scholarly journals Real-Time Jellyfish Classification and Detection Based on Improved YOLOv3 Algorithm

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8160
Author(s):  
Meijing Gao ◽  
Yang Bai ◽  
Zhilong Li ◽  
Shiyu Li ◽  
Bozhi Zhang ◽  
...  
Keyword(s):  
Real Time ◽  
Detection Method ◽  
Histogram Equalization ◽  
Detection Accuracy ◽  
Data Set ◽  
Marine Fishery ◽  
Multi Scale ◽  
Underwater Image ◽  
Neural Network Theory

In recent years, jellyfish outbreaks have frequently occurred in offshore areas worldwide, posing a significant threat to the marine fishery, tourism, coastal industry, and personal safety. Effective monitoring of jellyfish is a vital method to solve the above problems. However, the optical detection method for jellyfish is still in the primary stage. Therefore, this paper studies a jellyfish detection method based on convolution neural network theory and digital image processing technology. This paper studies the underwater image preprocessing algorithm because the quality of underwater images directly affects the detection results. The results show that the image quality is better after applying the three algorithms namely prior defogging, adaptive histogram equalization, and multi-scale retinal enhancement, which is more conducive to detection. We establish a data set containing seven species of jellyfishes and fish. A total of 2141 images are included in the data set. The YOLOv3 algorithm is used to detect jellyfish, and its feature extraction network Darknet53 is optimized to ensure it is conducted in real-time. In addition, we introduce label smoothing and cosine annealing learning rate methods during the training process. The experimental results show that the improved algorithms improve the detection accuracy of jellyfish on the premise of ensuring the detection speed. This paper lays a foundation for the construction of an underwater jellyfish optical imaging real-time monitoring system.

Development and Application of Quality Control System for Highway Subgrade Construction

2019 ◽  
Vol 2 (5) ◽  
Author(s):  
Tong Wang
Keyword(s):  
Quality Control ◽  
Real Time ◽  
Detection Method ◽  
System Development ◽  
Effective Control ◽  
Construction Process ◽  
Development Mode ◽  
The Road ◽  
Whole Process

The compaction quality of the subgrade is directly related to the service life of the road. Effective control of the subgrade construction process is the key to ensuring the compaction quality of the subgrade. Therefore, real-time, comprehensive, rapid and accurate prediction of construction compaction quality through informatization detection method is an important guarantee for speeding up construction progress and ensuring subgrade compaction quality. Based on the function of the system, this paper puts forward the principle of system development and the development mode used in system development, and displays the development system in real-time to achieve the whole process control of subgrade construction quality.

MobileNet-Yolo Based wildlife detection model: A case study in yunnan tongbiguan nature reserve, China

2021 ◽  
pp. 1-11
Author(s):  
Tingting Zhao ◽  
Xiaoli Yi ◽  
Zhiyong Zeng ◽  
Tao Feng
Keyword(s):  
Real Time ◽  
Nature Reserve ◽  
Complex Model ◽  
Training Data ◽  
Mean Average Precision ◽  
Detection Accuracy ◽  
High Definition ◽  
Average Precision ◽  
Data Set ◽  
Real Time Detection

YTNR (Yunnan Tongbiguan Nature Reserve) is located in the westernmost part of China’s tropical regions and is the only area in China with the tropical biota of the Irrawaddy River system. The reserve has abundant tropical flora and fauna resources. In order to realize the real-time detection of wild animals in this area, this paper proposes an improved YOLO (You only look once) network. The original YOLO model can achieve higher detection accuracy, but due to the complex model structure, it cannot achieve a faster detection speed on the CPU detection platform. Therefore, the lightweight network MobileNet is introduced to replace the backbone feature extraction network in YOLO, which realizes real-time detection on the CPU platform. In response to the difficulty in collecting wild animal image data, the research team deployed 50 high-definition cameras in the study area and conducted continuous observations for more than 1,000 hours. In the end, this research uses 1410 images of wildlife collected in the field and 1577 wildlife images from the internet to construct a research data set combined with the manual annotation of domain experts. At the same time, transfer learning is introduced to solve the problem of insufficient training data and the network is difficult to fit. The experimental results show that our model trained on a training set containing 2419 animal images has a mean average precision of 93.6% and an FPS (Frame Per Second) of 3.8 under the CPU. Compared with YOLO, the mean average precision is increased by 7.7%, and the FPS value is increased by 3.

