Robust Detection Algorithm Research Articles

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments.

Ensuring precise calving time prediction necessitates the adoption of an automatic and precisely accurate cattle tracking system. Nowadays, cattle tracking can be challenging due to the complexity of their environment and the potential for missed or false detections. Most existing deep-learning tracking algorithms face challenges when dealing with track-ID switch cases caused by cattle occlusion. To address these concerns, the proposed research endeavors to create an automatic cattle detection and tracking system by leveraging the remarkable capabilities of Detectron2 while embedding tailored modifications to make it even more effective and efficient for a variety of applications. Additionally, the study conducts a comprehensive comparison of eight distinct deep-learning tracking algorithms, with the objective of identifying the most optimal algorithm for achieving precise and efficient individual cattle tracking. This research focuses on tackling occlusion conditions and track-ID increment cases for miss detection. Through a comparison of various tracking algorithms, we discovered that Detectron2, coupled with our customized tracking algorithm (CTA), achieves 99% in detecting and tracking individual cows for handling occlusion challenges. Our algorithm stands out by successfully overcoming the challenges of miss detection and occlusion problems, making it highly reliable even during extended periods in a crowded calving pen.

Real-time, noise and drift resilient formaldehyde sensing at room temperature with aerogel filaments

Formaldehyde, a known human carcinogen, is a common indoor air pollutant. However, its real-time and selective recognition from interfering gases remains challenging, especially for low-power sensors suffering from noise and baseline drift. We report a fully 3D-printed quantum dot/graphene-based aerogel sensor for highly sensitive and real-time recognition of formaldehyde at room temperature. By optimizing the morphology and doping of printed structures, we achieve a record-high and stable response of 15.23% for 1 part per million formaldehyde and an ultralow detection limit of 8.02 parts per billion consuming only ∼130-microwatt power. On the basis of measured dynamic response snapshots, we also develop intelligent computational algorithms for robust and accurate detection in real time despite simulated substantial noise and baseline drift, hitherto unachievable for room temperature sensors. Our framework in combining materials engineering, structural design, and computational algorithm to capture dynamic response offers unprecedented real-time identification capabilities of formaldehyde and other volatile organic compounds at room temperature.

Internet of Things Based Oil Pipeline Spill Detection System Using Deep Learning and LAB Colour Algorithm

Given the role that pipelines play in transporting crude oil, which is considered the basis of the global economy and across different environments, hundreds of studies revolve around providing the necessary protection for it. Various technologies have been employed in this pursuit, differing in terms of cost, reliability, and efficiency, among other factors. Computer vision has emerged as a prominent technique in this field, albeit requiring a robust image-processing algorithm for spill detection. This study employs image segmentation techniques to enable the computer to interpret visual information and images effectively. The research focuses on detecting spills in oil pipes caused by leakage, utilizing images captured by a drone equipped with a Raspberry Pi and Pi camera. These images, along with their global positioning system (GPS) location, are transmitted to the base station using the message queuing telemetry transport Internet of Things (MQTT IoT) protocol. At the base station, deep learning techniques, specifically Holistically-Nested Edge Detection (HED) and extreme inception (Xception) networks, are employed for image processing to identify contours. The proposed algorithm can detect multiple contours in the images. To pinpoint a contour with a black color, representative of an oil spill, the CIELAB color space (LAB) algorithm effectively removes shadow effects. If a contour is detected, its area and perimeter are calculated to determine whether it exceeds a certain threshold. The effectiveness of the proposed system was tested on Iraqi oil pipeline systems, demonstrating its capability to detect spills of different sizes.

