used to improve the robustness of detection boxes, ensuring precise identification of rapidly changing target positions. To further enhance tracking performance, DIoU distance calculation, confidence-based bounding box reclassification, and a virtual trajectory update mechanism are introduced, ensuring accurate matching under occlusion and minimizing identity switches. Experimental results demonstrate that YOLO-BoT achieves a mean average precision (mAP) of 91.7% in cattle detection, with precision and recall increased by 4.4% and 1%, respectively. Moreover, the proposed method improves higher order tracking accuracy (HOTA), multi-object tracking accuracy (MOTA), multi-object tracking precision (MOTP), and IDF1 by 4.4%, 7%, 1.7%, and 4.3%, respectively, while reducing the identity switch rate (IDS) by 30.9%. The tracker operates in real-time at an average speed of 31.2 fps, significantly enhancing multi-object tracking performance in complex scenarios and providing strong support for long-term behavior analysis and contactless automated monitoring.

MFHARFNet: Multi-branch feature hybrid and adaptive receptive field network for image segmentation

Abstract Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model's adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.

Mcan-YOLO: An Improved Forest Fire and Smoke Detection Model Based on YOLOv7

Forest fires pose a significant threat to forest resources and wildlife. To balance accuracy and parameter efficiency in forest fire detection, this study proposes an improved model, Mcan-YOLO, based on YOLOv7. In the Neck section, the asymptotic feature pyramid network (AFPN) was employed to effectively capture multi-scale information, replacing the traditional module. Additionally, the content-aware reassembly of features (CARAFE) replaced the conventional upsampling method, further reducing the number of parameters. The normalization-based attention module (NAM) was integrated after the ELAN-T module to enhance the recognition of various fire smoke features, and the Mish activation function was used to optimize model convergence. A real fire smoke dataset was constructed using the mean structural similarity (MSSIM) algorithm for model training and validation. The experimental results showed that, compared to YOLOv7-tiny, Mcan-YOLO improved precision by 4.6%, recall by 6.5%, and mAP50 by 4.7%, while reducing the number of parameters by 5%. Compared with other mainstream algorithms, Mcan-YOLO achieved better precision with fewer parameters.

Classification and extraction method of hidden dangers along railway lines based on semantic segmentation network

ABSTRACT Foreign objects invading high-speed railway lines can cause danger. One existing solution is to use remote sensing images to analyse the dangerous areas along the railway line, thereby providing a certain amount of investigation time. Considering the spatial and temporal resolution characteristics of existing remote sensing technologies in identifying floating objects and the reality of rapid land use changes, this paper identifies areas on the ground where floating objects may be generated by using semantic segmentation techniques oriented to remotely sensed imagery and provides early warnings to staff along the route. However, these regions that need to be analysed have different semantics and scales. To address these challenges, this paper proposes a Dual-branch Parallel Fusion Network (DPFNet) based on Transformer, aimed at enhancing multi-class semantic segmentation in remote sensing images. To leverage global contextual information, we introduce a Swin Transformer-based backbone network, which employs self-attention to capture a comprehensive scene context, facilitating better segmentation by considering the entire scene’s context. For multi-scale semantic features, we propose one approach that involves independent branching feature expression and a Multi-scale Feature Space Fusion Module (MFSFM). The former enriches multi-scale information, while the latter fuses features across different levels to capture diverse semantic features. Experimental results demonstrate that DPFNet can effectively identify the hidden danger area, and the fusion of multi-scale features makes the network more accurately identify and segment the risk area of different sizes, improving the segmentation accuracy and robustness, and is of great significance to the formation of the ‘prevention’ as the core of the railway safety operation.

