scholarly journals Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4803
Author(s):  
Addie Ira Borja Parico ◽  
Tofael Ahamed
Keyword(s):  
Real Time ◽  
False Negative ◽  
Computational Cost ◽  
Suitable Model ◽  
Pear Fruit ◽  
Detection Model ◽  
Art Object ◽  
Detection And Counting ◽  
Accuracy Speed ◽  
The Ideal

This study aimed to produce a robust real-time pear fruit counter for mobile applications using only RGB data, the variants of the state-of-the-art object detection model YOLOv4, and the multiple object-tracking algorithm Deep SORT. This study also provided a systematic and pragmatic methodology for choosing the most suitable model for a desired application in agricultural sciences. In terms of accuracy, YOLOv4-CSP was observed as the optimal model, with an [email protected] of 98%. In terms of speed and computational cost, YOLOv4-tiny was found to be the ideal model, with a speed of more than 50 FPS and FLOPS of 6.8–14.5. If considering the balance in terms of accuracy, speed and computational cost, YOLOv4 was found to be most suitable and had the highest accuracy metrics while satisfying a real time speed of greater than or equal to 24 FPS. Between the two methods of counting with Deep SORT, the unique ID method was found to be more reliable, with an F1count of 87.85%. This was because YOLOv4 had a very low false negative in detecting pear fruits. The ROI line is more reliable because of its more restrictive nature, but due to flickering in detection it was not able to count some pears despite their being detected.

Approach to real time attack detection on the base of simulation and graph oriented modeling

2021 ◽  
Vol 7 ◽  
Author(s):  
V.A. Desnitsky ◽  
Keyword(s):  
Real Time ◽  
Software Tool ◽  
Attack Detection ◽  
Suitable Model ◽  
Distinctive Features ◽  
Detection Process ◽  
Detection Model ◽  
Security Incidents

The article presents an approach to detecting attacks in real time based on simulation and graph-oriented mod- eling. The detection process is performed in a mode close to real-time with the ability to promptly detect known types of security incidents. The distinctive features of the approach include the multidimensional nature of attack detection with the ability to select a specific type of simulation and graph-oriented attack detection model with their subsequent combination. In addition, within the practical part of the work, a software tool has been developed to select the most suitable model apparatus for detecting attacks of each type.

scholarly journals TF-YOLO: An Improved Incremental Network for Real-Time Object Detection

2019 ◽  
Vol 9 (16) ◽  
pp. 3225 ◽  
Author(s):  
He ◽  
Huang ◽  
Wei ◽  
Li ◽  
Guo
Keyword(s):  
Embedded System ◽  
Object Detection ◽  
Real Time ◽  
Visual Detection ◽  
Portable Devices ◽  
Detection Model ◽  
Multi Scale ◽  
Art Object ◽  
Feature Pyramid ◽  
Small Targets

In recent years, significant advances have been gained in visual detection, and an abundance of outstanding models have been proposed. However, state-of-the-art object detection networks have some inefficiencies in detecting small targets. They commonly fail to run on portable devices or embedded systems due to their high complexity. In this workpaper, a real-time object detection model, termed as Tiny Fast You Only Look Once (TF-YOLO), is developed to implement in an embedded system. Firstly, the k-means++ algorithm is applied to cluster the dataset, which contributes to more excellent priori boxes of the targets. Secondly, inspired by the multi-scale prediction idea in the Feature Pyramid Networks (FPN) algorithm, the framework in YOLOv3 is effectively improved and optimized, by three scales to detect the earlier extracted features. In this way, the modified network is sensitive for small targets. Experimental results demonstrate that the proposed TF-YOLO method is a smaller, faster and more efficient network model increasing the performance of end-to-end training and real-time object detection for a variety of devices.

Sky Segmentation for Enhanced Depth Reconstruction and Bokeh Rendering with Efficient Architectures

2020 ◽  
Vol 2020 (14) ◽  
pp. 378-1-378-7
Author(s):  
Tyler Nuanes ◽  
Matt Elsey ◽  
Radek Grzeszczuk ◽  
John Paul Shen
Keyword(s):  
Real Time ◽  
Mobile Device ◽  
Computational Cost ◽  
False Positives ◽  
Compact Model ◽  
High Quality ◽  
False Negatives ◽  
Trade Off ◽  
Depth Reconstruction ◽  
Binary Classifiers

We present a high-quality sky segmentation model for depth refinement and investigate residual architecture performance to inform optimally shrinking the network. We describe a model that runs in near real-time on mobile device, present a new, highquality dataset, and detail a unique weighing to trade off false positives and false negatives in binary classifiers. We show how the optimizations improve bokeh rendering by correcting stereo depth misprediction in sky regions. We detail techniques used to preserve edges, reject false positives, and ensure generalization to the diversity of sky scenes. Finally, we present a compact model and compare performance of four popular residual architectures (ShuffleNet, MobileNetV2, Resnet-101, and Resnet-34-like) at constant computational cost.

