scholarly journals Real-Time Detection of Railway Track Component via One-Stage Deep Learning Networks

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4325
Author(s):  
Tiange Wang ◽  
Fangfang Yang ◽  
Kwok-Leung Tsui
Keyword(s):  
Deep Learning ◽  
Learning Technologies ◽  
Railway Track ◽  
Detection Accuracy ◽  
Learning Approaches ◽  
Learning Networks ◽  
Railway Transportation ◽  
One Stage ◽  
Input Size ◽  
Feature Pyramid

Railway inspection has always been a critical task to guarantee the safety of the railway transportation. The development of deep learning technologies brings new breakthroughs in the accuracy and speed of image-based railway inspection application. In this work, a series of one-stage deep learning approaches, which are fast and accurate at the same time, are proposed to inspect the key components of railway track including rail, bolt, and clip. The inspection results show that the enhanced model, the second version of you only look once (YOLOv2), presents the best component detection performance with 93% mean average precision (mAP) at 35 image per second (IPS), whereas the feature pyramid network (FPN) based model provides a smaller mAP and much longer inference time. Besides, the detection performances of more deep learning approaches are evaluated under varying input sizes, where larger input size usually improves the detection accuracy but results in a longer inference time. Overall, the YOLO series models could achieve faster speed under the same detection accuracy.

scholarly journals Efficient Shot Detector: Lightweight Network Based on Deep Learning Using Feature Pyramid

2021 ◽  
Vol 11 (18) ◽  
pp. 8692
Author(s):  
Chansoo Park ◽  
Sanghun Lee ◽  
Hyunho Han
Keyword(s):  
Deep Learning ◽  
Detection Efficiency ◽  
Rapid Development ◽  
Extraction Process ◽  
General Purpose ◽  
Learning Technologies ◽  
Detection Accuracy ◽  
Data Set ◽  
Small Parameters ◽  
Feature Pyramid

Convolutional-neural-network (CNN)-based methods are continuously used in various industries with the rapid development of deep learning technologies. However, an inference efficiency problem was reported in applications that require real-time performance, such as a mobile device. It is important to design a lightweight network that can be used in general-purpose environments such as mobile environments and GPU environments. In this study, we propose a lightweight network efficient shot detector (ESDet) based on deep training with small parameters. The feature extraction process was performed using depthwise and pointwise convolution to minimize the computational complexity of the proposed network. The subsequent layer was formed in a feature pyramid structure to ensure that the extracted features were robust to multiscale objects. The network was trained by defining a prior box optimized for the data set of each feature scale. We defined an ESDet-baseline with optimal parameters through experiments and expanded it by gradually increasing the input resolution for detection accuracy. ESDet training and evaluation was performed using the PASCAL VOC and MS COCO2017 Dataset. Moreover, the average precision (AP) evaluation index was used for quantitative evaluation of detection performance. Finally, superior detection efficiency was demonstrated through the experiment compared to the conventional detection method.

scholarly journals L*a*b*Fruits: A Rapid and Robust Outdoor Fruit Detection System Combining Bio-Inspired Features with One-Stage Deep Learning Networks

Sensors ◽  
2020 ◽  
Vol 20 (1) ◽  
pp. 275 ◽  
Author(s):  
Raymond Kirk ◽  
Grzegorz Cielniak ◽  
Michael Mangan
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Model Complexity ◽  
Detection Accuracy ◽  
Learning Networks ◽  
Real World Data ◽  
Data Set ◽  
World Data ◽  
One Stage ◽  
Controlled Conditions

Automation of agricultural processes requires systems that can accurately detect and classify produce in real industrial environments that include variation in fruit appearance due to illumination, occlusion, seasons, weather conditions, etc. In this paper we combine a visual processing approach inspired by colour-opponent theory in humans with recent advancements in one-stage deep learning networks to accurately, rapidly and robustly detect ripe soft fruits (strawberries) in real industrial settings and using standard (RGB) camera input. The resultant system was tested on an existent data-set captured in controlled conditions as well our new real-world data-set captured on a real strawberry farm over two months. We utilise F 1 score, the harmonic mean of precision and recall, to show our system matches the state-of-the-art detection accuracy ( F 1 : 0.793 vs. 0.799) in controlled conditions; has greater generalisation and robustness to variation of spatial parameters (camera viewpoint) in the real-world data-set ( F 1 : 0.744); and at a fraction of the computational cost allowing classification at almost 30fps. We propose that the L*a*b*Fruits system addresses some of the most pressing limitations of current fruit detection systems and is well-suited to application in areas such as yield forecasting and harvesting. Beyond the target application in agriculture this work also provides a proof-of-principle whereby increased performance is achieved through analysis of the domain data, capturing features at the input level rather than simply increasing model complexity.