High-precision and lightweight small-target detection algorithm for low-cost edge intelligence

The proliferation of edge devices driven by advancements in Internet of Things (IoT) technology has intensified the challenge of achieving high-precision small target detection, as it demands extensive computational resources. This amplifies the conflict between the need for precise detection and the requirement for cost-efficiency across numerous edge devices. To solve this problem, this paper introduces an enhanced target detection algorithm, MSGD-YOLO, built upon YOLOv8. The Faster Implementation of CSP Bottleneck with 2 convolutions (C2f) module is enhanced through the integration of the Ghost module and dynamic convolution, resulting in a more lightweight architecture while enhancing feature generation. Additionally, Spatial Pyramid Pooling with Enhanced Local Attention Network (SPPELAN) replaces Spatial Pyramid Pooling Fast (SPPF) to expand the receptive field, optimizing multi-level feature aggregation for improved performance. Furthermore, a novel Multi-Scale Ghost Convolution (MSGConv) and Multi-Scale Generalized Feature Pyramid Network (MSGPFN) are introduced to enhance feature fusion and integrate multi-scale information. Finally, four optimized dynamic convolutional detection heads are employed to capture target features more accurately and improve small target detection precision. Evaluation on the VisDrone2019 dataset shows that compared with YOLOv8-n, MSGD-YOLO improves mAP@50 and mAP@50–95 by 14.1% and 11.2%, respectively. In addition, the model not only achieves a 16.1% reduction in parameters but also attains a processing speed of 24.6 Frames Per Second (FPS) on embedded devices, thereby fulfilling real-time detection requirements.

Weak Edge Target Segmentation Network Based on Dual Attention Mechanism

Segmentation of weak edge targets such as glass and plastic poses a challenge in the field of target segmentation. The detection process is susceptible to background interference and various external factors due to the transparent nature of these materials. To address this issue, this paper introduces a segmentation network for weak edge target objects (WETS-Net). To effectively extract edge information of such objects and eliminate redundant information during feature extraction, a dual-attention mechanism is employed, including the Edge Attention Extraction Module (EAEM) and the Multi-Scale Information Fusion Module (MIFM). Specifically, the EAEM combines improved edge feature extraction kernels to selectively enhance the importance of edge features, aiding in more precise target region extraction. The MIFM utilizes spatial attention mechanisms to fuse multi-scale features, reducing background and external interference. These innovations enhance the performance of WETS-Net, offering a new direction for weak edge target segmentation research. Finally, through ablation experiments, the effectiveness of each module is effectively validated. Moreover, the proposed algorithm achieves an average detection accuracy of 95.83% and 96.13% on the dataset and a self-made dataset, respectively, outperforming similar U-Net-improved networks.

SSN: Scale Selection Network for Multi-Scale Object Detection in Remote Sensing Images

The rapid growth of deep learning technology has made object detection in remote sensing images an important aspect of computer vision, finding applications in military surveillance, maritime rescue, and environmental monitoring. Nonetheless, the capture of remote sensing images at high altitudes causes significant scale variations, resulting in a heterogeneous range of object scales. These varying scales pose significant challenges for detection algorithms. To solve the scale variation problem, traditional detection algorithms compute multi-layer feature maps. However, this approach introduces significant computational redundancy. Inspired by the mechanism of cognitive scaling mechanisms handling multi-scale information, we propose a novel Scale Selection Network (SSN) to eliminate computational redundancy through scale attentional allocation. In particular, we have devised a lightweight Landmark Guided Scale Attention Network, which is capable of predicting potential scales in an image. The detector only needs to focus on the selected scale features, which greatly reduces the inference time. Additionally, a fast Reversible Scale Semantic Flow Preserving strategy is proposed to directly generate multi-scale feature maps for detection. Experiments demonstrate that our method facilitates the acceleration of image pyramid-based detectors by approximately 5.3 times on widely utilized remote sensing object detection benchmarks.

TFDNet: A triple focus diffusion network for object detection in urban congestion with accurate multi-scale feature fusion and real-time capability

Vehicle detection in congested urban scenes is essential for traffic control and safety management. However, the dense arrangement and occlusion of multi-scale vehicles in such environments present considerable challenges for detection systems. To tackle these challenges, this paper introduces a novel object detection method, dubbed the triple focus diffusion network (TFDNet). Firstly, the gradient convolution is introduced to construct the C2f-EIRM module, replacing the original C2f module, thereby enhancing the network’s capacity to extract edge information. Secondly, by leveraging the concept of the Asymptotic Feature Pyramid Network on the foundation of the Path Aggregation Network, the triple focus diffusion module structure is proposed to improve the network’s ability to fuse multi-scale features. Finally, the SPPF-ELA module employs an Efficient Local Attention mechanism to integrate multi-scale information, thereby significantly reducing the impact of background noise on detection accuracy. Experiments on the VisDrone 2021 dataset reveal that the average detection accuracy of the TFDNet algorithm reached 38.4%, which represents a 6.5% improvement over the original algorithm; similarly, its mAP50:90 performance has increased by 3.7%. Furthermore, on the UAVDT dataset, the TFDNet achieved a 3.3% enhancement in performance compared to the original algorithm. TFDNet, with a processing speed of 55.4 FPS, satisfies the real-time requirements for vehicle detection.