Detection of Streptococcus pneumoniae in Sputum Samples by Real- Time PCR.

2020 ◽  
Vol 18 ◽  
Author(s):  
Pegah Shakib ◽  
Mohammad Reza Zolfaghari
Keyword(s):  
Streptococcus Pneumoniae ◽  
Real Time ◽  
Real Time Pcr ◽  
False Negative ◽  
Cross Sectional Study ◽  
Laboratory Culture ◽  
Cross Sectional ◽  
Negative Results ◽  
False Negative Results ◽  
Pcr Method

Background: Conventional laboratory culture-based methods for diagnosis of Streptococcus pneumoniae are time-consuming and yield false negative results. Molecular methods including real-time (RT)-PCR rapid methods and conventional PCR due to higher sensitivity and accuracy have been replaced instead traditional culture assay. The aim of the current study was to evaluate lytA gene for detection of Streptococcus pneumoniae in the cerebrospinal fluid of human patients with meningitis using real-time PCR assay. Material and Methods: In this cross-sectional study, a total of 30 clinical specimens were collected from patients in a period from September to December 2018. In order to evaluate the presence of lytA gene, conventional and real-time PCR methods were used without culture. Results: From 30 sputum samples five (16.66%) isolates were identified as S. pneumoniae by lytA PCR and sequencing. Discussion: In this research, an accurate and rapid real-time PCR method was used, which is based on lytA gene for diagnosis of bacteria so that it can be diagnosed. Based on the sequencing results, the sensitivity for detection of lytA gene was 100% (5/5).

scholarly journals A misleading false-negative result of Pneumocystis real-time PCR assay due to a rare punctual mutation: A French multicenter study

2016 ◽  
Vol 55 (2) ◽  
pp. 180-184 ◽  
Author(s):  
Solène Le Gal ◽  
Florence Robert-Gangneux ◽  
Yann Pépino ◽  
Sorya Belaz ◽  
Céline Damiani ◽  
...  
Keyword(s):  
Real Time ◽  
Multicenter Study ◽  
Real Time Pcr ◽  
False Negative ◽  
False Negative Result ◽  
Pcr Assay

scholarly journals Viral Dynamics and Real-Time RT-PCR Ct Values Correlation with Disease Severity in COVID-19

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1091
Author(s):  
Ali A. Rabaan ◽  
Raghavendra Tirupathi ◽  
Anupam A Sule ◽  
Jehad Aldali ◽  
Abbas Al Mutair ◽  
...  
Keyword(s):  
Viral Load ◽  
Real Time ◽  
Disease Severity ◽  
False Negative ◽  
Influential Factors ◽  
Confirmatory Test ◽  
Acid Extraction ◽  
Rt Pcr ◽  
Viral Kinetics ◽  
Ct Value

Real-time RT-PCR is considered the gold standard confirmatory test for coronavirus disease 2019 (COVID-19). However, many scientists disagree, and it is essential to understand that several factors and variables can cause a false-negative test. In this context, cycle threshold (Ct) values are being utilized to diagnose or predict SARS-CoV-2 infection. This practice has a significant clinical utility as Ct values can be correlated with the viral load. In addition, Ct values have a strong correlation with multiple haematological and biochemical markers. However, it is essential to consider that Ct values might be affected by pre-analytic, analytic, and post-analytical variables such as collection technique, specimen type, sampling time, viral kinetics, transport and storage conditions, nucleic acid extraction, viral RNA load, primer designing, real-time PCR efficiency, and Ct value determination method. Therefore, understanding the interpretation of Ct values and other influential factors could play a crucial role in interpreting viral load and disease severity. In several clinical studies consisting of small or large sample sizes, several discrepancies exist regarding a significant positive correlation between the Ct value and disease severity in COVID-19. In this context, a revised review of the literature has been conducted to fill the knowledge gaps regarding the correlations between Ct values and severity/fatality rates of patients with COVID-19. Various databases such as PubMed, Science Direct, Medline, Scopus, and Google Scholar were searched up to April 2021 by using keywords including “RT-PCR or viral load”, “SARS-CoV-2 and RT-PCR”, “Ct value and viral load”, “Ct value or COVID-19”. Research articles were extracted and selected independently by the authors and included in the present review based on their relevance to the study. The current narrative review explores the correlation of Ct values with mortality, disease progression, severity, and infectivity. We also discuss the factors that can affect these values, such as collection technique, type of swab, sampling method, etc.

scholarly journals Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4237
Author(s):  
Hoon Ko ◽  
Kwangcheol Rim ◽  
Isabel Praça
Keyword(s):  
Anomaly Detection ◽  
Real Time ◽  
Feature Detection ◽  
Trading System ◽  
Judgment Accuracy ◽  
Energy Trading ◽  
Real Time Processing ◽  
Detection Model ◽  
Time Required ◽  
The Relationship