The Study on High Precision 3D Detection Method of Steel Plate Surface Based on Structured Light

2012 ◽  
Vol 572 ◽  
pp. 338-342 ◽  
Author(s):  
Zhi Guo Liang ◽  
Quan Yang ◽  
Ke Xu ◽  
Fei He ◽  
Xiao Chen Wang ◽  
...  
Keyword(s):  
Surface Quality ◽  
Steel Plate ◽  
Detection Method ◽  
Structured Light ◽  
Detection Methods ◽  
Measurement Technology ◽  
Detection Accuracy ◽  
Plate Surface ◽  
Factors Affecting

Structured light 3D measurement technology with its simple structure, non-contact measurement, fast measurement speed and other advantages, has been widely used. Steel plate surface quality detection is not confined to the two-dimensional feature of gray detection, and local topography measurement for surface quality of steel plate detection becomes increasingly important. In this paper, steel plate surface 3D detection method based on structured light and the factors affecting the measurement accuracy are analyzed. Several effective methods of improving 3D detection accuracy are put forward. Compared with the traditional structured light 3D detection methods, the detection accuracy of new methods is remarkably improved, thus possessing better application values.

Semi supervised inspection algorithm of automatic packaging curve based on deep learning

2021 ◽  
pp. 1-10
Author(s):  
Yong He
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Optimization Algorithm ◽  
Posterior Probability ◽  
Detection Method ◽  
Detection System ◽  
Experimental Results ◽  
Detection Accuracy ◽  
Data Set ◽  
Packaging Process

The current automatic packaging process is complex, requires high professional knowledge, poor universality, and difficult to apply in multi-objective and complex background. In view of this problem, automatic packaging optimization algorithm has been widely paid attention to. However, the traditional automatic packaging detection accuracy is low, the practicability is poor. Therefore, a semi-supervised detection method of automatic packaging curve based on deep learning and semi-supervised learning is proposed. Deep learning is used to extract features and posterior probability to classify unlabeled data. KDD CUP99 data set was used to verify the accuracy of the algorithm. Experimental results show that this method can effectively improve the performance of automatic packaging curve semi-supervised detection system.

scholarly journals Sensitivity of GNSS tropospheric gradients to processing options

2019 ◽  
Vol 37 (3) ◽  
pp. 429-446 ◽  
Author(s):  
Michal Kačmařík ◽  
Jan Douša ◽  
Florian Zus ◽  
Pavel Václavovic ◽  
Kyriakos Balidakis ◽  
...  
Keyword(s):  
Real Time ◽  
Elevation Angle ◽  
Mapping Function ◽  
Global Navigation Satellite Systems ◽  
Gradient Estimates ◽  
Post Processing ◽  
Data Set ◽  
Mapping Functions ◽  
Gradient Mapping

Abstract. An analysis of processing settings impacts on estimated tropospheric gradients is presented. The study is based on the benchmark data set collected within the COST GNSS4SWEC action with observations from 430 Global Navigation Satellite Systems (GNSS) reference stations in central Europe for May and June 2013. Tropospheric gradients were estimated in eight different variants of GNSS data processing using precise point positioning (PPP) with the G-Nut/Tefnut software. The impacts of the gradient mapping function, elevation cut-off angle, GNSS constellation, observation elevation-dependent weighting and real-time versus post-processing mode were assessed by comparing the variants by each to other and by evaluating them with respect to tropospheric gradients derived from two numerical weather models (NWMs). Tropospheric gradients estimated in post-processing GNSS solutions using final products were in good agreement with NWM outputs. The quality of high-resolution gradients estimated in (near-)real-time PPP analysis still remains a challenging task due to the quality of the real-time orbit and clock corrections. Comparisons of GNSS and NWM gradients suggest the 3∘ elevation angle cut-off and GPS+GLONASS constellation for obtaining optimal gradient estimates provided precise models for antenna-phase centre offsets and variations, and tropospheric mapping functions are applied for low-elevation observations. Finally, systematic errors can affect the gradient components solely due to the use of different gradient mapping functions, and still depending on observation elevation-dependent weighting. A latitudinal tilting of the troposphere in a global scale causes a systematic difference of up to 0.3 mm in the north-gradient component, while large local gradients, usually pointing in a direction of increasing humidity, can cause differences of up to 1.0 mm (or even more in extreme cases) in any component depending on the actual direction of the gradient. Although the Bar-Sever gradient mapping function provided slightly better results in some aspects, it is not possible to give any strong recommendation on the gradient mapping function selection.

