Research on detection algorithm of lithium battery surface defects based on embedded machine vision

2021 ◽  
pp. 1-9
Author(s):  
Yonggang Chen ◽  
Yufeng Shu ◽  
Xiaomian Li ◽  
Changwei Xiong ◽  
Shenyi Cao ◽  
...  
Keyword(s):  
Lithium Battery ◽  
Surface Defects ◽  
Visual Detection ◽  
Rapid Development ◽  
Detection Algorithm ◽  
Large Error ◽  
Detection Algorithms ◽  
Manual Inspection ◽  
Low Efficiency ◽  
Vision Detection

In the production process of lithium battery, the quality inspection requirements of lithium battery are very high. At present, most of the work is done manually. Aiming at the problem of large manual inspection workload and large error, the robot visual inspection technology is applied to the production of lithium battery. In recent years, with the rapid development and progress of science and technology, the rapid development of visual detection hardware and algorithms, making it possible to screen defective products through visual detection algorithms. This paper takes lithium battery as the research object, and studies its vision detection algorithm. As a common commodity, the quality of lithium battery is the key for users to choose. With the increasing requirements of users for battery quality, how to produce high-quality battery is the key problem to be solved by manufacturers. However, at present, the defects of battery surface are mostly carried out manually. There are low efficiency and low detection rate in the process of manual detection. In this paper, the visual detection algorithm is studied to detect the defects such as pits, rust marks and broken skin on the surface of lithium battery, specifically to design the imaging experimental platform of lithium battery; use different lighting schemes to design different battery positioning and extraction algorithms; use Hough detection method to locate the battery surface, and design the battery defect algorithm for this, and compare the algorithm through experiments.

scholarly journals Research on Visual Detection Algorithm of 500kV High Voltage Live Operating Robot

2021 ◽  
Vol 2087 (1) ◽  
pp. 012093
Author(s):  
Suping Guo ◽  
Jun Deng ◽  
Yahui Fan ◽  
Sijing Dai
Keyword(s):  
Transmission Line ◽  
High Voltage ◽  
Visual Detection ◽  
Detection Algorithm ◽  
Operating Efficiency ◽  
Detection Technology ◽  
Power Operation ◽  
Low Efficiency ◽  
Working Device ◽  
Vision Detection

Abstract The 500kV transmission line is exposed to the outdoor for a long time. It is affected by complex climate charge change and other factors which leads to line connection parts bolt loosening, wire breaking and fixture damage and other line failures. In order to ensure the stable transmission of electric energy, power operators need to wear shielding suits and work in the high-risk and high-voltage environment. Use of electric power operation robot instead of manual operation is an effective way to liberate maintenance staff labor. But robots still have some problems such as low degree of automation and low efficiency of power operation. Machine vision detection technology in recent years has been widely used in major areas including deep learning as emerging visual detection technology shows excellent performance. In this paper, the vision detection algorithm is studied respectively for the bolt fastening end working device and wire repairing end working device of the live transmission line robot to improve the operating efficiency of the robot.

scholarly journals A Method of Green Citrus Detection in Natural Environments Using a Deep Convolutional Neural Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Zhenhui Zheng ◽  
Juntao Xiong ◽  
Huan Lin ◽  
Yonglin Han ◽  
Baoxia Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Performance ◽  
Visual Detection ◽  
Detection Algorithm ◽  
Natural Environments ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Color Similarity ◽  
Feature Pyramid

The accurate detection of green citrus in natural environments is a key step in realizing the intelligent harvesting of citrus through robotics. At present, the visual detection algorithms for green citrus in natural environments still have poor accuracy and robustness due to the color similarity between fruits and backgrounds. This study proposed a multi-scale convolutional neural network (CNN) named YOLO BP to detect green citrus in natural environments. Firstly, the backbone network, CSPDarknet53, was trimmed to extract high-quality features and improve the real-time performance of the network. Then, by removing the redundant nodes of the Path Aggregation Network (PANet) and adding additional connections, a bi-directional feature pyramid network (Bi-PANet) was proposed to efficiently fuse the multilayer features. Finally, three groups of green citrus detection experiments were designed to evaluate the network performance. The results showed that the accuracy, recall, mean average precision (mAP), and detection speed of YOLO BP were 86, 91, and 91.55% and 18 frames per second (FPS), respectively, which were 2, 7, and 4.3% and 1 FPS higher than those of YOLO v4. The proposed detection algorithm had strong robustness and high accuracy in the complex orchard environment, which provides technical support for green fruit detection in natural environments.

