Segmentation and Phenotype Calculation of Rapeseed Pods Based on YOLO v8 and Mask R-Convolution Neural Networks

Plants, Год журнала: 2023, Номер 12(18), С. 3328 - 3328

Опубликована: Сен. 20, 2023

Rapeseed is a significant oil crop, and the size length of its pods affect productivity. However, manually counting number rapeseed measuring length, width, area pod takes time effort, especially when there are hundreds resources to be assessed. This work created two state-of-the-art deep learning-based methods identify related attributes, which then implemented in pots improve accuracy yield estimate. One these YOLO v8, other two-stage model Mask R-CNN based on framework Detectron2. The v8n with Resnet101 backbone Detectron2 both achieve precision rates exceeding 90%. recognition results demonstrated that models perform well graphic images segmented. In light this, we developed coin-based approach for estimating tested it test dataset made up nine different species Brassica napus one campestris L. correlation coefficients between manual measurement machine vision width were calculated using statistical methods. regression coefficient was 0.991, 0.989. conclusion, first time, utilized learning techniques characteristics while concurrently establishing pods. Our suggested approaches successful segmenting precisely. offers breeders an effective strategy digitally analyzing phenotypes automating identification screening process, not only germplasm but also leguminous plants, like soybeans possess

Язык: Английский

---

EMA-YOLO: A Novel Target-Detection Algorithm for Immature Yellow Peach Based on YOLOv8

Sensors, Год журнала: 2024, Номер 24(12), С. 3783 - 3783

Опубликована: Июнь 11, 2024

Accurate determination of the number and location immature small yellow peaches is crucial for bagging, thinning, estimating yield in modern orchards. However, traditional methods have faced challenges accurately distinguishing due to their resemblance leaves susceptibility variations shooting angles distance. To address these issues, we proposed an improved target-detection model (EMA-YOLO) based on YOLOv8. Firstly, sample space was enhanced algorithmically improve diversity samples. Secondly, EMA attention-mechanism module introduced encode global information; this could further aggregate pixel-level features through dimensional interaction strengthen small-target-detection capability by incorporating a 160 × detection head. Finally, EIoU utilized as loss function reduce incidence missed detections false target under condition high density peaches. Experimental results show that compared with original YOLOv8n model, EMA-YOLO improves mAP 4.2%, Furthermore, SDD, Objectbox, YOLOv5n, YOLOv7n, model’s 30.1%, 14.2%,15.6%, 7.2%, respectively. In addition, achieved good different conditions illumination distance significantly reduced detections. Therefore, method can provide technical support smart management yellow-peach

Язык: Английский

---

MAE-YOLOv8-based small object detection of green crisp plum in real complex orchard environments

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 226, С. 109458 - 109458

Опубликована: Сен. 20, 2024

Язык: Английский

---

PP-YOLO: Deep learning based detection model to detect apple and cherry trees in orchard based on Histogram and Wavelet preprocessing techniques

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 232, С. 110052 - 110052

Опубликована: Фев. 8, 2025

Язык: Английский

---

Comprehensive Performance Evaluation of YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments

Опубликована: Окт. 18, 2024

Object detection, specifically fruitlet is a crucial image processing technique in agricultural automation, enabling the accurate identification of fruitlets on orchard trees within images. It vital for early fruit load management and overall crop management, facilitating effective deployment automation robotics to optimize productivity resource use. This study systematically performed an extensive evaluation performances all configurations YOLOv8, YOLOv9, YOLOv10, YOLO11 object detection algorithms terms precision, recall, mean Average Precision at 50% Intersection over Union (mAP@50), computational speeds including pre-processing, inference, post-processing times immature green apple (or fruitlet) commercial orchards. Additionally, this research validated in-field counting using iPhone machine vision sensors 4 different varieties (Scifresh, Scilate, Honeycrisp & Cosmic crisp). investigation total 22 YOLOv10 (5 6 5 YOLO11) revealed that YOLOv9 gelan-base YOLO11s outperforms other YOLOv8 mAP@50 with score 0.935 0.933 respectively. In specifically, Gelan-e achieved highest 0.935, outperforming YOLOv11s's 0.0.933, YOLOv10s’s 0.924, YOLOv8s's 0.924. value among (0.899), YOLO11m best (0.897). comparison inference speeds, YOLO11n demonstrated fastest only 2.4 ms, while speed across were 5.5, 11.5 4.1 ms YOLOv10n, gelan-s YOLOv8n

Язык: Английский

---

A lightweight real-time algorithm for plum harvesting detection in orchards under complex conditions

Signal Image and Video Processing, Год журнала: 2025, Номер 19(4)