A robust circle detector with regionalized radius aid

The detection of circles in geometric shapes is highly valued in computer vision and pattern recognition. Conventionally, the least-squares fitting is sensitive to occlusion or noise and prone to false circles. Therefore, this paper proposes a novel algorithm for robust circle detection using the least-squares fitting method combined with regionalized radius aid on the arc and chord lengths. To reduce edge noise impact, we present an edge pruning method to prune non-curve edge branch ports. Furthermore, we extract arcs based on the inflection points and sharp corners of the approximate line segment. Next, curves that belong to the arcs obtain circle parameters according to the regionalized radius aided the least-squares method. Then, valid circles are obtained by considering two distance deviations to verify the candidate circles. Finally, valid arcs that belong to the same circle are combined and refitted, wherein the most representative arc is used as the basis for the refitting of all arcs. All experiments are conducted on real images from four publicly diverse datasets (one of them is the one we built). The detection results are compared with those of representative state-of-the-art algorithms, and the proposed algorithm has several advantages based on the comparison results: more robust to noise, effective rejection of false circles, and better performance.

A novel robust memetic algorithm for dynamic community structures detection in complex networks

A novel robust memetic algorithm for dynamic community structures detection in complex networks

Online Crack Detection of Highly Curved Cylindrical Coils

Many vision-based methods for defect detection have been proposed to replace inefficient manual inspection. However, due to the complex shape and high degree of freedom required to manipulate individual coils, an automatic optical inspection (AOI) method for cylindrical coils remains unsuccessful due to the difficulty of automatically scanning the front, rear, outer, and inner faces of complex spiral-shaped cylindrical coils. This paper presents a turnkey integrated system that can be operated in real time for real coil manufacturers. First, a novel 1-degree-of-freedom rotational progressive system is designed to automatically transport and sort individual spiral coils. Second, a multisensor imaging system is designed to capture images of 360° panoramic views of a cylindrical coil. Then, a robust automatic defect detection algorithm consisting of crack detection and geometric measurement is developed to detect defects in cylindrical coils during manufacturing procedures. The results of a large-scale validation experiment indicate that the proposed AOI system is robust and is practically immune to variations in surface normal vectors, occlusion, and defocus blur, and it has a high sensitivity and specificity of 99.75% and 94.2%, respectively. This validation experiment proved that the software and hardware designed in this study can implement defect detection of spiral coils.

A Highly Robust Helmet Detection Algorithm Based on YOLO V8 and Transformer

A Highly Robust Helmet Detection Algorithm Based on YOLO V8 and Transformer

A Robust Lane Detection Algorithm Adaptable to Challenging Weather Conditions

A Robust Lane Detection Algorithm Adaptable to Challenging Weather Conditions

Generalized wide-area fault detection and location algorithm for transmission system based on optimal PMUs allocation

The transmission system is one of the three major parts besides the generation and distribution systems. Transmission system protection requires a vital especially development it involves in modern wide-area systems. This paper suggests a generalized robust fault detection and location algorithm established on the optimally allocated phasor measurement units (PMUs). The optimum allocation of PMUs ensures the entire observability of all transmission lines, that are included within the zones of protection. The generalized fault detection and location algorithm is based on the roots deduced from the basic transmission line model under normal operation. The algorithm enables to detection of faults closed to buses equipped with PMUs and high impedance single line to ground faults. The algorithm is characterized by generality and independent variable system dynamics. The proposed algorithm can detect simultaneous faults of any type with a high degree of accuracy. To validate the developed algorithm, it is utilized in the IEEE 14-bus system. The simulation study is conducted using Matlab/Simulink® software package. Different fault types are modeled under various fault resistances. The modeled fault cases prove the security of the developed algorithm against external faults with a high degree of dependability in the case of internal faults.

DEEPFAKE DETECTION USING DEEP LEARNING (CNN+LSTM)

Artificial intelligence advancements have led to the development of deepfake technology, which seriously jeopardises the integrity of visual media material. Robust detection algorithms are becoming more and more necessary as deepfake creation techniques become more complex. This study combines Long Short-Term Memory (LSTM) networks with Convolutional Neural Networks (CNNs) to present a novel method for deepfake identification. The suggested CNN+LSTM architecture makes use of LSTMs' temporal modelling capabilities and CNNs' spatial feature extraction capabilities. While the LSTM component analyses the temporal connections between frames to identify patterns suggestive of deepfake manipulation, the CNN component concentrates on capturing local features and patterns in individual frames. The combination of these two networks improves the model's capacity to identify minute anomalies and inconsistencies that are indicative of deepfake content. To extract frame-level characteristics, we use Res-Next Convolutional Neural Networks. These attributes are then used to train a Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) to determine whether a video has been manipulated, i.e., whether it is a deepfake or a genuine video. We intend to train our deepfake detection model on a varied set of public datasets in order to improve its real-time performance. We improve the model's adaptability by learning features from different photos. Face-Forensic++, Deepfake Detection Challenge, and Celeb-DF datasets are used to extract videos. Furthermore, to assure competitive performance in real-world scenarios, our model will be assessed against a large amount of real-time data, including the YouTube dataset. Key Words: Temporal modelling, Deepfake technology , Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs)

