Existing Detection Algorithms Research Articles

Development of machine learning model for automatic ELM-burst detection without hyperparameter adjustment in KSTAR tokamak

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

Detection of microaneurysms in fundus images based on improved YOLOv4 with SENet embedded

Microaneurysm is the initial symptom of diabetic retinopathy. Eliminating this lesion can effectively prevent diabetic retinopathy in the early stage. However, due to the complex retinal structure and the different brightness and contrast of fundus image because of different factors such as patients, environment and acquisition equipment, the existing detection algorithms are difficult to achieve the accurate detection and location of the lesion. Therefore, an improved detection algorithm of you only look once (YOLO) v4 with Squeeze-and-Excitation networks (SENet) embedded was proposed. Firstly, an improved and fast fuzzy c-means clustering algorithm was used to optimize the anchor parameters of the target samples to improve the matching degree between the anchors and the feature graphs; Then, the SENet attention module was embedded in the backbone network to enhance the key information of the image and suppress the background information of the image, so as to improve the confidence of microaneurysms; In addition, an spatial pyramid pooling was added to the network neck to enhance the acceptance domain of the output characteristics of the backbone network, so as to help separate important context information; Finally, the model was verified on the Kaggle diabetic retinopathy dataset and compared with other methods. The experimental results showed that compared with other YOLOv4 network models with various structures, the improved YOLOv4 network model could significantly improve the automatic detection results such as F-score which increased by 12.68%; Compared with other network models and methods, the automatic detection accuracy of the improved YOLOv4 network model with SENet embedded was obviously better, and accurate positioning could be realized. Therefore, the proposed YOLOv4 algorithm with SENet embedded has better performance, and can accurately and effectively detect and locate microaneurysms in fundus images.

An Improved YOLOv5-Based Tapping Trajectory Detection Method for Natural Rubber Trees

The object detection algorithm is one of the core technologies of the intelligent rubber tapping robot, but most of the existing detection algorithms cannot effectively meet the tapping trajectory detection of natural rubber trees in the complex forest environment. This paper proposes a tapping trajectory detection method for natural rubber trees based on an improved YOLOv5 model to accomplish fast and accurate detection. Firstly, the coordinate attention (CA) mechanism is added to the Backbone network to embed the location information into the channel attention, which effectively improves the detection accuracy. Secondly, a module called convolution and GhostBottleneck (CGB) is designed, based on the Ghost module, to substitute the Cross Stage Partial Network (CSP) module in the Neck network, which ensures the detection accuracy while reducing model parameters. Finally, the EIoU loss function is introduced to enable a more accurate regression of the model. The experimental results show that the overall performance of the YOLOv5-CCE model outperforms the original YOLOv5 and other classical lightweight detection algorithms. Compared with the original YOLOv5 model, the YOLOv5-CCE model has a 2.1% improvement in mAP value, a 2.5% compression of model parameters, and a 7.0% reduction in the number of floating point operations (FLOPs). Therefore, the improved model can fully meet the requirements of real-time detection, providing a robust detection method for rubber tapping robots.

SF-YOLOv5: A Lightweight Small Object Detection Algorithm Based on Improved Feature Fusion Mode.

In the research of computer vision, a very challenging problem is the detection of small objects. The existing detection algorithms often focus on detecting full-scale objects, without making proprietary optimization for detecting small-size objects. For small objects dense scenes, not only the accuracy is low, but also there is a certain waste of computing resources. An improved detection algorithm was proposed for small objects based on YOLOv5. By reasonably clipping the feature map output of the large object detection layer, the computing resources required by the model were significantly reduced and the model becomes more lightweight. An improved feature fusion method (PB-FPN) for small object detection based on PANet and BiFPN was proposed, which effectively increased the detection ability for small object of the algorithm. By introducing the spatial pyramid pooling (SPP) in the backbone network into the feature fusion network and connecting with the model prediction head, the performance of the algorithm was effectively enhanced. The experiments demonstrated that the improved algorithm has very good results in detection accuracy and real-time ability. Compared with the classical YOLOv5, the mAP@0.5 and mAP@0.5:0.95 of SF-YOLOv5 were increased by 1.6% and 0.8%, respectively, the number of parameters of the network were reduced by 68.2%, computational resources (FLOPs) were reduced by 12.7%, and the inferring time of the mode was reduced by 6.9%.