Опубликована: Фев. 22, 2025

Язык: Английский

---

Systematic review on machine learning and computer vision in precision agriculture: Applications, trends, and emerging techniques

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 148, С. 110401 - 110401

Опубликована: Март 13, 2025

Язык: Английский

---

Advancing Capsicum Detection in Night-Time Greenhouse Environments using Deep Learning Models: Comparative Analysis and Improved Zero-Shot Detection through Fusion with a Single-Shot Detector

Franklin Open, Год журнала: 2025, Номер unknown, С. 100243 - 100243

Опубликована: Март 1, 2025

Язык: Английский

---

First Report of Lasiodiplodia pseudotheobromae Causing Soft Rot of Plum in China

Plant Disease, Год журнала: 2024, Номер 108(4), С. 1097 - 1097

Опубликована: Янв. 12, 2024

Plum (Prunus salicina) is one of the most important fruit tree species worldwide (Valderrama-Soto et al. 2021). In June 2023, postharvest soft rot symptoms were observed on plum fruits in several markets Guiyang city, Guizhou province, China. The disease incidence these ranged from 20 to 25% with 70% severity. showed rotting, which was characterized by water soaked tissue, softening and presence whitish mycelia four days post inoculation. severe conditions, whole become rotted covered white fungal mycelia. Small sections (5 × 3 mm) 6 diseased surface sterilized using 75% ethanol for 30 s followed 0.1% mercuric chloride solution 5 min, rinsed three times ddH2O, then transferred onto potato dextrose agar (PDA) incubated at 25 ± 2°C days. Three pure cultures (GUCC23-0001 GUCC23-0003) obtained transferring a single hyphal tip new PDA plates. Colonies isolates grayish-white initially, gradually turning brown fluffy aerial uneven edges finally turned dark gray colony after five pseudoparaphyses hyaline, cylindrical, aseptate, rounded apex. Conidia ellipsoidal, unicellular, 24.2 28.6 12.3 15.5 µm size (n = 30) (Fig. S1), similar morphology Lasiodiplodia pseudotheobromae (Alves 2008). Furthermore, DNA extracted fresh seven fungus genomic extraction kit (Biomiga, USA). Partial sequences loci including internal transcribed spacer (ITS), translation elongation factor 1-alpha (tef1), beta-tubulin (tub2), polymerase II second largest subunit (rpb2) amplified ITS1 ITS4 (White 1990), EF1-688F EF1-1251R 2008), Bt2a Bt2b (Glass Donaldson 1995), RPB2-LasF RPB2-LasR, respectively (Cruywagen 2017). GenBank accession numbers are OR361680, OR361681, OR361682 ITS, OR423394, OR423395, OR423396 tef1, OR423397, OR423398, OR423399 tub2, OR423391, OR423392, OR423393 rpb2, gene sequencing 99.6 100% identity ex-type strain L. (CBS 116459). Phylogenetic analysis also placed our highly supported clade reference isolate S2). Another experiment designed confirm pathogenicity test additional confirmation. Five mm mycelial plugs day old culture surface-sterilized non-wounded 12 hours 25°C Sterilized free used as negative control. Mycelial removed following plastic boxes 2°C. repeated twice. evaluated under control conditions laboratory (relative humidity, 70 5% temperature 5˚C). These signs initially plums markets. No fruits. re-isolated inoculated very those isolated samples morphology, fulfilling Koch's postulates. To best knowledge, this first report causing 2022, total planting area 1946.5 thousand hectares, produces approximately 6626300 tons (Food Agriculture Organization United Nations, 2022). Based severity reported current study, may be responsible nearly 35% yield losses severe. Therefore, study laid theoretical foundation prevention post-harvest plum.

Язык: Английский

---

Yolo-Chili: An Efficient Lightweight Network Model for Localization of Pepper Picking in Complex Environments

Опубликована: Апрель 29, 2024

Currently there are fewer depth models applied to pepper picking detection, while the existing generalized neural networks have problems such as large model parameters, long training time, and low accuracy.In order solve above problems, this paper proposes a Yolo-chili target detection algorithm for chili detection. First, classical yolov5 is used benchmark model, an adaptive spatial feature pyramid structure combining attention mechanism idea of multi-scale prediction introduced improve model's effect on occluded peppers small peppers. Secondly, three-channel module algorithm's long-distance recognition ability reduce interference redundant testers. Finally, quantized pruning method parameters realize lightweight processing model. Applying homemade dataset, AP value reaches 93.11%; accuracy rate 93.51% recall 92.55%.The experimental results show that yolo-chili able achieve accurate real-time under complex orchards.

Язык: Английский

---