YOLO-Based UAV Technology: A Review of the Research and Its Applications

Drones, Journal Year: 2023, Volume and Issue: 7(3), P. 190 - 190

Published: March 10, 2023

In recent decades, scientific and technological developments have continued to increase in speed, with researchers focusing not only on the innovation of single technologies but also cross-fertilization multidisciplinary technologies. Unmanned aerial vehicle (UAV) technology has seen great progress many aspects, such as geometric structure, flight characteristics, navigation control. The You Only Look Once (YOLO) algorithm was developed been refined over years provide satisfactory performance for real-time detection classification multiple targets. context cross-fusion becoming a new focus, proposed YOLO-based UAV (YBUT) by integrating above two This integration succeeds strengthening application emerging expanding idea development YOLO algorithms drone technology. Therefore, this paper presents history YBUT reviews practical applications engineering, transportation, agriculture, automation, other fields. aim is help users quickly understand researchers, consumers, stakeholders research future discussed explore areas.

Language: Английский

---

Individual Tree-Crown Detection and Species Identification in Heterogeneous Forests Using Aerial RGB Imagery and Deep Learning

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(5), P. 1463 - 1463

Published: March 6, 2023

Automatic identification and mapping of tree species is an essential task in forestry conservation. However, applications that can geolocate individual trees identify their heterogeneous forests on a large scale are lacking. Here, we assessed the potential Convolutional Neural Network algorithm, Faster R-CNN, which efficient end-to-end object detection approach, combined with open-source aerial RGB imagery for geolocation upper canopy layer temperate forests. We studied four species, i.e., Norway spruce (Picea abies (L.) H. Karst.), silver fir (Abies alba Mill.), Scots pine (Pinus sylvestris L.), European beech (Fagus sylvatica growing To fully explore approach identification, trained single-species multi-species models. For models, average accuracy (F1 score) was 0.76. Picea detected highest accuracy, F1 0.86, followed by A. = 0.84), F. 0.75), Pinus 0.59). Detection increased models 0.92), while it remained same or decreased slightly other species. Model performance more influenced site conditions, such as forest stand structure, less illumination. Moreover, misidentification number included increased. In conclusion, presented method accurately map location may serve basis future inventories targeted management actions to support resilient

Language: Английский

---

Individual Tree Species Identification for Complex Coniferous and Broad-Leaved Mixed Forests Based on Deep Learning Combined with UAV LiDAR Data and RGB Images

Forests, Journal Year: 2024, Volume and Issue: 15(2), P. 293 - 293

Published: Feb. 3, 2024

Automatic and accurate individual tree species identification is essential for the realization of smart forestry. Although existing studies have used unmanned aerial vehicle (UAV) remote sensing data identification, effects different spatial resolutions combining multi-source automatic using deep learning methods still require further exploration, especially in complex forest conditions. Therefore, this study proposed an improved YOLOv8 model multisource under stand Firstly, RGB LiDAR natural coniferous broad-leaved mixed forests conditions Northeast China were acquired via a UAV. Then, resolutions, scales, band combinations explored, based on identification. Subsequently, Attention Multi-level Fusion (AMF) Gather-and-Distribute (GD) was proposed, according to characteristics data, which two branches AMF Net backbone able extract fuse features from sources separately. Meanwhile, GD mechanism introduced into neck model, order fully utilize extracted main trunk complete eight area. The results showed that YOLOv8x images combined with current mainstream object detection algorithms achieved highest mAP 75.3%. When resolution within 8 cm, accuracy exhibited only slight variation. However, decreased significantly decrease when greater than 15 cm. scales x, l, m could exhibit higher compared other scales. DGB PCA-D superior 75.5% 76.2%, respectively. had more significant improvement single 81.0%. clarified impact demonstrated excellent performance provides new solution technical reference forestry resource investigation data.

Language: Английский

---

Identification of standing dead trees in Robinia pseudoacacia plantations across China’s Loess Plateau using multiple deep learning models

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 136, P. 104388 - 104388

Published: Feb. 1, 2025

Language: Английский

---

Instance segmentation of individual tree crowns with YOLOv5: A comparison of approaches using the ForInstance benchmark LiDAR dataset

ISPRS Open Journal of Photogrammetry and Remote Sensing, Journal Year: 2023, Volume and Issue: 9, P. 100045 - 100045

Published: Aug. 1, 2023

Fine-grained information on the level of individual trees constitute key components for forest observation enabling management practices tackling effects climate change and loss biodiversity in ecosystems. Such tree crowns (ITC's) can be derived from application ITC segmentation approaches, which utilize remotely sensed data. However, many approaches require prior knowledge about characteristics, is difficult to obtain parameterization. This avoided by adoption data-driven, automated workflows based convolutional neural networks (CNN). To contribute advancements efficient we present a novel approach YOLOv5 CNN. We analyzed performance this comprehensive international unmanned aerial laser scanning (UAV-LS) dataset (ForInstance), covers wide range types. The ForInstance consists 4192 individually annotated high-density point clouds with densities ranging 498 9529 points m-2 collected across 80 sites. original was split into 70% training validation 30% model assessment (test data). For best performing model, observed F1-score 0.74 detection rate (DET %) 64% test outperformed an approach, requires 41% 33% DET %, respectively. Furthermore, tested reduced (498, 50 10 per m-2) performance. YOLO exhibited promising F1-scores 0.69 0.62 even at m-2, respectively, were between 27% 34% better than that knowledge. areas segments resulting close reference (RMSE = 3.19 m-2), suggesting YOLO-derived used derive level.

