Search

Regularly detect the corrosion of metal structures and take countermeasures according to the degree of corrosion, which can reduce the potential safety hazards and avoid unnecessary economic losses. This paper presents a deep learning-based metal corrosion detection method, which is used to accurately segment the corrosion regions. This model incorporates Hybrid Attention Residual Block (HARB) and External Skip Connections (ESC) in the basic architecture of U-Net. HARB can reweight the features so that the network pays more attention to the corrosion regions and ignores other irrelevant regions. Shallow features and deep features are fused using ESC to make the features of network learning more effective and comprehensive, which is conducive to improving the segmentation accuracy. In order to further improve the semantic segmentation performance, the Attention Gate Residual Block (AGRB) is proposed, which can optimize segmentation by strengthening the regions to be segmented and reducing the activation value of the background, while overcoming the semantic and scale inconsistencies between input features. In this paper, comprehensive comparative experiments are conducted on the Metal Corrosion dataset. The experimental results show that the F1 and mIoU of the proposed method are 91.21% and 89.56%, respectively. Compared with U-Net, HEU-Net achieves a 7.91% improvement in F1 and a 10.16% improvement in mIoU. These results show that our method outperforms state-of-the-art models and can achieve better semantic segmentation results. [ABSTRACT FROM AUTHOR]

Unlike 2D images that are represented in regular grids, 3D point clouds are irregular and unordered, hence directly applying convolution neural networks (CNNs) to process point clouds is quite challenging. In this paper, we propose a novel deep neural network named AKNet to achieve point cloud semantic segmentation. The key to our AKNet is the attentive kernel convolution (AKConv), which is a deformed convolution operation for perceiving sufficient local context of 3D scenes. AKConv first constructs the Basic Weight Units that are robust to point's ordering. Then, for capturing the more distinctive local features, the convolution kernels of AKConv are associated with Attentive Weight Units through the self-attentive function acting on Basic Weight Units. Furthermore, 3D point clouds provide richer geometric shape information, which is helpful to recognize objects. However, inputting only raw point features to the convolution function could cause geometric information loss. Thus, we utilize augmented features as input of AKConv. Besides, to preserve the semantic information from the encoding to decoding layers, we introduce the backward encoding (BE) mechanism by utilizing higher-layer semantic features. We conduct experiments on three large-scale point clouds datasets. The experimental results demonstrate that our AKNet outperforms state-of-the-art (SOTA) networks. [ABSTRACT FROM AUTHOR]

Three-dimensional object detection plays a key role in autonomous driving, which becomes extremely challenging in occlusion situations. This paper presents a novel multimodal 3D object detection framework which fuses visual semantic information and depth point cloud information to accurately detect targets with distant object features and occlusion situations. The framework consists of the four steps. Firstly, an improved semantic segmentation network is used to extract semantic information of objects containing similar features. Secondly, semantic images and point clouds are combined to generate pixel-level fusion data so that the semantic information and training capability of sparse and far-point clouds can be improved. Thirdly, a deep learning-based point cloud classification network is used for training of the fused data to output accurate detection frames. Fourthly, an extended Kalman filter is incorporated into point cloud prediction for image-based object detection to further enhance the robustness of object detection. Both Cityscapes and KITTI datasets are used in ablation study and experiments to validate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

Using deep learning in remote sensing interpretation could reduce a lot of human and material costs. Semantic segmentation is the main method for this task. It can automatically outline the objects and it has recently achieved great success in remote sensing images. However, in the appliance of remote sensing interpretation, the accuracy of contour largely determines the evaluation of remote sensing interpretation. Though the current loss functions reflect the segmentation performance, they could not guide the model to optimize itself toward a more precise contour. This paper proposed an exactly defined contour loss (CL) for remote sensing interpretation with Residual Attention U-Net (RA U-Net) as the main framework. The RA U-Net uses the residual attention module as the skip connection layer. It enhances the judgment of U-Net. In CL, image processing methods are used to extract the contours of the foreground. And elements-sum and elements-subtract operations are used to transfer the contour information to a matrix of the same size as label images. Then, these matrices would be the weights for CE. By assigning different weights for different elements in different regions, this function will guide the model to reach a balance between accurate segmentation results and precise contours. The experiment on open datasets shows a good performance. The proposed model was also trained on the Construction Disturbance Dataset collected from Jiang Xi Province, China. The dataset was labeled manually. The evaluation enhanced a lot on the Construction Disturbance Dataset and the IoU on two datasets increased 1 % to 2 % when using CL as the loss function. This paper also compared the proposed method with other state-of-the-art methods and the results showed extensive effectiveness. [ABSTRACT FROM AUTHOR]