Robust data-driven design of a jamming detection filter for airborne electromechanical actuators

The electrification of the actuations on aircraft is a technological trend towards a greener aviation. Electromechanical Actuators (EMAs) are a key item in the more electric aircraft concept. However, EMAs are still prone to the jamming of their mechanical transmission, leading to possible incidents when flight surfaces can no longer be controlled. Jamming detection algorithms are thus envisaged. In this paper, we conduct a large experimental campaign on a 1:1 scale airborne EMA and design a robust data-driven jamming detection algorithm. The designed algorithm is compared with a traditional non-robust model-based jamming detection algorithm design. The benefits of robust data-driven approach are experimentally evaluated on real faulty data with several performance indexes.

Computer Vision and Image Processing Approaches for Corrosion Detection

Corrosion is an undesirable phenomenon resulting in material deterioration and degradation through electrochemical or chemical reactions with the surrounding environment. Additionally, corrosion presents considerable threats in both the short and long term because of its ability to create failures, leakages, and damage to materials, equipment, and environment. Despite swift technological developments, it remains difficult to determine the degrees of corrosion due to the different textures and the edgeless boundary of corrosion surfaces. Hence, there is a need to investigate the robust corrosion detection algorithms that are suitable for all degrees of corrosion. Recently, many computer vision and image processing algorithms have been developed for corrosion prediction, assessment, and detection, such as filtering, texture, color, pixelation, image enhancement, wavelet transformation, segmentation, classification, and clustering approaches. As a result, this paper reviews and discusses the state-of-the-art computer vision and image processing methods that have been developed for corrosion detection in various applications, industries, and academic research. The challenges for corrosion detection using computer vision and image processing algorithms are also explored. Finally, recommendations for future research are also detailed.

Oil Palm USB (Unstripped Bunch) Detector Trained on Synthetic Images Generated by PGGAN

Identifying Unstriped Bunches (USB) is a pivotal challenge in palm oil production, contributing to reduced mill efficiency. Existing manual detection methods are proven time-consuming and prone to inaccuracies. Therefore, we propose an innovative solution harnessing computer vision technology. Specifically, we leverage the Faster R-CNN (Region-based Convolution Neural Network), a robust object detection algorithm, and complement it with Progressive Growing Generative Adversarial Networks (PGGAN) for synthetic image generation. Nevertheless, a scarcity of authentic USB images may hinder the application of Faster R-CNN. Herein, PGGAN is assumed to be pivotal in generating synthetic images of Empty Fruit Bunches (EFB) and USB. Our approach pairs synthetic images with authentic ones to train the Faster R-CNN. The VGG16 feature generator serves as the architectural backbone, fostering enhanced learning. According to our experimental results, USB detectors that were trained solely with authentic images resulted in an accuracy of 77.1%, which highlights the potential of this methodology. However, employing solely synthetic images leads to a slightly reduced accuracy of 75.3%. Strikingly, the fusion of authentic and synthetic images in a balanced ratio of 1:1 fuels a remarkable accuracy surge to 87.9%, signifying a 10.1% improvement. This innovative amalgamation underscores the potential of synthetic data augmentation in refining detection systems. By amalgamating authentic and synthetic data, we unlock a novel dimension of accuracy in USB detection, which was previously unattainable. This contribution holds significant implications for the industry, ensuring further exploration into advanced data synthesis techniques and refining detection models.

