scholarly journals Concrete Cracks Detection Based on FCN with Dilated Convolution

2019 ◽  
Vol 9 (13) ◽  
pp. 2686 ◽  
Author(s):  
Jianming Zhang ◽  
Chaoquan Lu ◽  
Jin Wang ◽  
Lei Wang ◽  
Xiao-Guang Yue
Keyword(s):  
Crack Detection ◽  
Receptive Fields ◽  
Semantic Segmentation ◽  
Concrete Surface ◽  
Input Image ◽  
Feature Maps ◽  
Test Set ◽  
Dilated Convolution ◽  
Fully Convolutional Networks ◽  
Segmentation Task

In civil engineering, the stability of concrete is of great significance to safety of people’s life and property, so it is necessary to detect concrete damage effectively. In this paper, we treat crack detection on concrete surface as a semantic segmentation task that distinguishes background from crack at the pixel level. Inspired by Fully Convolutional Networks (FCN), we propose a full convolution network based on dilated convolution for concrete crack detection, which consists of an encoder and a decoder. Specifically, we first used the residual network to extract the feature maps of the input image, designed the dilated convolutions with different dilation rates to extract the feature maps of different receptive fields, and fused the extracted features from multiple branches. Then, we exploited the stacked deconvolution to do up-sampling operator in the fused feature maps. Finally, we used the SoftMax function to classify the feature maps at the pixel level. In order to verify the validity of the model, we introduced the commonly used evaluation indicators of semantic segmentation: Pixel Accuracy (PA), Mean Pixel Accuracy (MPA), Mean Intersection over Union (MIoU), and Frequency Weighted Intersection over Union (FWIoU). The experimental results show that the proposed model converges faster and has better generalization performance on the test set by introducing dilated convolutions with different dilation rates and a multi-branch fusion strategy. Our model has a PA of 96.84%, MPA of 92.55%, MIoU of 86.05% and FWIoU of 94.22% on the test set, which is superior to other models.

Attention U-Net with Feature Fusion Module for Robust Defect Detection

2021 ◽  
pp. 2150272
Author(s):  
Yu-Jie Xiong ◽  
Yong-Bin Gao ◽  
Hong Wu ◽  
Yao Yao
Keyword(s):  
Defect Detection ◽  
Crack Detection ◽  
Feature Fusion ◽  
Experimental Results ◽  
Feature Maps ◽  
Concrete Crack ◽  
Disaster Situation ◽  
Unpredictable Environment ◽  
Segmentation Task ◽  
Noisy Background

U-Net shows a remarkable performance and makes significant progress for segmentation task in medical images. Despite the outstanding achievements, the common case of defect detection in industrial scenes is still a challenging task, due to the noisy background, unpredictable environment, varying shapes and sizes of the defects. Traditional U-Net may not be suitable for low-quality images with low illumination and corruption, which are often presented in the practical collections in real-world scenes. In this paper, we propose an attention U-Net with feature fusion module for combining multi-scale features to detect the defects in noisy images automatically. Feature fusion module contains convolution kernels of different scales to capture shallow layer features and combine them with the high-dimensional features. Meanwhile, attention gates are used to enhance the robustness of skip connection between the feature maps. The proposed method is evaluated on two datasets. The best precision rate and MIoU of defect detection are 95.6% and 92.5%. The best F-score of concrete crack detection is 95.0%. Experimental results show that the proposed approach achieves promising results in both datasets. It demonstrates that our approach consistently outperforms other U-Net-based approaches for defect detection in low-quality images. Experimental results have shown the possibility of developing a mixture system that can be deployed in many applications, such as remote sensing image analysis, earthquake disaster situation assessment, and so on.

scholarly journals Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 717 ◽  
Author(s):  
Gang Li ◽  
Biao Ma ◽  
Shuanhai He ◽  
Xueli Ren ◽  
Qiangwei Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Width ◽  
Crack Detection ◽  
Detection Method ◽  
Learning Algorithm ◽  
Semantic Segmentation ◽  
Fully Convolutional Networks ◽  
Deep Learning Algorithm ◽  
Mean Width

