Search results

This paper aims to use fully convolutional network (FCN) to predict pixel-wise antipodal grasp affordances for unknown objects and improve the grasp detection performance through multi-scale feature fusion.

A modified FCN network is used as the backbone to extract pixel-wise features from the input image, which are further fused with multi-scale context information gathered by a three-level pyramid pooling module to make more robust predictions. Based on the proposed unify feature embedding framework, two head networks are designed to implement different grasp rotation prediction strategies (regression and classification), and their performances are evaluated and compared with a defined point metric. The regression network is further extended to predict the grasp rectangles for comparisons with previous methods and real-world robotic grasping of unknown objects.

The ablation study of the pyramid pooling module shows that the multi-scale information fusion significantly improves the model performance. The regression approach outperforms the classification approach based on same feature embedding framework on two data sets. The regression network achieves a state-of-the-art accuracy (up to 98.9%) and speed (4 ms per image) and high success rate (97% for household objects, 94.4% for adversarial objects and 95.3% for objects in clutter) in the unknown object grasping experiment.

A novel pixel-wise grasp affordance prediction network based on multi-scale feature fusion is proposed to improve the grasp detection performance. Two prediction approaches are formulated and compared based on the proposed framework. The proposed method achieves excellent performances on three benchmark data sets and real-world robotic grasping experiment.

The purpose of this paper is to focus on the design of a dual-branch balance saliency model based on fully convolutional network (FCN) for automatic fabric defect detection, and improve quality control in textile manufacturing.

This paper proposed a dual-branch balance saliency model based on discriminative feature for fabric defect detection. A saliency branch is firstly designed to address the problems of scale variation and contextual information integration, which is realized through the cooperation of a multi-scale discriminative feature extraction module (MDFEM) and a bidirectional stage-wise integration module (BSIM). These modules are respectively adopted to extract multi-scale discriminative context information and enrich the contextual information of features at each stage. In addition, another branch is proposed to balance the network, in which a bootstrap refinement module (BRM) is trained to guide the restoration of feature details.

To evaluate the performance of the proposed network, we conduct extensive experiments, and the experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) approaches on seven evaluation metrics. We also conduct adequate ablation analyses that provide a full understanding of the design principles of the proposed method.

The dual-branch balance saliency model was proposed and applied into the fabric defect detection. The qualitative and quantitative experimental results show the effectiveness of the detection method. Therefore, the proposed method can be used for accurate fabric defect detection and even surface defect detection of other industrial products.

The massive number of pavements and buildings coupled with the limited inspection resources, both monetary and human, to detect distresses and recommend maintenance actions lead to rapid deterioration, decreased service life, lower level of service and increased community disruption. Therefore, this paper aims at providing a state-of-the-art review of the literature with respect to deep learning techniques for detecting distress in both pavements and buildings; research advancements per asset/structure type; and future recommendations in deep learning applications for distress detection.

A critical analysis was conducted on 181 papers of deep learning-based cracks detection. A structured analysis was adopted so that major articles were analyzed according to their focus of study, used methods, findings and limitations.

The utilization of deep learning to detect pavement cracks is advanced compared to assess and evaluate the structural health of buildings. There is a need for studies that compare different convolutional neural network models to foster the development of an integrated solution that considers the data collection method. Further research is required to examine the setup, implementation and running costs, frequency of capturing data and deep learning tool. In conclusion, the future of applying deep learning algorithms in lieu of manual inspection for detecting distresses has shown promising results.

The availability of previous research and the required improvements in the proposed computational tools and models (e.g. artificial intelligence, deep learning, etc.) are triggering researchers and practitioners to enhance the distresses’ inspection process and make better use of their limited resources.

A critical and structured analysis of deep learning-based crack detection for pavement and buildings is conducted for the first time to enable novice researchers to highlight the knowledge gap in each article, as well as building a knowledge base from the findings of other research to support developing future workable solutions.