A dual U-Net algorithm for automating feature extraction from satellite imagery

2021 ◽  
pp. 154851292098354
Author(s):  
Samuel Humphries ◽  
Trevor Parker ◽  
Bryan Jonas ◽  
Bryan Adams ◽  
Nicholas J Clark
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Satellite Images ◽  
Detection Algorithm ◽  
Military Operations ◽  
Detection Algorithms ◽  
Us Military ◽  
Standard Product ◽  
Different Types ◽  
Road Intersections

Quick identification of building and roads is critical for execution of tactical US military operations in an urban environment. To this end, a gridded, referenced, satellite images of an objective, often referred to as a gridded reference graphic or GRG, has become a standard product developed during intelligence preparation of the environment. At present, operational units identify key infrastructure by hand through the work of individual intelligence officers. Recent advances in Convolutional Neural Networks, however, allows for this process to be streamlined through the use of object detection algorithms. In this paper, we describe an object detection algorithm designed to quickly identify and label both buildings and road intersections present in an image. Our work leverages both the U-Net architecture as well the SpaceNet data corpus to produce an algorithm that accurately identifies a large breadth of buildings and different types of roads. In addition to predicting buildings and roads, our model numerically labels each building by means of a contour finding algorithm. Most importantly, the dual U-Net model is capable of predicting buildings and roads on a diverse set of test images and using these predictions to produce clean GRGs.

scholarly journals Design of bio-inspired binocular UAV detection system based on improved STC algorithm of scale transformation and occlusion detection

2021 ◽  
Vol 13 ◽  
pp. 175682932110048
Author(s):  
Huajun Song ◽  
Yanqi Wu ◽  
Guangbing Zhou
Keyword(s):  
Detection System ◽  
Rapid Development ◽  
Reference Value ◽  
Scale Transformation ◽  
Hardware System ◽  
Time Requirements ◽  
Aerial Vehicle ◽  
Spatio Temporal ◽  
Small Targets ◽  
Vision Detection

With the rapid development of drones, many problems have arisen, such as invasion of privacy and endangering security. Inspired by biology, in order to achieve effective detection and robust tracking of small targets such as unmanned aerial vehicles, a binocular vision detection system is designed. The system is composed of long focus and wide-angle dual cameras, servo pan tilt, and dual processors for detecting and identifying targets. In view of the shortcomings of spatio-temporal context target tracking algorithm that cannot adapt to scale transformation and easy to track failure in complex scenes, the scale filter and loss criterion are introduced to make an improvement. Qualitative and quantitative experiments show that the designed system can adapt to the scale changes and partial occlusion conditions in the detection, and meets the real-time requirements. The hardware system and algorithm both have reference value for the application of anti-unmanned aerial vehicle systems.

scholarly journals A novel algorithm to detect non-wear time from raw accelerometer data using deep convolutional neural networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shaheen Syed ◽  
Bente Morseth ◽  
Laila A. Hopstock ◽  
Alexander Horsch
Keyword(s):  
Threshold Value ◽  
Detection Algorithm ◽  
Classification Model ◽  
Type I ◽  
Accelerometer Data ◽  
Deep Convolutional Neural Networks ◽  
Major Drawback ◽  
Wear Time ◽  
Detection Algorithms ◽  
Type Ii Errors