Regular crack inspection of tunnels is essential to guarantee their safe operation. At present, the manual detection method is time-consuming, subjective and even dangerous, while the automatic detection method is relatively inaccurate. Detecting tunnel cracks is a challenging task since cracks are tiny, and there are many noise patterns in the tunnel images. This study proposes a deep learning algorithm based on U-Net and a convolutional neural network with alternately updated clique (CliqueNet), called U-CliqueNet, to separate cracks from background in the tunnel images. A consumer-grade DSC-WX700 camera (SONY, Wuxi, China) was used to collect 200 original images, then cracks are manually marked and divided into sub-images with a resolution of 496   ×   496 pixels. A total of 60,000 sub-images were obtained in the dataset of tunnel cracks, among which 50,000 were used for training and 10,000 were used for testing. The proposed framework conducted training and testing on this dataset, the mean pixel accuracy (MPA), mean intersection over union (MIoU), precision and F1-score are 92.25%, 86.96%, 86.32% and 83.40%, respectively. We compared the U-CliqueNet with fully convolutional networks (FCN), U-net, Encoder–decoder network (SegNet) and the multi-scale fusion crack detection (MFCD) algorithm using hypothesis testing, and it’s proved that the MIoU predicted by U-CliqueNet was significantly higher than that of the other four algorithms. The area, length and mean width of cracks can be calculated, and the relative error between the detected mean crack width and the actual mean crack width ranges from −11.20% to 18.57%. The results show that this framework can be used for fast and accurate crack semantic segmentation of tunnel images.

scholarly journals MICRA-Net: MICRoscopy Analysis Neural Network to solve detection, classification, and segmentation from a single simple auxiliary task

2021 ◽  
Author(s):  
Anthony Bilodeau ◽  
Constantin V.L. Delmas ◽  
Martin Parent ◽  
Paul De Koninck ◽  
Audrey Durand ◽  
...  
Keyword(s):  
Neural Network ◽  
Quantitative Analysis ◽  
High Throughput ◽  
Semantic Segmentation ◽  
Feature Maps ◽  
Expert Annotation ◽  
Microscopy Analysis ◽  
Weakly Supervised ◽  
Segmentation Task ◽  
Microscopy Images

High throughput quantitative analysis of microscopy images presents a challenge due to the complexity of the image content and the difficulty to retrieve precisely annotated datasets. In this paper we introduce a weakly-supervised MICRoscopy Analysis neural network (MICRA-Net) that can be trained on a simple main classification task using image-level annotations to solve multiple the more complex auxiliary semantic segmentation task and other associated tasks such as detection or enumeration. MICRA-Net relies on the latent information embedded within a trained model to achieve performances similar to state-of-the-art fully-supervised learning. This learnt information is extracted from the network using gradient class activation maps, which are combined to generate detailed feature maps of the biological structures of interest. We demonstrate how MICRA-Net significantly alleviates the Expert annotation process on various microscopy datasets and can be used for high-throughput quantitative analysis of microscopy images.

scholarly journals Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation

2019 ◽  
Vol 9 (9) ◽  
pp. 1816 ◽  
Author(s):  
Guangsheng Chen ◽  
Chao Li ◽  
Wei Wei ◽  
Weipeng Jing ◽  
Marcin Woźniak ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Image Segmentation ◽  
High Resolution ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Dilated Convolution ◽  
Segmentation Task ◽  
Fully Connected ◽  
Spatial Pyramid

Recent developments in Convolutional Neural Networks (CNNs) have allowed for the achievement of solid advances in semantic segmentation of high-resolution remote sensing (HRRS) images. Nevertheless, the problems of poor classification of small objects and unclear boundaries caused by the characteristics of the HRRS image data have not been fully considered by previous works. To tackle these challenging problems, we propose an improved semantic segmentation neural network, which adopts dilated convolution, a fully connected (FC) fusion path and pre-trained encoder for the semantic segmentation task of HRRS imagery. The network is built with the computationally-efficient DeepLabv3 architecture, with added Augmented Atrous Spatial Pyramid Pool and FC Fusion Path layers. Dilated convolution enlarges the receptive field of feature points without decreasing the feature map resolution. The improved neural network architecture enhances HRRS image segmentation, reaching the classification accuracy of 91%, and the precision of recognition of small objects is improved. The applicability of the improved model to the remote sensing image segmentation task is verified.

