Improved YOLOv8 Model for Lightweight Pigeon Egg Detection

Animals, Journal Year: 2024, Volume and Issue: 14(8), P. 1226 - 1226

Published: April 19, 2024

In response to the high breakage rate of pigeon eggs and significant labor costs associated with egg-producing farming, this study proposes an improved YOLOv8-PG (real versus fake egg detection) model based on YOLOv8n. Specifically, Bottleneck in C2f module YOLOv8n backbone network neck are replaced Fasternet-EMA Block Fasternet Block, respectively. The is designed PConv (Partial Convolution) reduce parameter count computational load efficiently. Furthermore, incorporation EMA (Efficient Multi-scale Attention) mechanism helps mitigate interference from complex environments pigeon-egg feature-extraction capabilities. Additionally, Dysample, ultra-lightweight effective upsampler, introduced into further enhance performance lower overhead. Finally, EXPMA (exponential moving average) concept employed optimize SlideLoss propose EMASlideLoss classification loss function, addressing issue imbalanced data samples enhancing model's robustness. experimental results showed that F1-score, mAP50-95, mAP75 increased by 0.76%, 1.56%, 4.45%, respectively, compared baseline model. Moreover, reduced 24.69% 22.89%, Compared detection models such as Faster R-CNN, YOLOv5s, YOLOv7, YOLOv8s, exhibits superior performance. reduction contributes lowering deployment facilitates its implementation mobile robotic platforms.

Language: Английский

---

YO-AFD: an improved YOLOv8-based deep learning approach for rapid and accurate apple flower detection

Frontiers in Plant Science, Journal Year: 2025, Volume and Issue: 16

Published: March 12, 2025

The timely and accurate detection of apple flowers is crucial for assessing the growth status fruit trees, predicting peak blooming dates, early estimating yields. However, challenges such as variable lighting conditions, complex environments, occlusion flowers, clustered significant morphological variations, impede precise detection. To overcome these challenges, an improved YO-AFD method based on YOLOv8 flower was proposed. First, to enable adaptive focus features across different scales, a new attention module, ISAT, which integrated Inverted Residual Mobile Block (IRMB) with Spatial Channel Synergistic Attention (SCSA) module designed. This then incorporated into C2f within network’s neck, forming C2f-IS enhance model’s ability extract critical fuse scales. Additionally, balance between simple challenging targets, regression loss function Focaler Intersection over Union (FIoU) used calculation. Experimental results showed that model accurately detected both including small, occluded, morphologically diverse flowers. achieved F1 score 88.6%, mAP50 94.1%, mAP50-95 55.3%, size 6.5 MB average speed 5.3 ms per image. proposed outperforms five comparative models, demonstrating its effectiveness accuracy in real-time With lightweight design high accuracy, this offers promising solution developing portable systems.

Language: Английский

---

A lightweight weed detection model with global contextual joint features

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 136, P. 108903 - 108903

Published: July 17, 2024

Language: Английский

---

Improved MobileVit deep learning algorithm based on thermal images to identify the water state in cotton

Agricultural Water Management, Journal Year: 2025, Volume and Issue: 310, P. 109365 - 109365

Published: Feb. 12, 2025

Language: Английский

---

Disease detection on exterior surfaces of buildings using deep learning in China

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 12, 2025

Urban infrastructure, particularly in ageing cities, faces significant challenges maintaining building aesthetics and structural integrity. Traditional methods for detecting diseases on exteriors, such as manual inspections, are often inefficient, costly, prone to errors, leading incomplete assessments delayed maintenance actions. This study explores the application of advanced deep learning techniques accurately detect exterior surfaces buildings urban environments, aiming enhance detection efficiency accuracy while providing a real-time monitoring solution that can be widely implemented infrastructure health management. The research model improves feature extraction by integrating DenseNet blocks Swin-Transformer prediction heads, trained validated using dataset 289 high-resolution images collected from diverse environments China. Data augmentation improved model's robustness against varying conditions. proposed achieved high rate 84.42%, recall 77.83%, an F1 score 0.81, with speed 55 frames per second. These metrics demonstrate effectiveness identifying complex damage patterns, minute cracks, even within noisy significantly outperforming traditional methods. highlights potential transform strategies offering practical ultimately enhancing contributing practices timely interventions.

Language: Английский

---

Tracking dustbathing behavior of cage-free laying hens with machine vision technologies

Poultry Science, Journal Year: 2024, Volume and Issue: 103(12), P. 104289 - 104289

Published: Aug. 31, 2024

Dustbathing (DB) is a functionally important maintenance behavior in birds that clean plumage, realigns feather structures, removes lipids, which helps to remove parasites and prevents feathers from becoming too oily. Among different natural behaviors perform cage-free (CF) housing, DB one of the related bird welfare. Earlier studies have identified using manual method such as counting number bouts, duration bouts video recordings. The detection time-consuming, sometimes prone errors, limitations. Therefore, an automated precision monitoring needed detect laying hens early age CF housing environment. objectives this study were (1) develop test deep learning model for detecting find out optimal model; (2) assess performance at growing phases. In study, models, i.e., YOLOv7-DB, YOLOv7x-DB, YOLOv8s-DB YOLOv8x-DB, networks, developed, trained, compared tracking 4 rooms each with 200 (W-36 Hy-Line). Results indicate YOLOv8x-DB outperform all other models on 93.4%, recall 91.20%, mean average ([email protected]) 93.70%. All performed over 90% precision; however, was affected by equipment like drinking lines, perches, feeders. Based (YOLOv8x-DB), highest during grower phase (precision 96.80%, 97.10%, [email protected] 98.60%, [email protected] 79.10% followed prelay, layers, developer, peaking This provides reference poultry egg producers can be detected automatically least 89% or more any hens.