scholarly journals Speech Enhancement Using Deep Learning Methods: A Review

2021 ◽  
Vol 21 (1) ◽  
pp. 19
Author(s):  
Asri Rizki Yuliani ◽  
M. Faizal Amri ◽  
Endang Suryawati ◽  
Ade Ramdan ◽  
Hilman Ferdinandus Pardede
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Research Field ◽  
Learning Technologies ◽  
Learning Approaches ◽  
Speech Signal Processing ◽  
Generative Adversarial Network ◽  
Advantages And Disadvantages

Speech enhancement, which aims to recover the clean speech of the corrupted signal, plays an important role in the digital speech signal processing. According to the type of degradation and noise in the speech signal, approaches to speech enhancement vary. Thus, the research topic remains challenging in practice, specifically when dealing with highly non-stationary noise and reverberation. Recent advance of deep learning technologies has provided great support for the progress in speech enhancement research field. Deep learning has been known to outperform the statistical model used in the conventional speech enhancement. Hence, it deserves a dedicated survey. In this review, we described the advantages and disadvantages of recent deep learning approaches. We also discussed challenges and trends of this field. From the reviewed works, we concluded that the trend of the deep learning architecture has shifted from the standard deep neural network (DNN) to convolutional neural network (CNN), which can efficiently learn temporal information of speech signal, and generative adversarial network (GAN), that utilize two networks training.

Deep learning for drug–drug interaction extraction from the literature: a review

2019 ◽  
Vol 21 (5) ◽  
pp. 1609-1627 ◽  
Author(s):  
Tianlin Zhang ◽  
Jiaxu Leng ◽  
Ying Liu
Keyword(s):  
Deep Learning ◽  
Drug Research ◽  
Drug Effects ◽  
Learning Technologies ◽  
Biomedical Literature ◽  
Learning Approaches ◽  
Learning Methods ◽  
Feature Representations ◽  
Advantages And Disadvantages ◽  
Interaction Extraction

AbstractDrug–drug interactions (DDIs) are crucial for drug research and pharmacovigilance. These interactions may cause adverse drug effects that threaten public health and patient safety. Therefore, the DDIs extraction from biomedical literature has been widely studied and emphasized in modern biomedical research. The previous rules-based and machine learning approaches rely on tedious feature engineering, which is labourious, time-consuming and unsatisfactory. With the development of deep learning technologies, this problem is alleviated by learning feature representations automatically. Here, we review the recent deep learning methods that have been applied to the extraction of DDIs from biomedical literature. We describe each method briefly and compare its performance in the DDI corpus systematically. Next, we summarize the advantages and disadvantages of these deep learning models for this task. Furthermore, we discuss some challenges and future perspectives of DDI extraction via deep learning methods. This review aims to serve as a useful guide for interested researchers to further advance bioinformatics algorithms for DDIs extraction from the literature.

scholarly journals Deep Learning Approaches for Protein Structure Prediction

2018 ◽  
Vol 7 (4.5) ◽  
pp. 168
Author(s):  
Khatri Chandni ◽  
Prof. Mrudang Pandya ◽  
Dr. Sunil Jardosh
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Machine Learning Techniques ◽  
Great Promise ◽  
Learning Approaches ◽  
Learning Networks ◽  
Learning Techniques

In recent years, Machine Learning techniques that are based on Deep Learning networks that show a great promise in research          communities.Successful methods for deep learning involve Artificial Neural Networks and Machine Learning. Deep Learning solves severa  problems in bioinformatics. Protein Structure Prediction is one of the most important fields that can be solving using Deep Learning  approaches.These protein are categorized on basis of occurrence of amino acid patterns occur to extract the feature. In these paper aimed to review work based on protein structure prediction solve using Deep Learning Networks. Objective is to review motivate and facilitatethese deep learn the network for predicting protein sequences using Deep Learning. 

