Experimental Study of High Frequency Passive Bistatic Radar Energy Exposure Range Estimation Based on Watershed Algorithm DOI

Zheyu Tang,

Longquan Yang,

Xiao Han

et al.

Published: Dec. 15, 2023

The High Frequency Passive Bistatic Radar (HFPBR) is a typical two-base radar system in which the receiving station, transmitting station and detection area are located at long distances from each other. Since this does not emit signals itself, it necessary to obtain information about range of active source irradiation. In paper, received ground-sea clutter data analyzed representation energy distance-azimuth two-dimensional spectrogram. Then, watershed algorithm mathematical morphology used smooth binarize matrix, so as correct estimate irradiation coverage exogenous energy. experimental results highly consistent with measured data, verifying validity accuracy proposed methodology.

Language: Английский

Rapid identification of Astragalus membranaceus processing with rice water based on intelligent color recognition and multi-source information fusion technology DOI Open Access
Dongmei Guo,

Yijing Pan,

Shunshun Wang

et al.

Chinese Herbal Medicines, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

6
Feature engineering to identify plant diseases using image processing and artificial intelligence: A comprehensive review DOI Creative Commons
Seyed Mohamad Javidan, Ahmad Banakar, K Rahnama

et al.

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: 8, P. 100480 - 100480

Published: May 28, 2024

Plant diseases can significantly reduce crop yield and product quality. Visual inspections of plants by human observers for disease identification are time-consuming, costly, prone to error. Advances in artificial intelligence (AI) have created opportunities the rapid diagnosis non-destructive classification plant pathogens. Several machine vision techniques been developed identify classify automatically based on morphology specific symptoms. The use deep learning models has achieved acceptable results, but they require large datasets training, which be labor-intensive, computationally costly This problem solved, a point, using data augmentation generative AI order increase size datasets. Furthermore, combination feature extraction was used accurate detection classification. In some cases, traditional base classifiers trained with small including basic shape, color, texture features feasible efficient diseases. performance such depends primarily extracted from images; therefore, plays vital role identifying Feature engineering, process most relevant variables raw develop an predictive model, is explored this paper.

Language: Английский

Citations

14
An image segmentation of adhesive droplets based approach to assess the quality of pesticide spray DOI Creative Commons

Fengxin Yan,

Yu Zhang,

Yaoyao Zhu

et al.

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: 8, P. 100460 - 100460

Published: April 18, 2024

Pesticide spray is a widely used chemical control method to minimize biological disasters in the agriculture industry. It important evaluate efficacy and quality of pesticide sprayer, however, it cannot be conveniently achieved due lack accessibility sprayed droplets intensity associated work. This paper proposes novel method, based on an image processing-based approach, assess quality. The proposed uses combination algorithms criteria functions; such as, maximum between-cluster variance algorithm, area threshold criteria, roundness factor, mathematical morphology operations, optimized watershed segment dark blue adhesive droplet images water-sensitive paper, placed crop field. In this work, three kinds evaluation experiments are considered: (i) manual analysis via counting processing, (ii) automatic by commercially available analyzer Shenzhen DJI Co. Ltd., (iii) processing introduced paper. experimental results show better consistency between method. former, provides convenient rapid way comes with assessment algorithm along embedded device that hardware view

Language: Английский

Citations

3
Automated medication verification system (AMVS): System based on edge detection and CNN classification drug on embedded systems DOI Creative Commons
Yen‐Jung Chiu

Heliyon, Journal Year: 2024, Volume and Issue: 10(9), P. e30486 - e30486

Published: May 1, 2024

A novel automated medication verification system (AMVS) aims to address the limitation of manual among healthcare professionals with a high workload, thereby reducing errors in hospitals. Specifically, process is time-consuming and prone errors, especially settings workloads. The proposed strategy streamline automate this process, enhancing efficiency errors. employs deep learning models swiftly accurately classify multiple medications within single image without requiring labeling during model construction. It comprises edge detection classification verify types. Unlike previous studies conducted open spaces, our study takes place closed space minimize impact optical changes on capture. During experimental individually identifies each drug by method utilizes determine type. Our research has successfully developed fully recognition system, achieving an accuracy over 95 % identifying types conducting segmentation analyses. demonstrates rate approximately 96 for sets containing fewer than ten 93 those This builds quickly. holds promising potential assisting nursing staff AMVS, likelihood alleviating burden staff.

Language: Английский

Citations

2
An artificial intelligence-based and integrated procedure to reconstruct meshes for tomograms of 3D braided composites DOI
Xiaodong Liu, Chen Liu, Jingran Ge

et al.

Composites Science and Technology, Journal Year: 2024, Volume and Issue: 255, P. 110737 - 110737

Published: Aug. 1, 2024

Language: Английский

Citations

1
Optimizing Deep Learning Algorithms for Effective Chicken Tracking through Image Processing DOI Creative Commons
Saman Abdanan Mehdizadeh, Allan Lincoln Rodrigues Siriani, Danilo Florentino Pereira

et al.