Using Machine Learning Algorithm to Detect Blowing Snow and Fog in Antarctica Based on Ceilometer and Surface Meteorology Systems

Blowing snow is a common weather phenomenon in Antarctica and plays an important role in the water vapor cycle and ice sheet mass balance. Although it has a significant impact on the climate of Antarctica, people do not know much about this process. Fog events are difficult to distinguish from blowing snow events using existing detection algorithms by a ceilometer. In this study, based on ceilometer, the meteorological parameters observed by surface meteorology systems are further combined to detect blowing snow and fog using the AdaBoost algorithm. The weather phenomena recorded by human observers are ‘true’. The dataset is collected from 1 January 2016 to 31 December 2016 at the AWARE site. Among them, three-quarters of the data are used as the training set and the rest of the data as the testing set. The classification accuracy of the proposed algorithm for the testing set is about 94%. Compared with the Loeb method, the proposed algorithm can detect 89.12% of blowing snow events and 76.10% of fog events, while the Loeb method can only identify 64.29% of blowing snow events and 31.87% of fog events.

A ROBUST QRS COMPLEX DETECTION METHOD BASED ON SHANNON ENERGY ENVELOPE AND HILBERT TRANSFORM

QRS complex detection plays an important role in electrocardiogram (ECG) automatic analysis. The accuracy and robustness of the detection algorithm greatly affect its practicability. However, the existing detection algorithms are greatly affected by ECG signal quality, and some detection algorithms cannot even work properly due to the poor signal quality. In this paper, a robust QRS complex detection algorithm is proposed based on Shannon energy envelope and Hilbert transform. The detection algorithm extracts the Shannon energy envelope of the preprocessed ECG signal, performs Hilbert transform on the envelope signal, then detects the suspected [Formula: see text]-peaks on the envelope by detecting the position of zero pass and screens the real [Formula: see text]-peaks by using a combination of ECG refractory period and backtracking mechanism. The proposed detection algorithm is validated using MIT-BIH Arrhythmia Database, and achieves the average detection accuracy of 99.69%, sensitivity of 99.81% and positive predictivity of 99.88%. Experimental results show that the proposed detection algorithm can still detect QRS complex correctly under complex interference, and the performance of the algorithm is hardly affected.

Adaptive dense pyramid network for object detection in UAV imagery

Object detection in Unmanned Aerial Vehicle (UAV) imagery has a wide variety of applications in both military and civilian fields. As UAV images are usually captured from flexible perspectives, with multiple altitudes, containing objects in various sizes and scales, such characteristics bring huge challenges to the object detection task. To address this issue, we develop a novel Adaptive Dense Pyramid Network (ADPN) that integrates congested scene analysis, aiming to incorporate the object distribution information into the object detection workflow without introducing additional annotations. We also design a creative Pyramid Density Module (PDM) for adaptive density prediction. The proposed ADPN incorporates the PDM and Object Detection Module (ODM) in a parallel manner to facilitate the feature alignment between density information and instance recognition. Our method can be applied to existing detection algorithms, and experimental results demonstrate the effectiveness and robustness of ADPN, and ADPN is able to improve detection accuracy on challenging datasets.

Traffic Sign Detection via Improved Sparse R-CNN for Autonomous Vehicles

Traffic sign detection is an important component of autonomous vehicles. There is still a mismatch problem between the existing detection algorithm and its practical application in real traffic scenes, which is mainly due to the detection accuracy and data acquisition. To tackle this problem, this study proposed an improved sparse R-CNN that integrates coordinate attention block with ResNeSt and builds a feature pyramid to modify the backbone, which enables the extracted features to focus on important information, and improves the detection accuracy. In order to obtain more diverse data, the augmentation method used is specifically designed for complex traffic scenarios, and we also present a traffic sign dataset in this study. For on-road autonomous vehicles, we designed two modules, self-adaption augmentation (SAA) and detection time augmentation (DTA), to improve the robustness of the detection algorithm. The evaluations on traffic sign datasets and on-road testing demonstrate the accuracy and effectiveness of the proposed method.