Language: Английский

---

Efficient online detection device and method for cottonseed breakage based on Light-YOLO

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Aug. 9, 2024

High-quality cottonseed is essential for successful cotton production. The integrity of hulls plays a pivotal role in fostering the germination and growth plants. Consequently, it crucial to eliminate broken cottonseeds before planting process. Regrettably, there lack rapid cost-effective methods detecting at this critical stage. To address issue, study developed dual-camera system acquiring front back images multiple cottonseeds. Based on system, we designed hardware, software, control systems required online detection breakage. Moreover, enhance performance breakage detection, improved backbone YOLO head YOLOV8m by incorporating MobileOne-block GhostConv, resulting Light-YOLO. Light-YOLO achieved metrics 93.8% precision, 97.2% recall, 98.9% mAP50, 96.1% accuracy breakage, with compact model size 41.3 MB. In comparison, reported 93.7% 95.0% 99.0% 95.2% accuracy, larger 49.6 further validate device Light-YOLO, conducted an validation experiment, which resulted 86.7% information. results demonstrate that exhibits superior faster speed compared YOLOV8m, confirming feasibility technology proposed study. This provides effective method sorting

Language: Английский

---

On-Line Detection Method of Salted Egg Yolks with Impurities Based on Improved YOLOv7 Combined with DeepSORT

Foods, Journal Year: 2024, Volume and Issue: 13(16), P. 2562 - 2562

Published: Aug. 16, 2024

Salted duck egg yolk, a key ingredient in various specialty foods China, frequently contains broken eggshell fragments embedded the yolk due to high-speed shell-breaking processes, which pose significant food safety risks. This paper presents an online detection method, YOLOv7-SEY-DeepSORT (salted SEY), designed integrate enhanced YOLOv7 with DeepSORT for real-time and accurate identification of salted yolks impurities on production lines. The proposed method utilizes as core network, incorporating multiple Coordinate Attention (CA) modules its Neck section enhance extraction subtle impurities. To address impact imbalanced sample proportions accuracy, Focal-EIoU loss function is employed, adaptively adjusting bounding box values ensure precise localization images. backbone network replaced lightweight MobileOne neural reduce model parameters improve performance. used matching tracking targets across frames, accommodating rotational variations. Experimental results demonstrate that achieves mean average precision (mAP) 0.931, reflecting 0.53% improvement over original YOLOv7. also shows performance, Multiple Object Tracking Accuracy (MOTA) Precision (MOTP) scores 87.9% 73.8%, respectively, representing increases 17.0% 9.8% SORT 2.9% 4.7% Tracktor. Overall, balances high accuracy surpassing other mainstream object methods comprehensive Thus, it provides robust solution rapid defective offers technical foundation reference future research automated safe processing products.

Language: Английский

---

ОБЗОР МЕТОДОВ МАШИННОГО ОБУЧЕНИЯ И КОМПЬЮТЕРНОГО ЗРЕНИЯ В ТЕХНОЛОГИИ ИНКУБАЦИИ ЯИЦ СЕЛЬСКОХОЗЯЙСТВЕННЫХ ПТИЦ

Vestnik APK Verhnevolzh`ia, Journal Year: 2024, Volume and Issue: 4(68), P. 92 - 99

Published: Dec. 24, 2024

Определение состояния зародышей сельскохозяйственных птиц и подбор оптимальных условий инкубации являются важными проблемами птицеводства, применение системы компьютерного зрения (СКЗ) с возможностью использования машинного обучения могут быть оптимальными решениями данных проблем. Цель исследования – провести анализ научных исследований на тему разработки автоматизированных устройств для яиц применением алгоритмов зрения. Выявлены общие направления развития технологии автоматизированной птиц. Отмечена тенденция увеличения доли исследований, в которых компьютерное зрение используется совокупности искусственными нейронными сетями. Determining the state of embryos poultry and selecting optimal incubation conditions are important problems farming, use a computer vision system (CVS) with possibility using machine learning can be solutions to these problems. The purpose research is analyze scientific researches on development automated devices for incubating eggs algorithms. general directions egg technology have been revealed. There tendency increase proportion in which used conjunction artificial neural networks.

Language: Русский

---

Egg characteristics assessment as an enabler for in-ovo sexing technology: A review

Biosystems Engineering, Journal Year: 2024, Volume and Issue: 249, P. 41 - 57

Published: Dec. 2, 2024

Language: Английский

---