AgriEngineering, Journal Year: 2024, Volume and Issue: 6(3), P. 2749 - 2767

Published: Aug. 8, 2024

Identifying bird numbers in hostile environments, such as poultry facilities, presents significant challenges. The complexity of these environments demands robust and adaptive algorithmic approaches for the accurate detection tracking birds over time, ensuring reliable data analysis. This study aims to enhance methodologies automated chicken identification videos, addressing dynamic non-standardized nature farming environments. YOLOv8n model was chosen due its high portability. developed algorithm promptly identifies labels chickens they appear image. process is illustrated two parallel flowcharts, emphasizing different aspects image processing behavioral False regions chickens’ heads tails are excluded calculate body area more accurately. following three scenarios were tested with newly modified deep-learning algorithm: (1) reappearing temporary invisibility; (2) multiple missing object occlusion; (3) coalescing chickens. results a precise measure size shape, YOLO achieving an accuracy above 0.98 loss less than 0.1. In all scenarios, improved maintaining identification, enabling simultaneous several respective error rates 0, 0.007, 0.017. Morphological based on features extracted from each chicken, proved be effective strategy enhancing accuracy.

Language: Английский

Citations

1
Green fruit detection methods: Innovative application of camouflage object detection and multilevel feature mining DOI
Yuting Zhai, Zongmei Gao, Yang Zhou

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 225, P. 109356 - 109356

Published: Aug. 20, 2024

Language: Английский

Citations

1
Clustering and Segmentation of Adhesive Pests in Apple Orchards Based on GMM-DC DOI Creative Commons
Yunfei Wang,

Shuangxi Liu,

Zhuo Ren

et al.

Agronomy, Journal Year: 2023, Volume and Issue: 13(11), P. 2806 - 2806

Published: Nov. 13, 2023

The segmentation of individual pests is a prerequisite for pest feature extraction and identification. To address the issue adhesion in apple orchard identification process, this research proposed image method based on Gaussian Mixture Model with Density Curvature Weighting (GMM-DC). First, HSV color space, an was desaturated by adjusting hue inverting to mitigate threshold crossing points. Subsequently, contour selection methods were used separate background. Next, shape factor introduced determine regions quantities adhering pests, thereby determining number model clustering clusters. Then, point cloud reconstruction performed spatial distribution features pests. construct GMM-DC model, density (SD) curvature (SC) information function designed embedded GMM. Finally, experimental analysis conducted collected images. results showed that achieved average accurate rate 95.75%, over-segmentation 2.83%, under-segmentation 1.42%. These significantly outperformed traditional methods. In addition, original improved Mask R-CNN models as recognition models, mean Average Precision evaluation metric. Recognition experiments images without method. show segmented 92.43% 96.75%. This indicates improvement 13.01% 12.18% accuracy, respectively. demonstrate provides theoretical methodological foundation orchards.

Language: Английский

Citations

3
Image Analysis Artificial Intelligence Technologies for Plant Phenotyping: Current State of the Art DOI Creative Commons
Chrysanthos Maraveas

AgriEngineering, Journal Year: 2024, Volume and Issue: 6(3), P. 3375 - 3407

Published: Sept. 17, 2024

Modern agriculture is characterized by the use of smart technology and precision to monitor crops in real time. The technologies enhance total yields identifying requirements based on environmental conditions. Plant phenotyping used solving problems basic science allows scientists characterize select best genotypes for breeding, hence eliminating manual laborious methods. Additionally, plant useful such as subtle differences or complex quantitative trait locus (QTL) mapping which are impossible solve using conventional This review article examines latest developments image analysis AI, 2D, 3D reconstruction techniques limiting literature from 2020. collects data 84 current studies showcases novel applications various technologies. AI algorithms showcased predicting issues expected during growth cycles lettuce plants, soybeans different climates conditions, high-yielding improve yields. high throughput also facilitates monitoring crop canopies genotypes, root phenotyping, late-time harvesting weeds. methods combined with guide applications, leading higher accuracy than cases that consider either method. Finally, a combination undertake operations involving automated robotic harvesting. Future research directions where uptake smartphone-based time series ML recommended.

Language: Английский

Citations

0
Superpixel Segmentation Based on Feature Fusion and Boundary Constraint for Ferrograph Image Segmentation DOI
H. Li, Jiasheng Song, Leyang Dai

et al.

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2023, Volume and Issue: 72, P. 1 - 11

Published: Jan. 1, 2023

Accurate segmentation of wear particles in ferrograph image is pivotal for ferrography analysis. Although morphological processing techniques have made noteworthy strides particle segmentation, issues such as oversegmentation and boundary distortion remain evident. These challenges compromise the efficiency prevailing techniques, especially separating irregular delineating contours. In this study, we introduce an advanced superpixel technique based on feature fusion constraint (FBS). Key characteristics FBS include: 1) The development innovative framework to cater varied contents images. 2) implementation a strategy refine boundaries, ensuring alignment with Experimental results indicate that proposed method can adeptly segment particles, its performance matching or even surpassing state-of-the-art techniques. Furthermore, achieves accuracy 97.8% dataset.

Language: Английский

Citations

1