scholarly journals Enet Semantic Segmentation Combined with Attention Mechanism

2021 ◽  
Author(s):  
Wei Bai
Keyword(s):  
Feature Fusion ◽  
Receptive Fields ◽  
Design Feature ◽  
Semantic Segmentation ◽  
Attention Mechanism ◽  
Segmentation Algorithm ◽  
Feature Maps ◽  
Model Learning ◽  
Simple Method ◽  
Feature Map

Abstract Image semantic segmentation is one of the core tasks of computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the different channel and location features of the feature map and the simple method when the feature map is fused, this paper designs a semantic segmentation algorithm that combines the attention mechanism. Firstly, dilated convolution is used, and a smaller downsampling factor is used to maintain the resolution of the image and obtain the detailed information of the image. Secondly, the attention mechanism module is introduced to assign weights to different parts of the feature map, which reduces the accuracy loss. The design feature fusion module assigns weights to the feature maps of different receptive fields obtained by the two paths, and merges them together to obtain the final segmentation result. Finally, through experiments, it was verified on the Camvid, Cityscapes and PASCAL VOC2012 datasets. Mean intersection over union (MIoU) and mean pixel accuracy (MPA) are used as metrics. The method in this paper can make up for the loss of accuracy caused by downsampling while ensuring the receptive field and improving the resolution, which can better guide the model learning. And the proposed feature fusion module can better integrate the features of different receptive fields. Therefore, the proposed method can significantly improve the segmentation performance compared to the traditional method.

scholarly journals SEMANTIC SEGMENTATION OF AERIAL IMAGERY VIA MULTI-SCALE SHUFFLING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP SUPERVISION

2018 ◽  
Vol IV-1 ◽  
pp. 29-36 ◽  
Author(s):  
K. Chen ◽  
M. Weinmann ◽  
X. Sun ◽  
M. Yan ◽  
S. Hinz ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Semantic Segmentation ◽  
Aerial Imagery ◽  
Geometric Features ◽  
Feature Maps ◽  
Multi Scale ◽  
Intermediate Layers ◽  
Segmentation Task ◽  
The Impact

<p><strong>Abstract.</strong> In this paper, we address the semantic segmentation of aerial imagery based on the use of multi-modal data given in the form of true orthophotos and the corresponding Digital Surface Models (DSMs). We present the Deeply-supervised Shuffling Convolutional Neural Network (DSCNN) representing a multi-scale extension of the Shuffling Convolutional Neural Network (SCNN) with deep supervision. Thereby, we take the advantage of the SCNN involving the shuffling operator to effectively upsample feature maps and then fuse multiscale features derived from the intermediate layers of the SCNN, which results in the Multi-scale Shuffling Convolutional Neural Network (MSCNN). Based on the MSCNN, we derive the DSCNN by introducing additional losses into the intermediate layers of the MSCNN. In addition, we investigate the impact of using different sets of hand-crafted radiometric and geometric features derived from the true orthophotos and the DSMs on the semantic segmentation task. For performance evaluation, we use a commonly used benchmark dataset. The achieved results reveal that both multi-scale fusion and deep supervision contribute to an improvement in performance. Furthermore, the use of a diversity of hand-crafted radiometric and geometric features as input for the DSCNN does not provide the best numerical results, but smoother and improved detections for several objects.</p>

scholarly journals FPGA-Based Inter-layer Pipelined Accelerators for Filter-Wise Weight-Balanced Sparse Fully Convolutional Networks with Overlapped Tiling

2021 ◽  
Author(s):  
Masayuki Shimoda ◽  
Youki Sada ◽  
Hiroki Nakahara
Keyword(s):  
Embedded Systems ◽  
Power Efficiency ◽  
High Speed ◽  
Random Access ◽  
Semantic Segmentation ◽  
Input Image ◽  
Fpga Implementation ◽  
Image Size ◽  
Real Time Processing ◽  
Fully Convolutional Networks

