Small Target Vehicle Detection Algorithm Based on Improved YOLOv5s DOI

Xincheng Sun,

Huifang Kong,

Yibo Meng

и другие.

2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI), Год журнала: 2024, Номер unknown, С. 1 - 6

Опубликована: Окт. 25, 2024

Язык: Английский

Research trends in livestock facial identification – A review DOI Creative Commons
Mingue Kang,

Sang-Hyon Oh

Journal of Animal Science and Technology, Год журнала: 2025, Номер 67(1), С. 43 - 55

Опубликована: Янв. 1, 2025

This review examines the application of video processing and convolutional neural network (CNN)-based deep learning for animal face recognition, identification, re-identification. These technologies are essential precision livestock farming, addressing challenges in production efficiency, welfare, environmental impact. With advancements computer technology, monitoring systems have evolved into sensor-based contact methods video-based non-contact methods. Recent developments enable continuous analysis accumulated data, automating conditions. By integrating with CNN-based learning, it is possible to estimate growth, identify individuals, monitor behavior more effectively. enhance management systems, leading improved outcomes, sustainability farming practices.

Язык: Английский

Процитировано

1

A reliable unmanned aerial vehicle multi-target tracking system with global motion compensation for monitoring Procapra przewalskii DOI Creative Commons
Guoqing Zhang, Yongxiang Zhao, Ping Fu

и другие.

Ecological Informatics, Год журнала: 2024, Номер 81, С. 102556 - 102556

Опубликована: Март 20, 2024

Procapra przewalskii, which inhabits plateau areas, faces the constant threat of poaching and unpredictable risks that impede its survival. The implementation a comprehensive, real-time monitoring tracking system for przewalskii using artificial intelligence unmanned aerial vehicle (UAV) technology is crucial to safeguard existence. Therefore, UAV multi-object-tracking (MOT) with global motion compensation (GMC) was proposed in this study. YOLOv7 Deep SORT were employed object detection tracking, respectively. Furthermore, Kalman filter (KF) optimized enhance accuracy object-tracking. Moreover, novel appearance feature-extraction network (FEN) introduced enable more effective multi-scale feature (MSF) extraction. In addition, GMC module align neighboring frames through matching. This facilitates correction position target subsequent frame, mitigating impact camera on tracking. results demonstrated remarkable system. Compared model, exhibited an increase 6.4% MOTA, 2.7% MOTP, 7.9% IDF1. Through comprehensive evaluation analysis real-world scenarios, study exhibits reliability complex scenes holds potential significantly protection from threats.

Язык: Английский

Процитировано

7

A video object segmentation-based fish individual recognition method for underwater complex environments DOI Creative Commons
Tao Zheng, Junfeng Wu,

Han Kong

и другие.

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102689 - 102689

Опубликована: Июнь 15, 2024

Currently, aquaculture methods tend to combine scale and intelligence, which saves manpower improves the survival rate of seafood at same time. High-precision high-efficiency fish individual recognition can provide key technical support for disease detection, feeding habits, body condition, etc. In realm intelligent aquaculture, it provides robust data precision farming. However, current research struggle maintain network model's focus on in real marine underwater complex environments (e.g., environmental background interference such as coral reefs, overlap between bodies, light noise, etc.), leading unsatisfactory results. To this end, paper proposes a method based video object segmentation, consists three parts, including segmentation detection module, an all-in-one visualization module. The work adopts combination deep learning algorithms solve problem low attention poor accuracy individuals environments, effectively efficiency recognition, analyzes discusses comparison effects using different weights. results simulation experiments show that metric Rank1 value achieves more than 96% public datasets DlouFish, WideFish, Fish-seg dataset produced paper, over state-of-the-art by 2.23%, 1.33%, 1.25%, respectively.

Язык: Английский

Процитировано

6

Camouflage detection: Optimization-based computer vision for Alligator sinensis with low detectability in complex wild environments DOI Creative Commons
Yantong Liu,

Sai Che,

Liwei Ai

и другие.

Ecological Informatics, Год журнала: 2024, Номер 83, С. 102802 - 102802

Опубликована: Авг. 28, 2024

Alligator sinensis is an extremely rare species that possesses excellent camouflage, allowing it to fit perfectly into its natural environment. The use of camouflage makes detection difficult for both humans and automated systems, highlighting the importance modern technologies animal monitoring. To address this issue, we present YOLO v8-SIM, innovative technique specifically developed significantly enhance identification precision. v8-SIM utilizes a sophisticated dual-layer attention mechanism, optimized loss function called inner intersection-over-union (IoU), slim-neck cross-layer hopping. results our study demonstrate model achieves accuracy rate 91 %, recall 89.9 mean average precision (mAP) 92.3 % IoU threshold 0.5. In addition, operates at frame 72.21 frames per second (FPS) excels accurately recognizing objects are partially visible or smaller in size. further improve initiatives, suggest creating open-source collection data showcases A. native environment while using techniques. These developments collectively ability detect disguised animals, thereby promoting monitoring protection biodiversity, supporting ecosystem sustainability.

Язык: Английский

Процитировано

4

Efficient wildlife monitoring: Deep learning-based detection and counting of green turtles in coastal areas DOI Creative Commons

Naoya Noguchi,

Hideaki Nishizawa,

Taro Shimizu

и другие.

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103009 - 103009

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring DOI Creative Commons
Rui Zhu, Enting Zhao, Chunhe Hu

и другие.

Ecological Informatics, Год журнала: 2025, Номер 87, С. 103091 - 103091

Опубликована: Март 5, 2025

Язык: Английский

Процитировано

0

GD-YOLO: A lightweight model for household waste image detection DOI
S. Sun, Shuai Zheng, Xiangyang Xu

и другие.

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127525 - 127525

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

Using machine learning to count Antarctic shag (Leucocarbo bransfieldensis) nests on images captured by remotely piloted aircraft systems DOI Creative Commons

Andrew Cusick,

Katarzyna Fudala,

Piotr Pasza Storożenko

и другие.

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102707 - 102707

Опубликована: Июнь 29, 2024

Using 51 orthomosaics of 11 breeding locations the Antarctic shag (Leucocarbo bransfieldensis), we propose a method for automating counting nests. This is achieved by training an object detection model based on "You Only Look Once" (YOLO) architecture and identifying nests sections orthomosaic, which are later combined with predictions entire orthomosaic. Our results show that current use Remotely Piloted Aircraft Systems (RPAS) to collect images areas colonies, machine learning algorithms, can provide reliable fast estimates nest counts (F1 score > 0.95). By using data from only two colonies training, models be obtained generalise well both spatially temporally distinct colonies. The proposed practical application opens possibility aerial imagery perform large-scale surveys islands in search undiscovered We discuss conditions optimal performance as its limitations. code, trained allowing full reproducibility available at https://github.com/Appsilon/Antarctic-nests.

Язык: Английский

Процитировано

3

Lightweight and accurate aphid detection model based on an improved deep-learning network DOI Creative Commons
Wen‐Hua Sun, Yane Li, Hailin Feng

и другие.

Ecological Informatics, Год журнала: 2024, Номер 83, С. 102794 - 102794

Опубликована: Авг. 24, 2024

Язык: Английский

Процитировано

1

Conservation in action: Cost-effective UAVs and real-time detection of the globally threatened swamp deer (Rucervus duvaucelii) DOI Creative Commons
Ravindra Nath Tripathi,

Karan Agarwal,

Vikas Tripathi

и другие.

Ecological Informatics, Год журнала: 2024, Номер unknown, С. 102913 - 102913

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

1