Group-Wise Sidelink Synchronization Signal and Carrier Frequency Offset Detection Method for D2D-Based NR-V2X Systems

This article proposes an effective joint sidelink secondary synchronization signal (S-SSS) and carrier frequency offset (CFO) detection method for device-to-device-based new radio vehicle-to-everything networks. In order to improve the S-SSS and CFO detection performance, the proposed method uses a group-by-group correlation between four consecutive sidelink synchronization signals. The benefits and drawbacks of the proposed detection scheme are presented, and a theoretical analysis is derived, which is further discussed by means of simulation results. Both analytical results and simulations show that the proposed solution attains an improved detection performance using a group-wise correlation with slightly increased complexity, compared to existing detection algorithms.

Ground Obstacle Detection Technology Based on Fusion of RGB-D and Inertial Sensors

Aiming at the real-time detection of ground obstacles in the passable area for the visually impaired, a ground obstacle detection technology based on the fusion of RGB-D and inertial sensor is proposed. Firstly, the spatial model of the ground obstacle is established, and the inertial sensor parameters are fused to calculate the camera inclination to correct the world coordinates of the ground obstacle. Secondly, according to the actual scenes and needs of the visually impaired, the remote detection pixels in the depth image are removed by threshold segmentation algorithm, and the depth map is divided into 4 regions, and the dynamic division of ROI is realized by fusing inertial sensor data. Finally, an obstacle detection algorithm is designed by improved RANSAC algorithm based on the growth of ground area algorithm, and collected real data for experimental verification. The experimental results show that the accuracy and recall rates of the proposed technology reach 90.87% and 89.33%, and better than the existing detection algorithms in the time efficiency of execution, which meets the real-time requirements of the algorithm for the visually impaired.

A DFDD Based Detector for Space-Time Block Coded Differential Spatial Modulation Under Time-Selective Channels

Space-time block coded differential spatial modulation (STBC-DSM) is a recently proposed spectral efficient multiple-input-multiple-output (MIMO) transmission technique. Existing detection algorithms for STBC-DSM are designed for quasi-static channels, which limits the application of STBC-DSM in fast fading channels. In this letter, we propose a novel decision-feedback differential detection (DFDD) based detector for STBC-DSM system under fast-fading channels. The proposed detector mitigates the impact of channel vector changes by using the DFDD metric which contains multiple previous detection results. Simulation results show that the proposed detector is more tolerable in time-selective channels than other existing STBC-DSM detectors.

A Real-Time Zanthoxylum Target Detection Method for an Intelligent Picking Robot under a Complex Background, Based on an Improved YOLOv5s Architecture

The target recognition algorithm is one of the core technologies of Zanthoxylum pepper-picking robots. However, most existing detection algorithms cannot effectively detect Zanthoxylum fruit covered by branches, leaves and other fruits in natural scenes. To improve the work efficiency and adaptability of the Zanthoxylum-picking robot in natural environments, and to recognize and detect fruits in complex environments under different lighting conditions, this paper presents a Zanthoxylum-picking-robot target detection method based on improved YOLOv5s. Firstly, an improved CBF module based on the CBH module in the backbone is raised to improve the detection accuracy. Secondly, the Specter module based on CBF is presented to replace the bottleneck CSP module, which improves the speed of detection with a lightweight structure. Finally, the Zanthoxylum fruit algorithm is checked by the improved YOLOv5 framework, and the differences in detection between YOLOv3, YOLOv4 and YOLOv5 are analyzed and evaluated. Through these improvements, the recall rate, recognition accuracy and mAP of the YOLOv5s are 4.19%, 28.7% and 14.8% higher than those of the original YOLOv5s, YOLOv3 and YOLOv4 models, respectively. Furthermore, the model is transferred to the computing platform of the robot with the cutting-edge NVIDIA Jetson TX2 device. Several experiments are implemented on the TX2, yielding an average time of inference of 0.072, with an average GPU load in 30 s of 20.11%. This method can provide technical support for pepper-picking robots to detect multiple pepper fruits in real time.

DeepTag: A General Framework for Fiducial Marker Design and Detection.

