Search results

Automatic defect detection is a fundamental and vital topic in the research field of industrial intelligence. In this work, the authors develop a more flexible deep learning method for the industrial defect detection.

The authors propose a unified framework for detecting defects in industrial products or planar surfaces based on an end-to-end learning strategy. A lightweight deep learning architecture for blade defect detection is specifically demonstrated. In addition, a blade defect data set is collected with the dual-arm image collection system.

Numerous experiments are conducted on the collected data set, and experimental results demonstrate that the proposed system can achieve satisfactory performance over other methods. Furthermore, the data equalization operation helps for a better defect detection result.

An end-to-end learning framework is established for defect detection. Although the adopted fully convolutional network has been extensively used for semantic segmentation in images, to the best knowledge of the authors, it has not been used for industrial defect detection. To remedy the difficulties of blade defect detection which has been analyzed above, the authors develop a new network architecture which integrates the residue learning to perform the efficient defect detection. A dual-arm data collection platform is constructed and extensive experimental validation are conducted.

Computer vision for automated analysis of cells and tissues usually include extracting features from images before analyzing such features via various machine learning and machine vision algorithms. The purpose of this work is to explore and demonstrate the ability of a Convolutional Neural Network (CNN) to classify cells pictured via brightfield microscopy without the need of any feature extraction, using a minimum of images, improving work-flows that involve cancer cell identification.

The methodology involved a quantitative measure of the performance of a Convolutional Neural Network in distinguishing between two cancer lines. In their approach, they trained, validated and tested their 6-layer CNN on 1,241 images of MDA-MB-468 and MCF7 breast cancer cell line in an end-to-end fashion, allowing the system to distinguish between the two different cancer cell types.

They obtained a 99% accuracy, providing a foundation for more comprehensive systems.

Value can be found in that systems based on this design can be used to assist cell identification in a variety of contexts, whereas a practical implication can be found that these systems can be deployed to assist biomedical workflows quickly and at low cost. In conclusion, this system demonstrates the potentials of end-to-end learning systems for faster and more accurate automated cell analysis.

The grasping task of robots in dense cluttered scenes from a single-view has not been solved perfectly, and there is still a problem of low grasping success rate. This study aims to propose an end-to-end grasp generation method to solve this problem.

A new grasp representation method is proposed, which cleverly uses the normal vector of the table surface to derive the grasp baseline vectors, and maps the grasps to the pointed points (PP), so that there is no need to add orthogonal constraints between vectors when using a neural network to predict rotation matrixes of grasps.

Experimental results show that the proposed method is beneficial to the training of the neural network, and the model trained on synthetic data set can also have high grasping success rate and completion rate in real-world tasks.

The main contribution of this paper is that the authors propose a new grasp representation method, which maps the 6-DoF grasps to a PP and an angle related to the tabletop normal vector, thereby eliminating the need to add orthogonal constraints between vectors when directly predicting grasps using neural networks. The proposed method can generate hundreds of grasps covering the whole surface in about 0.3 s. The experimental results show that the proposed method has obvious superiority compared with other methods.

This study aims to analyze driver risks in the driving environment. A complete analysis of context aware assistive driving techniques. Context awareness in assistive driving by probabilistic modeling techniques. Advanced techniques using Spatio-temporal techniques, computer vision and deep learning techniques.

Autonomous vehicles have been aimed to increase driver safety by introducing vehicle control from the driver to Advanced Driver Assistance Systems (ADAS). The core objective of these systems is to cut down on road accidents by helping the user in various ways. Early anticipation of a particular action would give a prior benefit to the driver to successfully handle the dangers on the road. In this paper, the advancements that have taken place in the use of multi-modal machine learning for assistive driving systems are surveyed. The aim is to help elucidate the recent progress and techniques in the field while also identifying the scope for further research and improvement. The authors take an overview of context-aware driver assistance systems that alert drivers in case of maneuvers by taking advantage of multi-modal human processing to better safety and drivability.

There has been a huge improvement and investment in ADAS being a key concept for road safety. In such applications, data is processed and information is extracted from multiple data sources, thus requiring training of machine learning algorithms in a multi-modal style. The domain is fast gaining traction owing to its applications across multiple disciplines with crucial gains.

The research is focused on deep learning and computer vision-based techniques to generate a context for assistive driving and it would definitely adopt by the ADAS manufacturers.

As context-aware assistive driving would work in real-time and it would save the lives of many drivers, pedestrians.

This paper provides an understanding of context-aware deep learning frameworks for assistive driving. The research is mainly focused on deep learning and computer vision-based techniques to generate a context for assistive driving. It incorporates the latest state-of-the-art techniques using suitable driving context and the driver is alerted. Many automobile manufacturing companies and researchers would refer to this study for their enhancements.

This paper aims to apply a methodology that is capable to classify and localize mechanical, electrical and plumbing (MEP) elements to assist facility managers. Furthermore, it assists in decreasing the technical complexity and sophistication of different systems to the facility management (FM) team.

This research exploits artificial intelligence (AI) in FM operations through proposing a new system that uses a deep learning pre-trained model for transfer learning. The model can identify new MEP elements through image classification with a deep convolutional neural network using a support vector machine (SVM) technique under supervised learning. Also, an expert system is developed and integrated with an Android application to the proposed system to identify the required maintenance for the identified elements. FM team can reach the identified assets with bluetooth tracker devices to perform the required maintenance.