scholarly journals Structural Damage Detection Based on Real-Time Vibration Signal and Convolutional Neural Network

2020 ◽  
Vol 10 (14) ◽  
pp. 4720 ◽  
Author(s):  
Zhiqiang Teng ◽  
Shuai Teng ◽  
Jiqiao Zhang ◽  
Gongfa Chen ◽  
Fangsen Cui
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Structural State ◽  
Detection Method ◽  
Steel Frame ◽  
Engineering Practice ◽  
Detection Accuracy ◽  
Vibration Signals

The traditional methods of structural health monitoring (SHM) have obvious disadvantages such as being time-consuming, laborious and non-synchronizing, and so on. This paper presents a novel and efficient approach to detect structural damages from real-time vibration signals via a convolutional neural network (CNN). As vibration signals (acceleration) reflect the structural response to the changes of the structural state, hence, a CNN, as a classifier, can map vibration signals to the structural state and detect structural damages. As it is difficult to obtain enough damage samples in practical engineering, finite element analysis (FEA) provides an alternative solution to this problem. In this paper, training samples for the CNN are obtained using FEA of a steel frame, and the effectiveness of the proposed detection method is evaluated by inputting the experimental data into the CNN. The results indicate that, the detection accuracy of the CNN trained using FEA data reaches 94% for damages introduced in the numerical model and 90% for damages in the real steel frame. It is demonstrated that the CNN has an ideal detection effect for both single damage and multiple damages. The combination of FEA and experimental data provides enough training and testing samples for the CNN, which improves the practicability of the CNN-based detection method in engineering practice.

scholarly journals MW-ACGAN: Generating Multiscale High-Resolution SAR Images for Ship Detection

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6673
Author(s):  
Lichuan Zou ◽  
Hong Zhang ◽  
Chao Wang ◽  
Fan Wu ◽  
Feng Gu
Keyword(s):  
High Resolution ◽  
Small Sample ◽  
Generative Adversarial Networks ◽  
Detection Accuracy ◽  
Data Set ◽  
Ship Detection ◽  
Multi Scale ◽  
Adversarial Networks ◽  
Sar Data ◽  
Composite Data

In high-resolution Synthetic Aperture Radar (SAR) ship detection, the number of SAR samples seriously affects the performance of the algorithms based on deep learning. In this paper, aiming at the application requirements of high-resolution ship detection in small samples, a high-resolution SAR ship detection method combining an improved sample generation network, Multiscale Wasserstein Auxiliary Classifier Generative Adversarial Networks (MW-ACGAN) and the Yolo v3 network is proposed. Firstly, the multi-scale Wasserstein distance and gradient penalty loss are used to improve the original Auxiliary Classifier Generative Adversarial Networks (ACGAN), so that the improved network can stably generate high-resolution SAR ship images. Secondly, the multi-scale loss term is added to the network, so the multi-scale image output layers are added, and multi-scale SAR ship images can be generated. Then, the original ship data set and the generated data are combined into a composite data set to train the Yolo v3 target detection network, so as to solve the problem of low detection accuracy under small sample data set. The experimental results of Gaofen-3 (GF-3) 3 m SAR data show that the MW-ACGAN network can generate multi-scale and multi-class ship slices, and the confidence level of ResNet18 is higher than that of ACGAN network, with an average score of 0.91. The detection results of Yolo v3 network model show that the detection accuracy trained by the composite data set is as high as 94%, which is far better than that trained only by the original SAR data set. These results show that our method can make the best use of the original data set, improve the accuracy of ship detection.