Robust dual-channel correlation algorithm for complex weak target detection with wideband radar

Robust dual-channel correlation algorithm for complex weak target detection with wideband radar

Formula omitted]CA-GAM-ID: Coupling of probabilistic principal components analysis with generalised additive model to predict the [formula omitted]barriers for intrusion detection

Drastic advancement in computing technology and the dramatic increase in the usage of explainable machine learning algorithms provide a promising platform for developing robust intrusion detection algorithms. However, the development of these algorithms is constrained by their applicability over specific scenarios of Wireless Sensor Networks (WSNs). We introduced a hybrid framework by combining Probabilistic Principal Component Analysis (P2CA) and Generalised Additive Model (GAM), which is performing well for all the scenarios of WSNs. To demonstrate our framework’s broad applicability, we evaluated its performance over three publicly available intrusion detection datasets (i.e., LT-FS-ID, AutoML-ID, and FF-ANN-ID), each from different scenarios. Our findings highlight that the presented framework can accurately predict the number of k−barriers for all three datasets. Furthermore, we conducted a comprehensive performance comparison between our proposed framework and benchmark algorithms, which revealed that our approach outperforms all of them. Additionally, we evaluated the framework’s versatility by testing its performance on datasets unrelated to intrusion detection, specifically ALE datasets. Notably, our approach accurately predicted the response variable in these datasets and exceeded the performance of its primary algorithm, further demonstrating its robustness and adaptability.The implications of this research are substantial. By developing a robust intrusion detection framework that performs well across diverse WSN scenarios, we address a critical need for reliable network security in various domains, including industrial IoT, smart cities, and environmental monitoring. Our findings not only enhance the understanding of intrusion detection in WSNs but also pave the way for developing more sophisticated and adaptable systems to safeguard sensitive data and critical infrastructure.

Long-Range Thermal Target Detection in Data-Limited Settings Using Restricted Receptive Fields.

Long-range target detection in thermal infrared imagery is a challenging research problem due to the low resolution and limited detail captured by thermal sensors. The limited size and variability in thermal image datasets for small target detection is also a major constraint for the development of accurate and robust detection algorithms. To address both the sensor and data constraints, we propose a novel convolutional neural network (CNN) feature extraction architecture designed for small object detection in data-limited settings. More specifically, we focus on long-range ground-based thermal vehicle detection, but also show the effectiveness of the proposed algorithm on drone and satellite aerial imagery. The design of the proposed architecture is inspired by an analysis of popular object detectors as well as custom-designed networks. We find that restricted receptive fields (rather than more globalized features, as is the trend), along with less downsampling of feature maps and attenuated processing of fine-grained features, lead to greatly improved detection rates while mitigating the model's capacity to overfit on small or poorly varied datasets. Our approach achieves state-of-the-art results on the Defense Systems Information Analysis Center (DSIAC) automated target recognition (ATR) and the Tiny Object Detection in Aerial Images (AI-TOD) datasets.

A system-on-chip solution for deep learning-based automatic fetal biometric measurement

Ultrasound assessment of fetal biometry is widely used for gestational age prediction and abnormal fetal growth diagnosis. However, manual biometric measurements require time-consuming procedures and current automated measurement approaches remain challenging in terms of accuracy and computational complexity. This paper proposes deep learning-based efficient automatic fetal biometry measurement method for system-on-chip (SoC) solution. For end-to-end automated measurements, a hardware-friendly bilateral segmentation network (H-BiSeNet) was designed and optimized for multiple fetal objects (i.e., head, abdomen and femur), and fetal biometric parameters were then calculated with a robust multiple keypoint detection algorithm. For hardware implementation with a SoC, a deep learning processing unit (DPU) was employed to accelerate the proposed segmentation network, and biometric measurements with image pre- and postprocessing were conducted on an application processing unit (APU). A total of 6000 fetal ultrasound images in the three regions were collected from 2568 subjects, and the dataset was utilized to train the proposed network. In the performance evaluation, the proposed segmentation network with optimal quantization (H-BiSeNet-Q) outperformed other segmentation networks (i.e., U-Net, U-Net++, Attention U-Net, U-Net3+, DeepLabv3 + and BiSeNetv2) in terms of the average Dice coefficient, and automated measurements with H-BiSeNet-Q were highly correlated with manual measurements (r ≥ 0.983, p < 0.01 for all parameters, i.e., biparietal diameter, head circumference, abdominal circumference and femur length). In the execution time analysis, H-BiSeNet-Q ran at 4.25 frames per second (FPS) with parallelism corresponding to 80% resource utilization in the SoC. These results showed feasibility in low-resource hardware settings such as portable ultrasound systems.

