scholarly journals DEFECTS DETECTION METHOD BASED ON K-MEANS WITH PRIOR KNOWLEDGE FOR BIOMASS PARTICLES

2020 ◽  
Vol 61 (2) ◽  
pp. 225-232 ◽  
Author(s):  
Wei Wang ◽  
Yuan Juan Gong
Keyword(s):  
Prior Knowledge ◽  
Detection Method ◽  
Vision System ◽  
Detection Algorithm ◽  
Biomass Energy ◽  
Detection Accuracy ◽  
Detection Time ◽  
Region Detection ◽  
High Detection ◽  
Biomass Particles

Biomass particle is one of the most important solid briquette fuels for agricultural and forestry biomass energy. Temperature, pressure, moisture and discharge holes are important factors to control biomass particle forming. The inappropriate setting of the parameters or blocking of the discharge hole will lead to the defects of the biomass particles, such as too short or poor roundness or pits or cracks. In order to detect these defects automatically, this paper proposes a method based on K-Means with prior knowledge. Firstly, the inner boundary tracking region detection algorithm and filling algorithm are combined to extract the regions in the backlight image. The regions are divided into debris, independent biomass particle regions and adhesive biomass particle regions. Secondly, K-Means with prior knowledge is used to segment the adhesive regions to get the independent biomass particle regions. Finally, the features of the biomass particles are extracted to judge the type of defects. The proposed method has been tested on images acquired from the vision system of the ring roller pellet mill. Experimental results show the efficiency of the proposed method in high detection accuracy and short detection time.

Robot Collision Detection Without External Sensors Based on Time-Series Analysis

2020 ◽  
Vol 143 (4) ◽  
Author(s):  
Tie Zhang ◽  
Peizhong Ge ◽  
Yanbiao Zou ◽  
Yingwu He
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Collision Detection ◽  
Degrees Of Freedom ◽  
Detection Method ◽  
Industrial Robot ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
External Torque ◽  
Series Analysis

Abstract To ensure the human safety in the process of human–robot cooperation, this paper proposes a robot collision detection method without external sensors based on time-series analysis (TSA). In the investigation, first, based on the characteristics of the external torque of the robot, the internal variation of the external torque sequence during the movement of the robot is analyzed. Next, a time-series model of the external torque is constructed, which is used to predict the external torque according to the historical motion information of the robot and generate a dynamic threshold. Then, the detailed process of time-series analysis for collision detection is described. Finally, the real-machine experiment scheme of the proposed real-time collision detection algorithm is designed and is used to perform experiments with a six degrees-of-freedom (6DOF) articulated industrial robot. The results show that the proposed method helps to obtain a detection accuracy of 100%; and that, as compared with the existing collision detection method based on a fixed symmetric threshold, the proposed method based on TSA possesses smaller detection delay and is more feasible in eliminating the sensitivity difference of collision detection in different directions.

scholarly journals An Improved Object Detection Method using Feature Map Refinement and Anchor Optimization

2021 ◽  
Vol 15 ◽  
pp. 541-549
Author(s):  
Yuxia Wang ◽  
Wenzhu Yang ◽  
Tongtong Yuan ◽  
Qian Li
Keyword(s):  
Object Detection ◽  
Detection Method ◽  
Search Space ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Semantic Features ◽  
Feature Map ◽  
Input Size ◽  
Fusion Operation ◽  
Different Levels

Lower detection accuracy and insufficient detection ability for small objects are the main problems of the region-free object detection algorithm. Aiming at solving the abovementioned problems, an improved object detection method using feature map refinement and anchor optimization is proposed. Firstly, the reverse fusion operation is performed on each of the object detection layer, which can provide the lower layers with more semantic information by the fusion of detection features at different levels. Secondly, the self-attention module is used to refine each detection feature map, calibrates the features between channels, and enhances the expression ability of local features. In addition, the anchor optimization model is introduced on each feature layer associated with anchors, and the anchors with higher probability of containing an object and more closely match the location and size of the object are obtained. In this model, semantic features are used to confirm and remove negative anchors to reduce search space of the objects, and preliminary adjustments are made to the locations and sizes of anchors. Comprehensive experimental results on PASCAL VOC detection dataset demonstrate the effectiveness of the proposed method. In particular, with VGG-16 and lower dimension 300×300 input size, the proposed method achieves a mAP of 79.1% on VOC 2007 test set with an inference speed of 24.7 milliseconds per image.

scholarly journals Research on insulator defect detection algorithm of transmission line based on CenterNet

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0255135
Author(s):  
Chunming Wu ◽  
Xin Ma ◽  
Xiangxu Kong ◽  
Haichao Zhu
Keyword(s):  
Transmission Line ◽  
Defect Detection ◽  
Detection Method ◽  
Detection Efficiency ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Detection Algorithm ◽  
Electric Power System ◽  
Stable Operation ◽  
Detection Accuracy

The reliability of the insulator has directly affected the stable operation of electric power system. The detection of defective insulators has always been an important issue in smart grid systems. However, the traditional transmission line detection method has low accuracy and poor real-time performance. We present an insulator defect detection method based on CenterNet. In order to improve detection efficiency, we simplified the backbone network. In addition, an attention mechanism is utilized to suppress useless information and improve the accuracy of network detection. In image preprocessing, the blurring of some detected images results in the samples being discarded, so we use super-resolution reconstruction algorithm to reconstruct the blurred images to enhance the dataset. The results show that the AP of the proposed method reaches 96.16% and the reasoning speed reaches 30FPS under the test condition of NVIDIA GTX 1080 test conditions. Compared with Faster R-CNN, YOLOV3, RetinaNet and FSAF, the detection accuracy of proposed method is greatly improved, which fully proves the effectiveness of the proposed method.