Brain tumor is one of the most dangerous and life-threatening disease. In order to decide the type of tumor, devising a treatment plan and estimating the overall survival time of the patient, accurate segmentation of tumor region from images is extremely important. The process of manual segmentation is very time-consuming and prone to errors; therefore, this paper aims to provide a deep learning based method, that automatically segment the tumor region from MR images.

In this paper, the authors propose a deep neural network for automatic brain tumor (Glioma) segmentation. Intensity normalization and data augmentation have been incorporated as pre-processing steps for the images. The proposed model is trained on multichannel magnetic resonance imaging (MRI) images. The model outputs high-resolution segmentations of brain tumor regions in the input images.

The proposed model is evaluated on benchmark BRATS 2013 dataset. To evaluate the performance, the authors have used Dice score, sensitivity and positive predictive value (PPV). The superior performance of the proposed model is validated by training very popular UNet model in the similar conditions. The results indicate that proposed model has obtained promising results and is effective for segmentation of Glioma regions in MRI at a clinical level.

The model can be used by doctors to identify the exact location of the tumorous region.

The proposed model is an improvement to the UNet model. The model has fewer layers and a smaller number of parameters in comparison to the UNet model. This helps the network to train over databases with fewer images and gives superior results. Moreover, the information of bottleneck feature learned by the network has been fused with skip connection path to enrich the feature map.

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.

This paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.

Extensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.

The modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

The purpose of this paper is to focus on the design of automated fabric defect detection based on cascaded low-rank decomposition and to maintain high quality control in textile manufacturing.

This paper proposed a fabric defect detection algorithm based on cascaded low-rank decomposition. First, the constructed Gabor feature matrix is divided into a low-rank matrix and sparse matrix using low-rank decomposition technique, and the sparse matrix is used as priori matrix where higher values indicate a higher probability of abnormality. Second, we conducted the second low-rank decomposition for the constructed texton feature matrix under the guidance of the priori matrix. Finally, an improved adaptive threshold segmentation algorithm was adopted to segment the saliency map generated by the final sparse matrix to locate the defect regions.

The proposed method was evaluated on the public fabric image databases. By comparing with the ground-truth, the average detection rate of 98.26% was obtained and is superior to the state-of-the-art.

The cascaded low-rank decomposition was first proposed and applied into the fabric defect detection. The quantitative value shows the effectiveness of the detection method. Hence, the proposed method can be used for accurate defect detection and automated analysis system.

The traditional vision system cannot automatically adjust the feature point extraction method according to the type of welding seam. In addition, the robot cannot self-correct the laying position error or machining error. To solve this problem, this paper aims to propose a hierarchical visual model to achieve automatic arc welding guidance.

The hierarchical visual model proposed in this paper is divided into two layers: welding seam classification layer and feature point extraction layer. In the welding seam classification layer, the SegNet network model is trained to identify the welding seam type, and the prediction mask is obtained to segment the corresponding point clouds. In the feature point extraction layer, the scanning path is determined by the point cloud obtained from the upper layer to correct laying position error. The feature points extraction method is automatically determined to correct machining error based on the type of welding seam. Furthermore, the corresponding specific method to extract the feature points for each type of welding seam is proposed. The proposed visual model is experimentally validated, and the feature points extraction results as well as seam tracking error are finally analyzed.

The experimental results show that the algorithm can well accomplish welding seam classification, feature points extraction and seam tracking with high precision. The prediction mask accuracy is above 90% for three types of welding seam. The proposed feature points extraction method for each type of welding seam can achieve sub-pixel feature extraction. For the three types of welding seam, the maximum seam tracking error is 0.33–0.41 mm, and the average seam tracking error is 0.11–0.22 mm.

The main innovation of this paper is that a hierarchical visual model for robotic arc welding is proposed, which is suitable for various types of welding seam. The proposed visual model well achieves welding seam classification, feature point extraction and error correction, which improves the automation level of robot welding.

Thin cracks on the surface, such as those found in nuclear power plant concrete structures, are difficult to identify because they tend to be thin. This paper aims to design a novel segmentation network, called U-shaped contextual aggregation network (UCAN), for better recognition of weak cracks.