Constructing three-dimension digital rock with porosity information constraint: A double-network-cycled style-based deep-learning approach

Understanding reservoir properties from geophysical responses necessitates the construction of accurate petrophysical templates based on adequate petrophysical data. However, engineering coring is often limited by complex subsurface conditions and high costs. Artificial intelligence (AI) techniques offer an efficient and economical way to synthesize digital samples. Nevertheless, traditional deep learning approaches may suffer from mode collapse, particularly when generating samples with complex structures from a limited number of training samples. To address this challenge, we propose novel Generative Adversarial Networks (GANs) to controllably generate 3D digital rock samples according to porosity distribution. By employing a style-transfer generator, multi-scale information of 3D digital rock is integrated into the generation process, effectively reducing the risk of mode collapse. Embedding the generator into a double-network-cycled framework further enhances the controllability of conditional information in the generated samples. Our analysis shows that the minimum error between the generated samples and the desired samples in terms of porosity is only 0.07%. A clear contrast is observed in morphological parameters, and differences in pore structure lead to significant variations in mechanical and hydraulic properties between original samples and synthetic samples with similar porosity. This indicates that the property contrast is likely caused by differences in pore structures rather than porosity. These findings will assist in future studies on the effect of pore structure on petrophysical properties and improve the utility of rock physics templates in geophysical inversion.

Two-stage Day-ahead Multi-step Prediction of Wind Power Considering Time-series Information Interaction

With the large-scale development of wind power, high penetration wind power grid connection poses serious challenges to the safe and stable operation of the power system. However, the current accuracy of wind power forecasting is facing bottlenecks due to the limitations of Numerical Weather Prediction (NWP) data. Therefore, this article proposes a two-stage day-ahead multi-step wind power prediction (WPP) scheme that considers temporal information interaction. In the first stage, the next day prediction of wind power is based on historical power and 0∼24 hours NWP data. Then, an embedded deep decomposition module is used to extract predictable components and multi-scale information fusion is performed. In the second stage, the result of day-ahead WPP is obtained based on the extracted predictable components and combined with 24∼48 hours of NWP data. The wind farms in Jilin and Inner Mongolia of China are used to experimental analysis. The results show that the scheme proposed in the article has a better prediction effect compared with other schemes in the paper, which can effectively improve the multi-step prediction accuracy of day-ahead wind power.

GRNet:Geometry Restoration for G-PCC Compressed Point Clouds Using Auxiliary Density Signaling.

The lossy Geometry-based Point Cloud Compression (G-PCC) inevitably impairs the geometry information of point clouds, which deteriorates the quality of experience (QoE) in reconstruction and/or misleads decisions in tasks such as classification. To tackle it, this work proposes GRNet for the geometry restoration of G-PCC compressed large-scale point clouds. By analyzing the content characteristics of original and G-PCC compressed point clouds, we attribute the G-PCC distortion to two key factors: point vanishing and point displacement. Visible impairments on a point cloud are usually dominated by an individual factor or superimposed by both factors, which are determined by the density of the original point cloud. To this end, we employ two different models for coordinate reconstruction, termed Coordinate Expansion and Coordinate Refinement, to attack the point vanishing and displacement, respectively. In addition, 4-byte auxiliary density information is signaled in the bitstream to assist the selection of Coordinate Expansion, Coordinate Refinement, or their combination. Before being fed into the coordinate reconstruction module, the G-PCC compressed point cloud is first processed by a Feature Analysis Module for multiscale information fusion, in which kNN-based Transformer is leveraged at each scale to adaptively characterize neighborhood geometric dynamics for effective restoration. Following the common test conditions recommended in the MPEG standardization committee, GRNet significantly improves the G-PCC anchor and remarkably outperforms state-of-the-art methods on a great variety of point clouds (e.g., solid, dense, and sparse samples) both quantitatively and qualitatively. Meanwhile, GRNet runs fairly fast and uses a smaller-size model when compared with existing learning-based approaches, making it attractive to industry practitioners.

MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification

The main challenge in the Visible-Infrared Person Re-Identification (VI-ReID) task lies in extracting discriminative features from different modalities for matching purposes. While existing studies primarily focus on reducing modal discrepancies, the modality information fails to be thoroughly exploited. To solve this problem, the Multi-scale Semantic Correlation Mining network (MSCMNet) is proposed to comprehensively exploit semantic features at multiple scales. The network fuses shallow-level features into the deep network through dimensionality reduction and mapping, and the fused features are utilized to minimize modality information loss in feature extraction. Firstly, considering the effective utilization of modality information, the Multi-scale Information Correlation Mining Block (MIMB) is designed to fuse features at different scales and explore the semantic correlation of fusion features. Secondly, in order to enrich the semantic information that MIMB can utilize, the Quadruple-stream Feature Extractor (QFE) with non-shared parameters is specifically designed to extract information from different dimensions of the dataset. Finally, the Quadruple Center Triplet Loss (QCT) is further proposed to address the information discrepancy in the comprehensive features. Extensive experiments on the SYSU-MM01, RegDB, and LLCM datasets demonstrate that the proposed MSCMNet achieves the greatest accuracy. We release the source code on https://github.com/Hua-XC/MSCMNet.

Multi-scale attention in attention neural network for single image deblurring

Image deblurring, which eliminates blurring artifacts to recover details from a given input image, represents an important task for the computer vision field. Recently, the attention mechanism with deep neural networks (DNN) demonstrates promising performance of image deblurring. However, they have difficulty learning complex blurry and sharp relationships through a balance of spatial detail and high-level contextualized information. Moreover, most existing attention-based DNN methods fail to selectively exploit the information from attention and non-attention branches. To address these challenges, we propose a new approach called Multi-Scale Attention in Attention (MSAiA) for image deblurring. MSAiA incorporates dynamic weight generation by leveraging the joint dependencies of channel and spatial information, allowing for adaptive changes to the weight values in attention and non-attention branches. In contrast to existing attention mechanisms that primarily consider channel or spatial dependencies and do not adequately utilize the information from attention and non-attention branches, our proposed AiA design combines channel-spatial attention. This attention mechanism effectively utilizes the dependencies between channel-spatial information to allocate weight values for attention and non-attention branches, enabling the full utilization of information from both branches. Consequently, the attention branch can more effectively incorporate useful information, while the non-attention branch avoids less useful information. Additionally, we employ a novel multi-scale neural network that aims to learn the relationships between blurring artifacts and the original sharp image by further exploiting multi-scale information. The experimental results prove that the proposed MSAiA achieves superior deblurring performance compared with the state-of-the-art methods.

A three-stage model for camouflaged object detection

Camouflaged objects are typically assimilated into their backgrounds and exhibit fuzzy boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their surroundings pose significant challenges in accurately locating and segmenting these objects in their entirety. While existing methods have demonstrated remarkable performance in various real-world scenarios, they still face limitations when confronted with difficult cases, such as small targets, thin structures, and indistinct boundaries. Drawing inspiration from human visual perception when observing images containing camouflaged objects, we propose a three-stage model that enables coarse-to-fine segmentation in a single iteration. Specifically, our model employs three decoders to sequentially process subsampled features, cropped features, and high-resolution original features. This proposed approach not only reduces computational overhead but also mitigates interference caused by background noise. Furthermore, considering the significance of multi-scale information, we have designed a multi-scale feature enhancement module that enlarges the receptive field while preserving detailed structural cues. Additionally, a boundary enhancement module has been developed to enhance performance by leveraging boundary information. Subsequently, a mask-guided fusion module is proposed to generate fine-grained results by integrating coarse prediction maps with high-resolution feature maps. Our network shows superior performance without introducing unnecessary complexities. Upon acceptance of the paper, the source code will be made publicly available at https://github.com/clelouch/TSNet.