AbstractTo date, non-wear detection algorithms commonly employ a 30, 60, or even 90 mins interval or window in which acceleration values need to be below a threshold value. A major drawback of such intervals is that they need to be long enough to prevent false positives (type I errors), while short enough to prevent false negatives (type II errors), which limits detecting both short and longer episodes of non-wear time. In this paper, we propose a novel non-wear detection algorithm that eliminates the need for an interval. Rather than inspecting acceleration within intervals, we explore acceleration right before and right after an episode of non-wear time. We trained a deep convolutional neural network that was able to infer non-wear time by detecting when the accelerometer was removed and when it was placed back on again. We evaluate our algorithm against several baseline and existing non-wear algorithms, and our algorithm achieves a perfect precision, a recall of 0.9962, and an F1 score of 0.9981, outperforming all evaluated algorithms. Although our algorithm was developed using patterns learned from a hip-worn accelerometer, we propose algorithmic steps that can easily be applied to a wrist-worn accelerometer and a retrained classification model.

Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings

2021 ◽  
pp. 1-18
Author(s):  
Hui Liu ◽  
Boxia He ◽  
Yong He ◽  
Xiaotian Tao
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Seal Ring ◽  
Fine Grained ◽  
Aerospace Applications ◽  
Surface Defect Detection ◽  
The Mean

The existing seal ring surface defect detection methods for aerospace applications have the problems of low detection efficiency, strong specificity, large fine-grained classification errors, and unstable detection results. Considering these problems, a fine-grained seal ring surface defect detection algorithm for aerospace applications is proposed. Based on analysis of the stacking process of standard convolution, heat maps of original pixels in the receptive field participating in the convolution operation are quantified and generated. According to the generated heat map, the feature extraction optimization method of convolution combinations with different dilation rates is proposed, and an efficient convolution feature extraction network containing three kinds of dilated convolutions is designed. Combined with the O-ring surface defect features, a multiscale defect detection network is designed. Before the head of multiscale classification and position regression, feature fusion tree modules are added to ensure the reuse and compression of the responsive features of different receptive fields on the same scale feature maps. Experimental results show that on the O-rings-3000 testing dataset, the mean condition accuracy of the proposed algorithm reaches 95.10% for 5 types of surface defects of aerospace O-rings. Compared with RefineDet, the mean condition accuracy of the proposed algorithm is only reduced by 1.79%, while the parameters and FLOPs are reduced by 35.29% and 64.90%, respectively. Moreover, the proposed algorithm has good adaptability to image blur and light changes caused by the cutting of imaging hardware, thus saving the cost.

Structural Design of Intrusion Detection System

2014 ◽  
Vol 530-531 ◽  
pp. 705-708
Author(s):  
Yao Meng
Keyword(s):  
Intrusion Detection ◽  
Structural Design ◽  
Intrusion Detection System ◽  
Detection System ◽  
Algorithm Design ◽  
Detection Algorithm ◽  
Attack Detection ◽  
Detection Algorithms ◽  
Defense Systems ◽  
Ddos Attack Detection

This paper first engine starting defense from Intrusion Detection, Intrusion detection engine analyzes the hardware platform, the overall structure of the technology and the design of the overall structure of the plug, which on the whole structure from intrusion defense systems were designed; then described in detail improved DDOS attack detection algorithm design thesis, and the design of anomaly detection algorithms.

An Image Change Detection Algorithm Based on Multi-Feature Self-Attention Fusion Mechanism UNet Network

2021 ◽  
Author(s):  
Gulnaz Alimjan ◽  
Yiliyaer Jiaermuhamaiti ◽  
Huxidan Jumahong ◽  
Shuangling Zhu ◽  
Pazilat Nurmamat
Keyword(s):  
Change Detection ◽  
Detection Algorithm ◽  
Convolutional Network ◽  
Detection Algorithms ◽  
Multiple Dimensions ◽  
Change Detection Algorithms ◽  
Image Change Detection ◽  
Control Loss ◽  
The Relationship ◽  
Entire Network