scholarly journals A Real-Time Detection Method for Abnormal Data of Internet of Things Sensors Based on Mobile Edge Computing

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Xuguang Liu
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Data Processing ◽  
Real Time ◽  
Detection Method ◽  
Edge Computing ◽  
Sensor Data ◽  
Detection Accuracy ◽  
Spatiotemporal Correlation ◽  
Real Time Detection

Aiming at the anomaly detection problem in sensor data, traditional algorithms usually only focus on the continuity of single-source data and ignore the spatiotemporal correlation between multisource data, which reduces detection accuracy to a certain extent. Besides, due to the rapid growth of sensor data, centralized cloud computing platforms cannot meet the real-time detection needs of large-scale abnormal data. In order to solve this problem, a real-time detection method for abnormal data of IoT sensors based on edge computing is proposed. Firstly, sensor data is represented as time series; K-nearest neighbor (KNN) algorithm is further used to detect outliers and isolated groups of the data stream in time series. Secondly, an improved DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm is proposed by considering spatiotemporal correlation between multisource data. It can be set according to sample characteristics in the window and overcomes the slow convergence problem using global parameters and large samples, then makes full use of data correlation to complete anomaly detection. Moreover, this paper proposes a distributed anomaly detection model for sensor data based on edge computing. It performs data processing on computing resources close to the data source as much as possible, which improves the overall efficiency of data processing. Finally, simulation results show that the proposed method has higher computational efficiency and detection accuracy than traditional methods and has certain feasibility.

scholarly journals To Optimize Network Call Drops and Enhances Real Time (CDR) Data Handling with Security

2020 ◽  
Author(s):  
Ashok G V ◽  
Dr.Vasanthi Kumari P
Keyword(s):  
Real Time ◽  
Service Providers ◽  
Large Data ◽  
Network Capacity ◽  
Data Set ◽  
Satisfaction Index ◽  
Customer Churn ◽  
Trend Forecasting ◽  
Telecom Networks

The telecom networks generate multitudes and large sets of data related to networks, applications, users, network operations and real time call processing (Call Detail Record (CDR)). This large data set has the capability to give valuable business insights - for example, real-time user quality of service, network issues, call drop issues, customer satisfaction index, customer churn, network capacity forecast and many more revenue impacting insights. As even setting up of more towers for better coverage would also directly affect the health of habitants around. In this paper, the overall condition of call drops has been reviewed and possible ways to minimize the spectacles of network call drops. Applied Linear Regression algorithm which is used type of predictive analysis. Three major uses for regression analysis Determining the strength of predictors, Forecasting an effect and Trend forecasting. This paper gives to telecom service providers to improve their networks and minimize the network call drops with security. Deliver quality of services to their subscribers using the advanced technologies with accurate algorithms.

scholarly journals Efficient Moving Vehicle Detection Algorithm for Various Traffic Conditions

2019 ◽  
Vol 8 (3) ◽  
pp. 6069-6076
Keyword(s):  
Real Time ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Traffic Monitoring ◽  
Visual Surveillance ◽  
Detection Accuracy ◽  
Data Set ◽  
Moving Vehicle ◽  
Detection Techniques

Many computer vision applications needs to detect moving object from an input video sequences. The main applications of this are traffic monitoring, visual surveillance, people tracking and security etc. Among these, traffic monitoring is one of the most difficult tasks in real time video processing. Many algorithms are introduced to monitor traffic accurately. But most of the cases, the detection accuracy is very less and the detection time is higher which makes the algorithms are not suitable for real time applications. In this paper, a new technique to detect moving vehicle efficiently using Modified Gaussian Mixture Model and Modified Blob Detection techniques is proposed. The modified Gaussian Mixture model generates the background from overall probability of the complete data set and by calculating the required step size from the frame differences. The modified Blob Analysis is then used to classify proper moving objects. The simulation results shows that the method accurately detect the target

Sign in / Sign up

Export Citation Format

Share Document