High speed neuromorphic vision-based inspection of countersinks in automated manufacturing processes

Countersink inspection is crucial in various automated assembly lines, especially in the aerospace and automotive sectors. Advancements in machine vision introduced automated robotic inspection of countersinks using laser scanners and monocular cameras. Nevertheless, the aforementioned sensing pipelines require the robot to pause on each hole for inspection due to high latency and measurement uncertainties with motion, leading to prolonged execution times of the inspection task. The neuromorphic vision sensor, on the other hand, has the potential to expedite the countersink inspection process, but the unorthodox output of the neuromorphic technology prohibits utilizing traditional image processing techniques. Therefore, novel event-based perception algorithms need to be introduced. We propose a countersink detection approach on the basis of event-based motion compensation and the mean-shift clustering principle. In addition, our framework presents a robust event-based circle detection algorithm to precisely estimate the depth of the countersink specimens. The proposed approach expedites the inspection process by a factor of 10×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} compared to conventional countersink inspection methods. The work in this paper was validated for over 50 trials on three countersink workpiece variants. The experimental results show that our method provides a standard deviation of 0.025 mm and an accuracy of 0.026 mm for countersink depth inspection despite the low resolution of commercially available neuromorphic cameras. Video Link: https://www.dropbox.com/s/pateqqwh4d605t3/final_video_new.mp4?dl=0.

Segmentation Head Networks with Harnessing Self-Attention and Transformer for Insulator Surface Defect Detection

Current methodologies for insulator defect detection are hindered by limitations in real-world applicability, spatial constraints, high computational demand, and segmentation challenges. Addressing these shortcomings, this paper presents a robust fast detection algorithm combined segmentation head networks with harnessing self-attention and transformer (HST-Net), which is based on the You Only Look Once (YOLO) v5 to recognize and assess the extent and types of damage on the insulator surface. Firstly, the original backbone network is replaced by the transformer cross-stage partial (Transformer-CSP) networks to enrich the network’s ability by capturing information across different depths of network feature maps. Secondly, an insulator defect segmentation head network is presented to handle the segmentation of defect areas such as insulator losses and flashovers. It facilitates instance-level mask prediction for each insulator object, significantly reducing the influence of intricate backgrounds. Finally, comparative experiment results show that the positioning accuracy and defect segmentation accuracy of the proposed both surpass that of other popular models. It can be concluded that the proposed model not only satisfies the requirements for balance between accuracy and speed in power facility inspection, but also provides fresh perspectives for research in other defect detection domains.

Deep learning‐based crop row detection for infield navigation of agri‐robots

AbstractAutonomous navigation in agricultural environments is challenged by varying field conditions that arise in arable fields. State‐of‐the‐art solutions for autonomous navigation in such environments require expensive hardware, such as Real‐Time Kinematic Global Navigation Satellite System. This paper presents a robust crop row detection algorithm that withstands such field variations using inexpensive cameras. Existing data sets for crop row detection do not represent all the possible field variations. A data set of sugar beet images was created representing 11 field variations comprised of multiple grow stages, light levels, varying weed densities, curved crop rows, and discontinuous crop rows. The proposed pipeline segments the crop rows using a deep learning‐based method and employs the predicted segmentation mask for extraction of the central crop using a novel central crop row selection algorithm. The novel crop row detection algorithm was tested for crop row detection performance and the capability of visual servoing along a crop row. The visual servoing‐based navigation was tested on a realistic simulation scenario with the real ground and plant textures. Our algorithm demonstrated robust vision‐based crop row detection in challenging field conditions outperforming the baseline.