Internet of Things in Healthcare

2020 ◽  
pp. 23-39
Author(s):  
Rajasekaran Thangaraj ◽  
Sivaramakrishnan Rajendar ◽  
Vidhya Kandasamy
Keyword(s):  
Machine Learning ◽  
Cloud Computing ◽  
Deep Learning ◽  
Internet Of Things ◽  
Healthcare Systems ◽  
Wearable Devices ◽  
Healthcare Research ◽  
Learning Technologies ◽  
Learning Approaches ◽  
And Performance

Healthcare motoring has become a popular research in recent years. The evolution of electronic devices brings out numerous wearable devices that can be used for a variety of healthcare motoring systems. These devices measure the patient's health parameters and send them for further processing, where the acquired data is analyzed. The analysis provides the patients or their relatives with the medical support required or predictions based on the acquired data. Cloud computing, deep learning, and machine learning technologies play a prominent role in processing and analyzing the data respectively. This chapter aims to provide a detailed study of IoT-based healthcare systems, a variety of sensors used to measure parameters of health, and various deep learning and machine learning approaches introduced for the diagnosis of different diseases. The chapter also highlights the challenges, open issues, and performance considerations for future IoT-based healthcare research.

scholarly journals DGG: A Novel Framework for Crowd Gathering Detection

Electronics ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 31
Author(s):  
Jianqiang Xu ◽  
Haoyu Zhao ◽  
Weidong Min ◽  
Yi Zou ◽  
Qiyan Fu
Keyword(s):  
Deep Learning ◽  
Local Area ◽  
Video Frame ◽  
Detection Accuracy ◽  
Learning Approaches ◽  
Counting Method ◽  
Crowd Counting ◽  
Stable Pattern ◽  
Crowd Density ◽  
Public Areas

Crowd gathering detection plays an important role in security supervision of public areas. Existing image-processing-based methods are not robust for complex scenes, and deep-learning-based methods for gathering detection mainly focus on the design of the network, which ignores the inner feature of the crowd gathering action. To alleviate such problems, this work proposes a novel framework Detection of Group Gathering (DGG) based on the crowd counting method using deep learning approaches and statistics to detect crowd gathering. The DGG mainly contains three parts, i.e., Detecting Candidate Frame of Gathering (DCFG), Gathering Area Detection (GAD), and Gathering Judgement (GJ). The DCFG is proposed to find the frame index in a video that has the maximum people number based on the crowd counting method. This frame means that the crowd has gathered and the specific gathering area will be detected next. The GAD detects the local area that has the maximum crowd density in a frame with a slide search box. The local area contains the inner feature of the gathering action and represents that the crowd gathering in this local area, which is denoted by grid coordinates in a video frame. Based on the detected results of the DCFG and the GAD, the GJ is proposed to analyze the statistical relationship between the local area and the global area to find the stable pattern for the crowd gathering action. Experiments based on benchmarks show that the proposed DGG has a robust representation of the gathering feature and a high detection accuracy. There is the potential that the DGG can be used in social security and smart city domains.

scholarly journals ShipYOLO: An Enhanced Model for Ship Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xu Han ◽  
Lining Zhao ◽  
Yue Ning ◽  
Jingfeng Hu
Keyword(s):  
Feature Extraction ◽  
Target Space ◽  
Small Scale ◽  
Model Parameters ◽  
Detection Accuracy ◽  
Ship Detection ◽  
Backbone Network ◽  
Input Size ◽  
Pyramid Structure ◽  
Feature Pyramid