In the task of semantic segmentation, researchers often use self-attention module to capture long-range contextual information. These methods are often effective. However, the use of the self-attention module will cause a problem that cannot be ignored, that is, the huge consumption of computing resources. Therefore, how to reduce the resource consumption of the self-attention module under the premise of ensuring performance is a very meaningful research topic. In this paper, we propose a Sparse Attention Model combined with a powerful multi-task feature extraction network for semantic segmentation. Compared with the classic self-attention model, our Sparse Attention Model does not calculate the inner product between pairs of all vectors. Instead, we first sparse the feature block Query and the feature block Key defined in self-attention module through the credit matrix generated by the pre-output. Then, we perform similarity modeling on the two sparse feature blocks. Meanwhile, to ensure that the vectors in Query could capture dense contextual information, we design a Class Attention Module and embed it into Sparse Attention Module. Note that, compared with Dual Attention Network for scene segmentation, our attention module greatly reduces the consumption of computing resources while ensuring the accuracy. Furthermore, in the stage of feature extraction, the use of downsampling will cause serious loss of detailed information and affect the segmentation performance of the network, so we adopt a multi-task feature extraction network. It learns semantic features and edge features in parallel, and we feed the learned edge features into the deep layer of the network to help restore detailed information for capturing high-quality semantic features. We do not use pure concatenation. Instead, we extract the edge features related to each channel by element-wise multiplication before concatenation. Finally, we conduct experiments on three datasets: Cityscapes, PASCAL VOC2012 and ADE20K, and obtain competitive results. [ABSTRACT FROM AUTHOR]

Medical image segmentation is a critical and important step for developing computer-aided system in clinical situations. It remains a complicated and challenging task due to the large variety of imaging modalities and different cases. Recently, Unet has become one of the most popular deep learning frameworks because of its accurate performance in biomedical image segmentation. In this paper, we propose a contour-aware semantic segmentation network, which is an extension of Unet, for medical image segmentation. The proposed method includes a semantic branch and a detail branch. The semantic branch focuses on extracting the semantic features from shallow and deep layers; the detail branch is used to enhance the contour information implied in the shallow layers. In order to improve the representation capability of the network, a MulBlock module is designed to extract semantic information with different receptive fields. Spatial attention module (CAM) is used to adaptively suppress the redundant features. In comparison with the state-of-the-art methods, our method achieves a remarkable performance on several public medical image segmentation challenges. [ABSTRACT FROM AUTHOR]

Semantic segmentation plays a crucial role in the fields of computer vision and computer graphics, with extensive applications in various practical scenarios. Significant progress has been made in semantic segmentation tasks using deep learning-based methods. However, most existing semantic segmentation algorithms focus on good weather conditions, and they face challenges in terms of accuracy and robustness when applied to rainy scenes due to factors such as raindrops, haze, and lighting variations. To address this issue, this paper proposes a rainy-day semantic segmentation method based on a two-stage progressive network. The proposed method consists of two modules: a rain removal module responsible for eliminating raindrops and haze from the input rainy images and restoring the basic structural information of the images, and a segmentation module that performs pixel-level semantic prediction on the rain-removed images. Specifically, the rain removal module introduces two progressive units with shared weights to gradually achieve rain removal. The segmentation module adopts an encoder–decoder architecture, utilizing down-sampling and deep asynchronous bottleneck units for encoding. It also introduces a dual attention-guided fusion module to aggregate channel attention information and spatial attention information, guiding the multiscale feature fusion process in the decoder. Experimental results demonstrate that this method effectively mitigates the influence of rain streaks on semantic segmentation, thereby improving segmentation performance and achieving more accurate and robust semantic segmentation results in rainy conditions. We will provide the code and datasets on https://github.com/zhang152267/TSPN. [ABSTRACT FROM AUTHOR]