AbstractConvolutional neural networks (CNNs) exhibit state-of-the-art performance while performing computer-vision tasks. CNNs require high-speed, low-power, and high-accuracy hardware for various scenarios, such as edge environments. However, the number of weights is so large that embedded systems cannot store them owing to their limited on-chip memory. A different method is used to minimize the input image size, for real-time processing, but it causes a considerable drop in accuracy. Although pruned sparse CNNs and special accelerators are proposed, the requirement of random access incurs a large number of wide multiplexers for a high degree of parallelism, which becomes more complicated and unsuitable for FPGA implementation. To address this problem, we propose filter-wise pruning with distillation and block RAM (BRAM)-based zero-weight skipping accelerator. It eliminates weights such that each filter has the same number of nonzero weights, performing retraining with distillation, while retaining comparable accuracy. Further, filter-wise pruning enables our accelerator to exploit inter-filter parallelism, where a processing block for a layer executes filters concurrently, with a straightforward architecture. We also propose an overlapped tiling algorithm, where tiles are extracted with overlap to prevent both accuracy degradation and high utilization of BRAMs storing high-resolution images. Our evaluation using semantic-segmentation tasks showed a 1.8 times speedup and 18.0 times increase in power efficiency of our FPGA design compared with a desktop GPU. Additionally, compared with the conventional FPGA implementation, the speedup and accuracy improvement were 1.09 times and 6.6 points, respectively. Therefore, our approach is useful for FPGA implementation and exhibits considerable accuracy for applications in embedded systems.

scholarly journals Salient Object Detection Combining a Self-Attention Module and a Feature Pyramid Network

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1702
Author(s):  
Guangyu Ren ◽  
Tianhong Dai ◽  
Panagiotis Barmpoutis ◽  
Tania Stathaki
Keyword(s):  
Object Detection ◽  
Receptive Fields ◽  
Semantic Segmentation ◽  
Salient Object Detection ◽  
Object Localization ◽  
Salient Object ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Fully Convolutional Networks ◽  
High Level

Salient object detection has achieved great improvements by using the Fully Convolutional Networks (FCNs). However, the FCN-based U-shape architecture may cause dilution problems in the high-level semantic information during the up-sample operations in the top-down pathway. Thus, it can weaken the ability of salient object localization and produce degraded boundaries. To this end, in order to overcome this limitation, we propose a novel pyramid self-attention module (PSAM) and the adoption of an independent feature-complementing strategy. In PSAM, self-attention layers are equipped after multi-scale pyramid features to capture richer high-level features and bring larger receptive fields to the model. In addition, a channel-wise attention module is also employed to reduce the redundant features of the FPN and provide refined results. Experimental analysis demonstrates that the proposed PSAM effectively contributes to the whole model so that it outperforms state-of-the-art results over five challenging datasets. Finally, quantitative results show that PSAM generates accurate predictions and integral salient maps, which can provide further help to other computer vision tasks, such as object detection and semantic segmentation.

scholarly journals A Novel Multi-Scale Attention PFE-UNet for Forest Image Segmentation

Forests ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 937
Author(s):  
Boyang Zhang ◽  
Hongbo Mu ◽  
Mingyu Gao ◽  
Haiming Ni ◽  
Jianfeng Chen ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Image Segmentation ◽  
State Of The Art ◽  
Computational Cost ◽  
Receptive Fields ◽  
Feature Maps ◽  
Multi Scale ◽  
Extensive Evaluation ◽  
Network Transition ◽  
Segmentation Task

The precise segmentation of forest areas is essential for monitoring tasks related to forest exploration, extraction, and statistics. However, the effective and accurate segmentation of forest images will be affected by factors such as blurring and discontinuity of forest boundaries. Therefore, a Pyramid Feature Extraction-UNet network (PFE-UNet) based on traditional UNet is proposed to be applied to end-to-end forest image segmentation. Among them, the Pyramid Feature Extraction module (PFE) is introduced in the network transition layer, which obtains multi-scale forest image information through different receptive fields. The spatial attention module (SA) and the channel-wise attention module (CA) are applied to low-level feature maps and PFE feature maps, respectively, to highlight specific segmentation task features while fusing context information and suppressing irrelevant regions. The standard convolution block is replaced by a novel depthwise separable convolutional unit (DSC Unit), which not only reduces the computational cost but also prevents overfitting. This paper presents an extensive evaluation with the DeepGlobe dataset and a comparative analysis with several state-of-the-art networks. The experimental results show that the PFE-UNet network obtains an accuracy of 94.23% in handling the real-time forest image segmentation, which is significantly higher than other advanced networks. This means that the proposed PFE-UNet also provides a valuable reference for the precise segmentation of forest images.

Sign in / Sign up

Export Citation Format

Share Document