Research on Key Security Detection Method of Cross Domain Information Sharing Based on PKG Trust Gateway

2021 ◽  
Author(s):  
RunQi Li
Keyword(s):  
Information Sharing ◽  
Detection Method ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Detection Time ◽  
System Parameters ◽  
Management Platform ◽  
Cross Domain ◽  
Domain Information ◽  
Detection Effect

Aiming at the problems of low precision, long detection time and poor detection effect in current cross domain information sharing key security detection methods, a cross domain information sharing key security detection method based on PKG trust gateway is proposed. By analyzing bilinear pairing based on elliptic curve and identity based encryption scheme, according to the independent system parameters of PKG management platform, cross domain authentication access mechanism is proposed. PKG of different trust domains is used as the trust gateway for cross domain authentication. The key escrow problem of PKG of different trust domains is solved through key sharing, and the communication key agreement mechanism is established to mutually authenticate the user nodes in the trust domains with different system parameters. The formal description of the rule detection of cryptographic functions, parameters and other information, supported by the dynamic binary analysis platform pin, dynamically records the encryption and decryption process information during the operation of the program, and realizes cross domain information sharing key security detection through the design of correlation vulnerability detection algorithm. The experimental results show that the cross-domain information shared key security detection effect of the proposed method is better, which can effectively improve the detection accuracy and shorten the detection time.

Research on Technology of the Laser Designator Multi-Parameter Integrated Detection Method

2013 ◽  
Vol 552 ◽  
pp. 276-280
Author(s):  
Jin Song Wang ◽  
Jin Qiu Qi ◽  
Hao Zeng Wang ◽  
Jian Nan Deng ◽  
Zhi Yong An
Keyword(s):  
Image Processing ◽  
Detection Method ◽  
Detection Efficiency ◽  
Detection Accuracy ◽  
High Detection ◽  
Testing Technology ◽  
Beam Displacement ◽  
Focus Spot ◽  
Integrated Detection ◽  
Detection Principle

According to the state of testing technology for laser designator multi-parametric, a multi-parameter integrated detection method on the basis of optical collimation and digital image processing technology is proposed, and the way for the detection of multi-parameter characteristics and integrated detection is analyzed. By using the detection principle of large aperture lens focus spot method, the parameter measurements, such as the divergence angle of the laser designator beam, displacement amount of the light spot move, spot of adjustment range and deviation and the multi-axis consistency are measured. Simultaneously, the parameters of the sight line alteration of daylight aiming sight, the graduation precision can also be tested. By the analysis of experiment,the method has high detection accuracy and detection efficiency.

scholarly journals Solder Joint Defect Detection in the Connectors Using Improved Faster-RCNN Algorithm

2021 ◽  
Vol 11 (2) ◽  
pp. 576
Author(s):  
Kaihua Zhang ◽  
Haikuo Shen
Keyword(s):  
Solder Joint ◽  
Defect Detection ◽  
Data Augmentation ◽  
Detection Method ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Data Set ◽  
Electronic Products ◽  
Original Algorithm

The miniaturization and high integration of electronic products have higher and higher requirements for welding of internal components of electronic products. A welding quality detection method has always been one of the important research contents in the industry, among which, the research on solder joint defect detection of a connector has gradually attracted people’s attention with the development of image detection algorithm. The traditional solder joint detection method of connector adopts manual detection or automatic detection methods, which is inefficient and not safe enough. With the development of deep learning, the application of a deep convolutional neural network to target detection has become a research hotspot. In this paper, a data set of connector solder joint samples was made and the number of image samples was expanded to more than 3 times of the original by using data augmentation. Clustering generates anchor boxes and transfer learning with ResNet-101 were fused, so an improved faster region-based convolutional neural networks (Faster RCNN) algorithm was proposed. The experiment verified that the improved algorithm proposed in this paper had a great improvement in all aspects compared with the original algorithm. The average detection accuracy of this method can reach 94%, and the detection rate of some defects can even reach 100%, which can completely meet the industrial requirements.

scholarly journals A Novel Zero Velocity Detection Method Based on the Plantar Pressure

2020 ◽  
Author(s):  
Chengbin Wang ◽  
Meifeng Guo ◽  
Juan Wu ◽  
Bin Zhou ◽  
Qi Wei
Keyword(s):  
Plantar Pressure ◽  
Detection Method ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Pedestrian Navigation ◽  
Zero Velocity ◽  
High Detection ◽  
Walking Environment ◽  
Motion Characteristics ◽  
Indoor And Outdoor