A fiducial marker system usually consists of markers, a detection algorithm, and a coding system. The appearance of markers and the detection robustness are generally limited by the existing detection algorithms, which are hand-crafted with traditional low-level image processing techniques. Furthermore, a sophisticatedly designed coding system is required to overcome the shortcomings of both markers and detection algorithms. To improve the flexibility and robustness in various applications, we propose a general deep learning based framework, DeepTag, for fiducial marker design and detection. DeepTag not only supports detection of a wide variety of existing marker families, but also makes it possible to design new marker families with customized local patterns. Moreover, we propose an effective procedure to synthesize training data on the fly without manual annotations. Thus, DeepTag can easily adapt to existing and newly-designed marker families. To validate DeepTag and existing methods, beside existing datasets, we further collect a new large and challenging dataset where markers are placed in different view distances and angles. Experiments show that DeepTag well supports different marker families and greatly outperforms the existing methods in terms of both detection robustness and pose accuracy. Both code and dataset are available at https://herohuyongtao.github.io/research/publications/deep-tag/.

Round Traffic Sign Detection Algorithm

Traffic signs are an important part of autonomous driving and intelligent transportation. It provides instructions for pedestrians and vehicles and is critical to road traffic safety. However, existing detection algorithms cannot achieve real-time high-precision detection. Therefore, this paper proposes an algorithm that combines traditional methods with deep learning to detect circular traffic signs. Based on the HSV color space, the red and blue channel images are separated, and the candidate regions of the original image are extracted using the Hough transform. The shallow convolutional neural network (CNN) classifier rejects not traffic signs and classifies traffic signs. Experiments show that the algorithm is real and effective. On the CPU platform, the average accuracy rate is 96.2%, and the detection speed reaches 0.3 s / frame. Under the condition of ensuring the average accuracy rate, the detection speed is greatly reduced. The algorithm achieves the fastest speed, which makes real-time high-precision detection possible. The algorithm is more suitable for vehicle embedded systems.

A two-step method for paroxysmal atrial fibrillation event detection based on machine learning.

Detection of atrial fibrillation (AF) events is significant for early clinical diagnosis and appropriate intervention. However, in existing detection algorithms for paroxysmal AF (AFp), the location of AF starting and ending points in AFp is not concerned. To achieve an accurate identification of AFp events in the long-term dynamic electrocardiograms (ECGs), this paper proposes a two-step method based on machine learning. In the first step, based on features extracted from the calculated R-to-R intervals (RR intervals, the cycle of heart beat), the rhythm type of the ECG signal is first classified into three classes (AFp rhythm, persistent AF (AFf) rhythm, and non-atrial fibrillation (non-AF, N) rhythm) using support vector machine (SVM). In the second step, the starting and ending points for AF episodes of AFp rhythms predicted in the first step are further located based on heartbeat classification. By training a deep convolutional neural network with phased training, the segmented beats of AFp rhythms are divided into AF beats and non-AF beats to determine the beginning and end of any AF episode. The proposed two-step method is trained and tested on the 4th China Physiological Signal Challenge 2021 databases. A final score U of 1.9310 is obtained on the unpublished test set maintained by the challenge organizers, which demonstrates the advantage of the two-step method in AFp event detection. The work is useful for assessing AF burden index for AFp patients.

Reliable detection of pulse arrival time for partial discharge location in HV cable based on improved Allen-Bear algorithm

In multi-sensor data based partial discharge (PD) source location in high voltage (HV) cable, poor reliability of detection of pulse arrival time against noises, waveform distortion, amplitude attenuation is the major barriers to practical application. In this paper, an improved Allen-Bear PD pulse detection algorithm, which combines the advantage of the characteristic functions of the two time-window energy ratio based detection algorithms, is proposed for robust PD location. The most critical contribution of proposed method is the extension of frequency domain component compared to the characteristic functions of the original algorithm. Simulation and physical experiment results demonstrate that the proposed method not only ensures the detection accuracy of the PD pulse arrival time, but also improves the reliability under harsh practical scenarios. It performs significantly better than the existing detection algorithm in terms of anti-noise, anti-waveform distortion, time window length variation, etc. It has significant value for practical applications.