A multiscale approach for network intrusion detection based on variance–covariance subspace distance and EQL v2

As an important network defense approach, network intrusion detection is mainly used to identify anomaly traffic behavior. However, dominant network intrusion detection approaches are now struggling to identify the complex and variable means of attack, leading to high false alarm rate. Additionally, the feature redundancy and class imbalance problem in the intrusion detection dataset also constrain the performance of detection methods. This paper proposes a multiscale intrusion detection approach based on variance–covariance subspace distance and Equalization Loss v2 (EQL v2). Firstly, the variance–covariance subspace distance is used for feature selection on the preprocessed dataset to determine a set of representative feature subsets that can effectively approximate the original feature space. Secondly, the loss function, EQL v2, is adopted to balance the positive and negative gradients, addressing the class imbalance problem. Finally, a pyramid depthwise separable convolution model is proposed to capture the multiscale information of the traffic, and the convolutional layer in the depthwise convolution is replaced with self-supervised predictive convolutional attention block to compensate for the performance loss caused by the parameter reduction. Extensive experiments demonstrated that the proposed approach exhibits better performance on the three datasets of NSL-KDD, UNSW_NB15, and CIC-IDS-2017, with accuracy rates of 99.19%, 97.81%, and 99.83%, respectively, effectively improve the intrusion detection performance.

Experimental Design of Steel Surface Defect Detection Based on MSFE-YOLO—An Improved YOLOV5 Algorithm with Multi-Scale Feature Extraction

Integrating artificial intelligence (AI) technology into student training programs is strategically crucial for developing future professionals with both forward-thinking capabilities and practical skills. This paper uses steel surface defect detection as a case study to propose a simulation-based teaching method grounded in deep learning. The method encompasses the entire process from data preprocessing and model training to validation analysis and innovation optimization with the goal of deepening students’ understanding of AI technology and enhancing their ability to apply it to real-world scenarios. We have designed an experimental framework that incorporates the Efficient Multi-Scale Attention (EMA) mechanism into the Backbone network. This approach helps students understand the principles of feature extraction and the core functions of attention mechanisms. Additionally, we introduced a novel architecture—Convolution 3 Dilated Convolution X (C3DX)—into the Neck network. This architecture effectively expands the network’s receptive field, improves its ability to capture multi-scale information, and thus enhances defect detection accuracy. Furthermore, the implementation of the Efficient Intersection over Union (EIoU) loss function optimizes the bounding box predictions, further increasing the model’s accuracy and robustness. Overall, the teaching design not only ensures that the content remains at the cutting edge of technology but also emphasizes its practicality and operability. This approach enables students to effectively apply theoretical knowledge to real-world engineering projects.

Narrow road extraction from high-resolution remote sensing images: SWGE-Net and MSIF-Net

ABSTRACT Accurate and complete road network extraction plays a critical role in urban planning, street navigation, and emergency response. At present, narrow roads are a main feature in most public road datasets. However, the continuity and boundary completeness of the extraction results for these narrow roads are relatively poor, due to their varied shapes, uneven spatial distribution, and the presence of various interfering elements. To address these issues, this study introduces a novel network, the Self-weighted Global Context Road Extraction Network (SWGE-Net), which integrates a dilate block and an improved coordinate attention mechanism to effectively capture the complex details and spatial information of narrow roads. Furthermore, most public road training datasets often lack labels for very narrow roads, this omission leads to poor extraction results for these roads in test datasets. In order to further improve the extraction capability for unlabeled, extremely narrow roads, this study introduces another network called the Multi-scale Information Fusion Road Extraction Network (MSIF-Net), which uses the same encoders as SWGE-Net and has a special module for merging information at different scales. This module, with a dilate block and pyramid pooling-based decoder, makes the network better at recognizing and combining features of different sizes. Experimental results indicate that SWGE-Net outperforms the baseline network with road IoU scores of 71.57% and 60.67% on the DeepGlobe and CHN6-CUG road datasets, respectively an improvement of 18.51% and 5.40%. Meanwhile, MSIF-Net not only exceeds the baseline in road IoU scores for both datasets, but also achieves the best performance in extracting unlabeled, extremely narrow roads in qualitative experiments.