UCAN uses dilated convolutional layers with exponentially changing dilation rates to extract additional contextual features of thin cracks while preserving resolution. Furthermore, this paper has developed a topology-based loss function, called ℓ_cl Dice, which enhances the crack segmentation’s connectivity.

This paper generated five data sets with varying crack widths to evaluate the performance of multiple algorithms. The results show that the UCAN network proposed in this study achieves the highest F1-Score on thinner cracks. Additionally, training the UCAN network with the ℓ_cl Dice improves the F1-Scores compared to using the cross-entropy function alone. These findings demonstrate the effectiveness of the UCAN network and the value of incorporating the ℓ_cl Dice in crack segmentation tasks.

In this paper, an exponentially dilated convolutional layer is constructed to replace the commonly used pooling layer to improve the model receptive field. To address the challenge of preserving fracture connectivity segmentation, this paper introduces ℓ_cl Dice. This design enables UCAN to extract more contextual features while maintaining resolution, thus improving the crack segmentation performance. The proposed method is evaluated using extensive experiments where the results demonstrate the effectiveness of the algorithm.

An abundance of techniques has been presented so forth for waste classification but, they deliver inefficient results with low accuracy. Their achievement on various repositories is different and also, there is insufficiency of high-scale databases for training. The purpose of the study is to provide high security.

In this research, optimization-assisted federated learning (FL) is introduced for thermoplastic waste segregation and classification. The deep learning (DL) network trained by Archimedes Henry gas solubility optimization (AHGSO) is used for the classification of plastic and resin types. The deep quantum neural networks (DQNN) is used for first-level classification and the deep max-out network (DMN) is employed for second-level classification. This developed AHGSO is obtained by blending the features of Archimedes optimization algorithm (AOA) and Henry gas solubility optimization (HGSO). The entities included in this approach are nodes and servers. Local training is carried out depending on local data and updations to the server are performed. Then, the model is aggregated at the server. Thereafter, each node downloads the global model and the update training is executed depending on the downloaded global and the local model till it achieves the satisfied condition. Finally, local update and aggregation at the server is altered based on the average method. The Data tag suite (DATS_2022) dataset is used for multilevel thermoplastic waste segregation and classification.

By using the DQNN in first-level classification the designed optimization-assisted FL has gained an accuracy of 0.930, mean average precision (MAP) of 0.933, false positive rate (FPR) of 0.213, loss function of 0.211, mean square error (MSE) of 0.328 and root mean square error (RMSE) of 0.572. In the second level classification, by using DMN the accuracy, MAP, FPR, loss function, MSE and RMSE are 0.932, 0.935, 0.093, 0.068, 0.303 and 0.551.

The multilevel thermoplastic waste segregation and classification using the proposed model is accurate and improves the effectiveness of the classification.

The purpose of this study is to provide a new convolutional neural network (CNN) model with multi-scale feature extractor to segment and recognize wear particles in complex ferrograph images, especially fatigue and severe sliding wear particles, which are similar in morphology while different in wear mechanism.

A CNN model named DWear is proposed to semantically segment fatigue, severe sliding particles and four other types of particles, that is, chain, spherical, cutting and oxide particles, which unifies segmentation and recognition together. DWear is constructed using four modules, namely, encoder, densely connected atrous spatial pyramid pooling, decoder and fully connected conditional random field. Different from the architectures of ordinary semantic segmentation CNN models, a multi-scale feature extractor using cascade connections and a coprime atrous rate group is incorporated into the DWear model to obtain multi-scale receptive fields and better extract features of wear particles. Moreover, fully connected conditional random field module is adopted for post-processing to smooth coarse prediction and obtain finer results.

DWear is trained and verified on the ferrograph image data set, and experimental results show that the final Mean Pixel Accuracy is 95.6% and the Mean Intersection over Union is 92.2%, which means that the recognition and segmentation accuracy is higher than those of previous works.

DWear provides a promising approach for wear particle analysis and can be further developed in equipment condition monitoring applications.