TWO-LEAD JOINT DETECTION ALGORITHM OF QRS COMPLEXES IN ECG SIGNAL

Objective: The detection of QRS complexes is an important part of computer-aided analysis of electrocardiogram (ECG). However, most of the existing detection algorithms are mainly for single-lead ECG signals, which requires high quality of signal. If the signal quality decreases suddenly due to some interference, then the current algorithm is easy to cause misjudgment or missed detection. To improve the detection ability of QRS complexes under sudden interference, we study the QRS complexes information on multiple leads in-depth, and propose a two-lead joint detection algorithm of QRS complexes. Methods: Firstly, the suspected QRS complexes are screened on the main lead. For the suspected QRS complexes with low confidence and the complexes that may be missed, further accurate detection and joint judgment shall be carried out at the corresponding position of the auxiliary lead. At the same time, the adaptive threshold adjustment algorithm and backtracking mechanism are used to modify the detection results. Results: The proposed detection algorithm is validated using 48 ECG records of the MIT-BIH arrhythmia database, and achieves average detection accuracy of 99.71%, sensitivity of 99.88% and positive predictivity of 99.81%. Conclusion: The proposed algorithm has high accuracy, which can effectively deal with the sudden interference of ECG signal. Meanwhile, the algorithm requires small amount of computation, and can be embedded into hardware for real-time detection.

Research on Remote Sensing Image Target Detection Methods Based on Convolutional Neural Networks

Remote sensing image is extremely important for the study of natural and social phenomena and environmental analysis, remote sense image with a complex background, the goal is relatively small, arbitrary direction and disordered distribution, difficult access to information. With the continuous development of convolutional neural networks, great achievements have been made in target detection on natural images, which provides a good solution for obtaining remote sensing image information. How to improve the existing detection algorithms to make them more suitable for the characteristics of remote sensing images has become the main research direction in the current exploration of remote sensing image information. This paper reviews the existing research results of target detection on remote sensing images in detail, and finally looks forward to the future research directions of target detection methods in remote sensing images.

A Real-Time Detection Algorithm for Kiwifruit Defects Based on YOLOv5

Defect detection is the most important step in the postpartum reprocessing of kiwifruit. However, there are some small defects difficult to detect. The accuracy and speed of existing detection algorithms are difficult to meet the requirements of real-time detection. For solving these problems, we developed a defect detection model based on YOLOv5, which is able to detect defects accurately and at a fast speed. The main contributions of this research are as follows: (1) a small object detection layer is added to improve the model’s ability to detect small defects; (2) we pay attention to the importance of different channels by embedding SELayer; (3) the loss function CIoU is introduced to make the regression more accurate; (4) under the prerequisite of no increase in training cost, we train our model based on transfer learning and use the CosineAnnealing algorithm to improve the effect. The results of the experiment show that the overall performance of the improved network YOLOv5-Ours is better than the original and mainstream detection algorithms. The mAP@0.5 of YOLOv5-Ours has reached 94.7%, which was an improvement of nearly 9%, compared to the original algorithm. Our model only takes 0.1 s to detect a single image, which proves the effectiveness of the model. Therefore, YOLOv5-Ours can well meet the requirements of real-time detection and provides a robust strategy for the kiwi flaw detection system.

A Hybrid DC Fault Primary Protection Algorithm for Multi-Terminal HVdc Systems

Protection against dc faults is one of the main technical hurdles faced when operating converter-based HVdc systems. Protection becomes even more challenging for multi-terminal dc (MTdc) systems with more than two terminals/converter stations. In this paper, a hybrid primary fault detection algorithm for MTdc systems is proposed to detect a broad range of failures. Sensor measurements, i.e., line currents and dc reactor voltages measured at local terminals, are first processed by a top-level context clustering algorithm. For each cluster, the best fault detector is selected among a detector pool according to a rule resulting from a learning algorithm. The detector pool consists of existing detection algorithms, each performing differently across fault scenarios. The proposed detection algorithm: i) offers superior performance compared to an individual detector through a data-driven approach; ii) detects all major fault types including pole-to-pole (P2P), pole-to-ground (P2G), and external dc faults; iii) identifies faults with various fault locations and impedances; iv) is more robust to noisy sensor measurements compared to existing methods; v) does not require exhaustive simulation and sampling for training the model. Performance and effectiveness of the proposed algorithm are evaluated and verified based on time-domain simulations in the PSCAD/EMTDC software environment.