Various UNet architecture-based image change detection algorithms promote the development of image change detection, but there are still some defects. First, under the encoder–decoder framework, the low-level features are extracted many times in multiple dimensions, which generates redundant information; second, the relationship between each feature layer is not modeled so sufficiently that it cannot produce the optimal feature differentiation representation. This paper proposes a remote image change detection algorithm based on the multi-feature self-attention fusion mechanism UNet network, abbreviated as MFSAF UNet (multi-feature self-attention fusion UNet). We attempt to add multi-feature self-attention mechanism between the encoder and decoder of UNet to obtain richer context dependence and overcome the two above-mentioned restrictions. Since the capacity of convolution-based UNet network is directly proportional to network depth, and a deeper convolutional network means more training parameters, so the convolution of each layer of UNet is replaced as a separated convolution, which makes the entire network to be lighter and the model’s execution efficiency is slightly better than the traditional convolution operation. In addition to these, another innovation point of this paper is using preference to control loss function and meet the demands for different accuracies and recall rates. The simulation test results verify the validity and robustness of this approach.

scholarly journals A Corner Detection Algorithm Based on Regional Center of Mass in Imaging through Water Surface

2021 ◽  
Vol 2083 (3) ◽  
pp. 032090
Author(s):  
Changli Mai ◽  
Bijian Jian ◽  
Yongfa Ling
Keyword(s):  
Water Surface ◽  
Center Of Mass ◽  
Detection Algorithm ◽  
Corner Detection ◽  
Random Fluctuation ◽  
False Detection ◽  
Detection Algorithms ◽  
Regional Center ◽  
Underwater Environment ◽  
Active Imaging

Abstract Structural light active imaging can obtain more information about the target scene, which is widely used in image registration,3D reconstruction of objects and motion detection. Due to the random fluctuation of water surface and complex underwater environment, the current corner detection algorithm has the problems of false detection and uncertainty. This paper proposes a corner detection algorithm based on the region centroid extraction. Experimental results show that, compared with the traditional detection algorithms, the proposed algorithm can extract the feature point information of the image in real time, which is of great significance to the subsequent image restoration.

scholarly journals STABILIZATION OF SENTINEL-1 SAR TIME-SERIES USING CLIMATE AND FOREST STRUCTURE DATA FOR EARLY TROPICAL DEFORESTATION DETECTION

2020 ◽  
Vol V-3-2020 ◽  
pp. 89-96
Author(s):  
J. Doblas ◽  
A. Carneiro ◽  
Y. Shimabukuro ◽  
S. Sant’Anna ◽  
L. Aragão ◽  
...  
Keyword(s):  
Time Series ◽  
Forest Structure ◽  
Detection Algorithm ◽  
Structure Information ◽  
Detection Algorithms ◽  
Alternative State ◽  
Level Data ◽  
Relevant Variables ◽  
Long Time ◽  
Omission Errors

Abstract. In this study we analyse the factors of variability of Sentinel-1 C-band radar backscattering over tropical rainforests, and propose a method to reduce the effects of this variability on deforestation detection algorithms. To do so, we developed a random forest regression model that relates Sentinel-1 gamma nought values with local climatological data and forest structure information. The model was trained using long time-series of 26 relevant variables, sampled over 6 undisturbed tropical forests areas. The resulting model explained 71.64% and 73.28% of the SAR signal variability for VV and VH polarizations, respectively. Once the best model for every polarization was selected, it was used to stabilize extracted pixel-level data of forested and non-deforested areas, which resulted on a 10 to 14% reduction of time-series variability, in terms of standard deviation. Then a statistically robust deforestation detection algorithm was applied to the stabilized time-series. The results show that the proposed method reduced the rate of false positives on both polarizations, especially on VV (from 21% to 2%, α=0.01). Meanwhile, the omission errors increased on both polarizations (from 27% to 37% in VV and from 27% to 33% on VV, α=0.01). The proposed method yielded slightly better results when compared with an alternative state-of-the-art approach (spatial normalization).

Sign in / Sign up

Export Citation Format

Share Document