Language: Английский

---

A self-adaptive wildfire detection algorithm by fusing physical and deep learning schemes

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 127, P. 103671 - 103671

Published: Jan. 27, 2024

Currently, the spectra-based physical models and deep learning methods are frequently used to detect wildfires from remote sensing data. However, algorithms mainly rely on radiative transfer processes, which limit their effectiveness in detecting small weak fires. On other hand, usually lack mechanism constraints, thus generally resulting false alarms of bright surfaces. It is promising combine advantages them correspondingly reduce inherent error a single algorithm. To this end, paper, both local contextual global index method based mechanisms optimized, simultaneously, new U-Net model also establish accurately Moreover, YOLO v5 incorporated for first time extract remove objects with high exposure. Based above series novel works, self-adaptive fusing algorithm finally proposed. Our results reveal that: (1) Short-wave infrared band about 2.15 μm crucial fire detection data moderate-to-high resolutions. Taking Landsat 8 as an example, combinations 7, 6, 2(SWIR + VI), 5(SWIR NIR), 5, 3(SWIR VI NIR) show reasonable accuracy, recall rate greater than 81 %. The thermal can be assist general location serve alternative choice extreme cases. (2) optimized predict more accurate positions. (3) very effective introduce framework exposure urban suburban regions. (4) proposed fusion integrates various schemes, proving its better performance terms robustness, stability generality compared any method. Even situations such Gobi Desert, thin cloud edges, mountain shadow areas, still works well. tests Sentinel-2A, WorldView-3, SPOT-4 potential applicability newly algorithm, especially fine spatial spectral

Language: Английский

---

UAV-Based Computer Vision System for Orchard Apple Tree Detection and Health Assessment

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(14), P. 3558 - 3558

Published: July 15, 2023

Accurate and efficient orchard tree inventories are essential for acquiring up-to-date information, which is necessary effective treatments crop insurance purposes. Surveying trees, including tasks such as counting, locating, assessing health status, plays a vital role in predicting production volumes facilitating management. However, traditional manual known to be labor-intensive, expensive, prone errors. Motivated by recent advancements UAV imagery computer vision methods, we propose UAV-based framework individual detection assessment. Our proposed approach follows two-stage process. Firstly, model employing hard negative mining strategy using RGB images. Subsequently, address the classification problem leveraging multi-band imagery-derived vegetation indices. The achieves an F1-score of 86.24% overall accuracy 97.52% study demonstrates robustness accurately from Moreover, holds potential application various other plantation settings, enabling plant assessment imagery.

Language: Английский

---

Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(2), P. 335 - 335

Published: Jan. 14, 2024

Achieving the accurate and efficient monitoring of forests at tree level can provide detailed information for precise scientific forest management. However, detection individual trees under planted characterized by dense distribution, serious overlap, complicated background is still a challenge. A new deep learning network, YOLO-DCAM, has been developed to effectively promote amidst complex scenes. The YOLO-DCAM constructed leveraging YOLOv5 network as basis further enhancing network’s capability extracting features reasonably incorporating deformable convolutional layers into backbone. Additionally, an multi-scale attention module integrated neck enable prioritize crown reduce interference information. combination these two modules greatly enhance performance. achieved impressive performance Chinese fir instances within comprehensive dataset comprising 978 images across four typical scenes, with model evaluation metrics precision (96.1%), recall (93.0%), F1-score (94.5%), [email protected] (97.3%), respectively. comparative test showed that good balance between accuracy efficiency compared advanced models. Specifically, increased 2.6%, 1.6%, 2.1%, 1.4% YOLOv5. Across three supplementary plots, consistently demonstrates strong robustness. These results illustrate effectiveness detecting in plantation environments. This study serve reference utilizing UAV-based RGB imagery precisely detect trees, offering valuable implications practical applications.

Language: Английский

---

Automatic detection of urban flood level with YOLOv8 using flooded vehicle dataset

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 639, P. 131625 - 131625

Published: July 2, 2024

Language: Английский

---

Deep Learning for Detecting Verticillium Fungus in Olive Trees: Using YOLO in UAV Imagery

Algorithms, Journal Year: 2023, Volume and Issue: 16(7), P. 343 - 343

Published: July 17, 2023

The verticillium fungus has become a widespread threat to olive fields around the world in recent years. accurate and early detection of disease at scale could support solving problem. In this paper, we use YOLO version 5 model detect trees using aerial RGB imagery captured by unmanned vehicles. aim our paper is compare different architectures evaluate their performance on task. are evaluated two input sizes each through most widely used metrics for object classification tasks (precision, recall, [email protected] [email protected]:0.95). Our results show that YOLOv5 algorithm able deliver good detecting predicting status, with having strengths weaknesses.

Language: Английский

---