The zero velocity update(ZUPT) algorithm is the core of a foot-mounted pedestrian navigation system. The zero velocity detection method is the premise and guarantee of the effective application of the ZUPT algorithm. To make ZUPT work properly, it is necessary to detect zero velocity intervals correctly. The detection accuracy of the existing zero velocity detection methods is easy to be affected by users and environment. A novel zero velocity detection method based on the plantar pressure is proposed in this paper, which has higher detection accuracy and better environmental adaptability. First, the paper analyzes the motion characteristics of foot during walking. Second, the inherent relationship between the plantar pressure and the gait change during walking is studied based on the pressure sensor. Then, the model of the zero velocity detection method using the plantar pressure is established. Finally, the indoor and outdoor multi-scene experiments show that this method not only has a high detection accuracy, but also has good adaptability to users and walking environment.

scholarly journals Ablation studies on YOLOFruit detection algorithm for fruit harvesting robot using deep learning

2021 ◽  
Vol 922 (1) ◽  
pp. 012001
Author(s):  
O M Lawal ◽  
Z Huamin ◽  
Z Fan
Keyword(s):  
Detection Efficiency ◽  
Activation Function ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Detection Time ◽  
Detection Algorithms ◽  
Spatial Pyramid Pooling ◽  
Feature Pyramid ◽  
Harvesting Robot ◽  
Spatial Pyramid

Abstract Fruit detection algorithm as an integral part of harvesting robot is expected to be robust, accurate, and fast against environmental factors such as occlusion by stem and leaves, uneven illumination, overlapping fruit and many more. For this reason, this paper explored and compared ablation studies on proposed YOLOFruit, YOLOv4, and YOLOv5 detection algorithms. The final selected YOLOFruit algorithm used ResNet43 backbone with Combined activation function for feature extraction, Spatial Pyramid Pooling Network (SPPNet) for detection accuracies, Feature Pyramid Network (FPN) for feature pyramids, Distance Intersection Over Union-Non Maximum Suppression (DIoU-NMS) for detection efficiency and accuracy, and Complete Intersection Over Union (CIoU) loss for faster and better performance. The obtained results showed that the average detection accuracy of YOLOFruit at 86.2% is 1% greater than YOLOv4 at 85.2% and 4.3% higher than YOLOv5 at 81.9%, while the detection time of YOLOFruit at 11.9ms is faster than YOLOv4 at 16.6ms, but not with YOLOv5 at 2.7ms. Hence, the YOLOFruit detection algorithm is highly prospective for better generalization and real-time fruit detection.

Accuracy Analysis of Centroid Detection Method Used to Star Sensor

2012 ◽  
Vol 468-471 ◽  
pp. 401-404 ◽  
Author(s):  
Qi Li ◽  
Wei Xu ◽  
Zhi Hai Xu ◽  
Hua Jun Feng
Keyword(s):  
Simulation Experiment ◽  
Detection Method ◽  
Detection Algorithm ◽  
Motion Blur ◽  
Detection Accuracy ◽  
Star Sensor ◽  
Detection Algorithms ◽  
Satellite Attitude ◽  
Centroid Detection ◽  
Acceptable Parameter

Star sensor is important equipment for measuring satellite attitude and motion, and star centroid detection accuracy is the basis of the overall accuracy of star sensor. In star sensors, slightly- defocus method is often adopted to acquire dispersive light spots so as to facilitate centroid detection, and certain motion blur can also be introduced because of the motion of satellites. In this paper, we analyzed several commonly-used centroid detection algorithms by using simulation experiment to study the influence of defocus and motion parameters on the accuracy of centroid detection algorithm and provided acceptable parameter value ranges.

Study on the Method of Pedestrian Detection in Automobile Safety System

2012 ◽  
Vol 580 ◽  
pp. 118-121
Author(s):  
Zhong Hao Bai ◽  
Zhi Peng Ding ◽  
Qiang Yan
Keyword(s):  
Traffic Accidents ◽  
Detection Method ◽  
Detection System ◽  
Pedestrian Detection ◽  
Active Safety ◽  
Detection Accuracy ◽  
Cascade Algorithm ◽  
Automobile Safety ◽  
High Detection ◽  
Detection Effect

In order to improve automobile active safety performance, and reduce the traffic accidents between pedestrians and vehicles, a pedestrian detection method combined with pedestrian contour features is proposed based on the combination of the reliable Adaboost and SVM. For the requirements of fast and accurate pedestrian detection system, ten types of haar-like features are given as the coarse features firstly, and which are trained through Adaboost cascade algorithm to ensure the system with a high detection speed. Then, the hog features of strong ability to distinguish pedestrians are selected as the fine features, and the pedestrian classifier is got by using SVM of different kernels to improve the detection accuracy. It is shown that the method has a higher detection rate and achieves a better detection effect.

Sign in / Sign up

Export Citation Format

Share Document