The biggest problem with conventional anomaly signal detection using features was that it was difficult to use it in real time and it requires processing of network signals. Furthermore, analyzing network signals in real-time required vast amounts of processing for each signal, as each protocol contained various pieces of information. This paper suggests anomaly detection by analyzing the relationship among each feature to the anomaly detection model. The model analyzes the anomaly of network signals based on anomaly feature detection. The selected feature for anomaly detection does not require constant network signal updates and real-time processing of these signals. When the selected features are found in the received signal, the signal is registered as a potential anomaly signal and is then steadily monitored until it is determined as either an anomaly or normal signal. In terms of the results, it determined the anomaly with 99.7% (0.997) accuracy in f(4)(S0) and in case f(4)(REJ) received 11,233 signals with a normal or 171anomaly judgment accuracy of 98.7% (0.987).

scholarly journals Pooling of Upper Respiratory Specimens Using a SARS-CoV-2 Real-time RT-PCR Assay Authorized for Emergency Use in Low-Prevalence Populations for High-Throughput Testing

2020 ◽  
Vol 7 (11) ◽  
Author(s):  
Gwynngelle A Borillo ◽  
Ron M Kagan ◽  
Russell E Baumann ◽  
Boris M Fainstein ◽  
Lamela Umaru ◽  
...  
Keyword(s):  
Real Time ◽  
False Negative ◽  
False Negative Rate ◽  
Nucleic Acid Amplification ◽  
Rt Pcr ◽  
Pooled Testing ◽  
Negative Results ◽  
Single Positive ◽  
Upper Respiratory ◽  
Respiratory Specimens

Abstract Background Nucleic acid amplification testing is a critical tool for addressing the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic. Specimen pooling can increase throughput and conserve testing resources but requires validation to ensure that reduced sensitivity does not increase the false-negative rate. We evaluated the performance of a real-time reverse transcription polymerase chain reaction (RT-PCR) test authorized by the US Food and Drug Administration (FDA) for emergency use for pooled testing of upper respiratory specimens. Methods Positive specimens were selected from 3 prevalence groups, 1%–3%, >3%–6%, and >6%–10%. Positive percent agreement (PPA) was assessed by pooling single-positive specimens with 3 negative specimens; performance was assessed using Passing-Bablok regression. Additionally, we assessed the distributions of RT-PCR cycle threshold (Ct) values for 3091 positive specimens. Results PPA was 100% for the 101 pooled specimens. There was a linear relationship between Ct values for pooled and single-tested specimens (r = 0.96–0.99; slope ≈ 1). The mean pooled Ct shifts at 40 cycles were 2.38 and 1.90, respectively, for the N1 and N3 targets. The median Cts for 3091 positive specimens were 25.9 (N1) and 24.7 (N3). The percentage of positive specimens with Cts between 40 and the shifted Ct was 1.42% (N1) and 0.0% (N3). Conclusions Pooled and individual testing of specimens positive for SARS-CoV-2 demonstrated 100% agreement, which demonstrates the viability of pooled specimens for SARS-COV-2 testing using a dual-target RT-PCR system. Pooled specimen testing can help increase testing capacity for SARS-CoV-2 with a low risk of false-negative results.

scholarly journals Real-Time Path Planning Based on Harmonic Functions under a Proper Generalized Decomposition-Based Framework

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 3943
Author(s):  
Nicolas Montés ◽  
Francisco Chinesta ◽  
Marta C. Mora ◽  
Antonio Falcó ◽  
Lucia Hilario ◽  
...  
Keyword(s):  
Path Planning ◽  
Real Time ◽  
Harmonic Functions ◽  
Autonomous Navigation ◽  
Numerical Technique ◽  
Computational Cost ◽  
Main Idea ◽  
Main Property ◽  
Proper Generalized Decomposition ◽  
Computational Vademecum

This paper presents a real-time global path planning method for mobile robots using harmonic functions, such as the Poisson equation, based on the Proper Generalized Decomposition (PGD) of these functions. The main property of the proposed technique is that the computational cost is negligible in real-time, even if the robot is disturbed or the goal is changed. The main idea of the method is the off-line generation, for a given environment, of the whole set of paths from any start and goal configurations of a mobile robot, namely the computational vademecum, derived from a harmonic potential field in order to use it on-line for decision-making purposes. Up until now, the resolution of the Laplace or Poisson equations has been based on traditional numerical techniques unfeasible for real-time calculation. This drawback has prevented the extensive use of harmonic functions in autonomous navigation, despite their powerful properties. The numerical technique that reverses this situation is the Proper Generalized Decomposition. To demonstrate and validate the properties of the PGD-vademecum in a potential-guided path planning framework, both real and simulated implementations have been developed. Simulated scenarios, such as an L-Shaped corridor and a benchmark bug trap, are used, and a real navigation of a LEGO®MINDSTORMS robot running in static environments with variable start and goal configurations is shown. This device has been selected due to its computational and memory-restricted capabilities, and it is a good example of how its properties could help the development of social robots.

Sign in / Sign up

Export Citation Format

Share Document