The proposed system aids facility managers in their tasks and decreases the maintenance costs of facilities by maintaining, upgrading, operating assets cost-effectively using the proposed system.

The paper considers three fire protection systems for proactive maintenance, where other structural or architectural systems can also significantly affect the level of service and cost expensive repairs and maintenance. Also, the proposed system relies on different platforms that required to be consolidated for facility technicians and managers end-users. Therefore, the authors will consider these limitations and expand the study as a case study in future work.

This paper assists in a proactive manner to decrease the lack of knowledge of the required maintenance to MEP elements that leads to a lower life cycle cost. These MEP elements have a big share in the operation and maintenance costs of building facilities.

Most source recording device identification models for Web media forensics are based on a single feature to complete the identification task and often have the disadvantages of long time and poor accuracy. The purpose of this paper is to propose a new method for end-to-end network source identification of multi-feature fusion devices.

This paper proposes an efficient multi-feature fusion source recording device identification method based on end-to-end and attention mechanism, so as to achieve efficient and convenient identification of recording devices of Web media forensics.

The authors conducted sufficient experiments to prove the effectiveness of the models that they have proposed. The experiments show that the end-to-end system is improved by 7.1% compared to the baseline i-vector system, compared to the authors’ previous system, the accuracy is improved by 0.4%, and the training time is reduced by 50%.

With the development of Web media forensics and internet technology, the use of Web media as evidence is increasing. Among them, it is particularly important to study the authenticity and accuracy of Web media audio.

This paper aims to promote the development of source recording device identification and provide effective technology for Web media forensics and judicial record evidence that need to apply device source identification technology.

Conventional learning-based visual odometry (VO) systems usually use convolutional neural networks (CNN) to extract features, where some important context-related and attention-holding global features might be ignored. Without essential global features, VO system will be sensitive to various environmental perturbations. The purpose of this paper is to design a novel learning-based framework that aims to improve accuracy of learning-based VO without decreasing the generalization ability.

Instead of CNN, a context-gated convolution is adopted to build an end-to-end learning framework, which enables convolutional layers that dynamically capture representative local patterns and composes local features of interest under the guidance of global context. In addition, an attention mechanism module is introduced to further improve learning ability and enhance robustness and generalization ability of the VO system.

The proposed system is evaluated on the public data set KITTI and the self-collected data sets of our college building, where it shows competitive performance compared with some classical and state-of-the-art learning-based methods. Quantitative experimental results on the public data set KITTI show that compared with CNN-based VO methods, the average translational error and rotational error of all the test sequences are reduced by 45.63% and 37.22%, respectively.

The main contribution of this paper is that an end-to-end deep context gate convolutional VO system based on lightweight attention mechanism is proposed, which effectively improves the accuracy compared with other learning-based methods.

Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.

This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features.

The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.

In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space simultaneously in real-time, which is applicable in real-world scenarios such as safety monitoring and collaborative assembly.

This paper design an end-to-end deep learning network called collaborator only watch once (COWO). COWO recognizes the ongoing human activities in real-time with enhanced accuracy. COWO inherits from the architecture of you only watch once (YOWO), known to be the best performing network for online action localization to date, but with three major structural modifications: COWO enhances the intraclass compactness and enlarges the interclass separability in the feature level. A new correlation channel fusion and attention mechanism are designed based on the Pearson correlation coefficient. Accordingly, a correction loss function is designed. This function minimizes the same class distance and enhances the intraclass compactness. Use a probabilistic K-means clustering technique for selecting the initial seed points. The idea behind this is that the initial distance between cluster centers should be as considerable as possible. CIOU regression loss function is applied instead of the Smooth L1 loss function to help the model converge stably.

COWO outperforms the original YOWO with improvements of frame mAP 3% and 2.1% at a speed of 35.12 fps. Compared with the two-stream, T-CNN, C3D, the improvement is about 5% and 14.5% when applied to J-HMDB-21, UCF101-24 and AGOT data sets.

COWO extends more flexibility for assembly scenarios as it perceives spatiotemporal human actions in real-time. It contributes to many real-world scenarios such as safety monitoring and collaborative assembly.

In order to solve the problem that the performance of the existing local feature descriptors in uncontrolled environment is greatly affected by illumination, background, occlusion and other factors, we propose a novel face recognition algorithm in uncontrolled environment which combines the block central symmetry local binary pattern (CS-LBP) and deep residual network (DRN) model.

The algorithm first extracts the block CSP-LBP features of the face image, then incorporates the extracted features into the DRN model, and gives the face recognition results by using a well-trained DRN model. The features obtained by the proposed algorithm have the characteristics of both local texture features and deep features that robust to illumination.

Compared with the direct usage of the original image, the usage of local texture features of the image as the input of DRN model significantly improves the computation efficiency. Experimental results on the face datasets of FERET, YALE-B and CMU-PIE have shown that the recognition rate of the proposed algorithm is significantly higher than that of other compared algorithms.

The proposed algorithm fundamentally solves the problem of face identity recognition in uncontrolled environment, and it is particularly robust to the change of illumination, which proves its superiority.