The application of ship detection for assistant intelligent ship navigation has stringent requirements for the model’s detection speed and accuracy. In response to this problem, this study uses an improved YOLO-V4 detection model (ShipYOLO) to detect ships. Compared to YOLO-V4, the model has three main improvements. Firstly, the backbone network (CSPDarknet) of YOLO-V4 is optimized. In the training process, the 3  ×  3 convolution, 1  ×  1 convolution, and identity parallel mode are used to replace the original feature extraction component (ResUnit) and more features are extracted. In the inference process, the branch parameters are combined to form a new backbone network named RCSPDarknet, which improves the inference speed of the model while improving the accuracy. Secondly, in order to solve the problem of missed detection of the small-scale ships, we designed a new amplified receptive field module named DSPP with dilated convolution and Max-Pooling, which improves the model’s acquisition of small-scale ship spatial information and robustness of ship target space displacement. Finally, we use the attention mechanism and Resnet’s shortcut idea to improve the feature pyramid structure (PAFPN) of YOLO-V4 and get a new feature pyramid structure named AtFPN. The structure effectively improves the model’s feature extraction effect for ships of different scales and reduces the number of model parameters, further improving the model’s inference speed and detection accuracy. In addition, we have created a ship dataset with a total of 2238 images, which is a single-category dataset. The experimental results show that ShipYOLO has the advantage of faster speed and higher accuracy even in different input sizes. Considering the input size of 320  ×  320 on the PC equipped with NVIDIA 1080Ti GPU, the FPS and mAP@5 : 5:95 (mAP90) of ShipYOLO are increased by 23.7% and 13.6% (10.6%), respectively, with an input size of 320  ×  320, ShipYOLO, compared to YOLO-V4.

scholarly journals RAPID OBJECT DETECTION SYSTEMS, UTILISING DEEP LEARNING AND UNMANNED AERIAL SYSTEMS (UAS) FOR CIVIL ENGINEERING APPLICATIONS

2018 ◽  
Vol XLII-2 ◽  
pp. 391-398 ◽  
Author(s):  
D. Griffiths ◽  
J. Boehm
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Network Architecture ◽  
Model Performance ◽  
Image Understanding ◽  
Detection Algorithm ◽  
Railway Track ◽  
Track Length ◽  
Unmanned Aerial Systems ◽  
Learning Approaches

With deep learning approaches now out-performing traditional image processing techniques for image understanding, this paper accesses the potential of rapid generation of Convolutional Neural Networks (CNNs) for applied engineering purposes. Three CNNs are trained on 275 UAS-derived and freely available online images for object detection of 3m2 segments of railway track. These includes two models based on the Faster RCNN object detection algorithm (Resnet and Incpetion-Resnet) as well as the novel onestage Focal Loss network architecture (Retinanet). Model performance was assessed with respect to three accuracy metrics. The first two consisted of Intersection over Union (IoU) with thresholds 0.5 and 0.1. The last assesses accuracy based on the proportion of track covered by object detection proposals against total track length. In under six hours of training (and two hours of manual labelling) the models detected 91.3 %, 83.1 % and 75.6 % of track in the 500 test images acquired from the UAS survey Retinanet, Resnet and Inception-Resnet respectively. We then discuss the potential for such applications of such systems within the engineering field for a range of scenarios.

Facemask Detection Based on Double Convolutional Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Guoqiang Chen ◽  
Bingxin Bai ◽  
Hongpeng Zhou ◽  
Mengchao Liu ◽  
Huailong Yi
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Feature Fusion ◽  
Contextual Information ◽  
Detection Accuracy ◽  
Learning Networks ◽  
Position Information ◽  
Detection Model ◽  
Multi Stage

Background: The study on facemask detection is of great significance because facemask detection is difficult, and the workload is heavy in places with a large number of people during the COVID-19 outbreak. Objective: The study aims to explore new deep learning networks that can accurately detect facemasks and improve the network's ability to extract multi-level features and contextual information. In addition, the proposed network effectively avoids the interference of objects like masks. The new network could eventually detect masks wearers in the crowd. Method: A Multi-stage Feature Fusion Block (MFFB) and a Detector Cascade Block (DCB) are proposed and connected to the deep learning network for facemask detection. The network's ability to obtain information improves. The network proposed in the study is Double Convolutional Neural Networks (CNN) called DCNN, which can fuse mask features and face position information. During facemask detection, the network extracts the featural information of the object and then inputs it into the data fusion layer. Results: The experiment results show that the proposed network can detect masks and faces in a complex environment and dense crowd. The detection accuracy of the network improves effectively. At the same time, the real-time performance of the detection model is excellent. Conclusion: The two branch networks of the DCNN can effectively obtain the feature and position information of facemasks. The network overcomes the disadvantage that a single CNN is susceptible to the interference of the suspected mask objects. The verification shows that the MFFB and the DCB can improve the network's ability to obtain object information, and the proposed DCNN can achieve excellent detection performance.

Sign in / Sign up

Export Citation Format

Share Document