Growth characteristics based multi-class kiwifruit bud detection with overlap-partitioning algorithm for robotic thinning DOI

Haojie Dang,

Leilei He,

Yufei Shi

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 229, P. 109715 - 109715

Published: Dec. 6, 2024

Language: Английский

A robust vision system for measuring and positioning green asparagus based on YOLO-seg and 3D point cloud data DOI
Chen Chen, Jing Li, Binglin Liu

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 230, P. 109937 - 109937

Published: Jan. 13, 2025

Language: Английский

Citations

1
Advancements in artificial pollination of crops: from manual to autonomous DOI

Leilei He,

Xiaojuan Liu, Yezhang Ding

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 231, P. 110067 - 110067

Published: Feb. 5, 2025

Language: Английский

Citations

1
Morphological estimation of primary branch length of individual apple trees during the deciduous period in modern orchard based on PointNet++ DOI
Xiaoming Sun,

Leilei He,

Hanhui Jiang

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 220, P. 108873 - 108873

Published: April 6, 2024

Language: Английский

Citations

8
An overview of recent advancements in hyperspectral imaging in the egg and hatchery industry DOI Creative Commons
Md Wadud Ahmed, Alin Khaliduzzaman, J.L. Emmert

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 230, P. 109847 - 109847

Published: Dec. 18, 2024

Language: Английский

Citations

8
Advances in Object Detection and Localization Techniques for Fruit Harvesting Robots DOI Creative Commons
Xiaojie Shi, Shaowei Wang, Bo Zhang

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(1), P. 145 - 145

Published: Jan. 9, 2025

Due to the short time, high labor intensity and workload of fruit vegetable harvesting, robotic harvesting instead manual operations is future. The accuracy object detection location directly related picking efficiency, quality speed fruit-harvesting robots. Because its low recognition accuracy, slow poor localization traditional algorithm cannot meet requirements automatic-harvesting increasingly evolving powerful deep learning technology can effectively solve above problems has been widely used in last few years. This work systematically summarizes analyzes about 120 literatures on three-dimensional positioning algorithms robots over 10 years, reviews several significant methods. difficulties challenges faced by current are proposed from aspects lack large-scale high-quality datasets, complexity agricultural environment, etc. In response challenges, corresponding solutions future development trends constructively proposed. Future research technological should first these using weakly supervised learning, efficient lightweight model construction, multisensor fusion so on.

Language: Английский

Citations

0
A Novel Multinozzle Targeting Pollination Robot for Clustered Kiwifruit Flowers Based on Air–Liquid Dual‐Flow Spraying DOI Open Access

Changqing Gao,

Leilei He,

Yezhang Ding

et al.

Journal of Field Robotics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 19, 2025

ABSTRACT Manual pollination of kiwifruit flowers is a labor‐intensive work that highly desired to be replaced by robotic operations. In this research, robot was developed achieve precision clustered in the orchard. The consists five systems, including multinozzle end‐effector, mechanical arm, vision system, crawler‐type chassis, and control system. can select preferential then target their pistil pollination. First, statistical analysis dimensions flower clusters individual conducted fit normal distribution curves, which guided design spray coverage combination intervals for end‐effector. Second, optimal parameters were determined based on three‐factor, five‐level quadratic orthogonal experiment, is, air pressure 70.4 kPa, rate flow 86.0 mL/min, distance 27.8 cm. A targeted strategy selection structure Field experiments commercial orchard evaluate its feasibility performance, an average success targeting 93.4% at speed 1.0 s per achieved. Furthermore, compared with artificial assisted methods, it improve utilization pollen consumption 0.20 g every 60 fruit set 88.9%. validations demonstrated efficiently pollinate save pollen.

Language: Английский

Citations

0
Yield estimation in precision viticulture by combining deep segmentation and depth-based clustering DOI Creative Commons
Rosa Pia Devanna, Laura Romeo, Giulio Reina

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 110025 - 110025

Published: Feb. 11, 2025

Language: Английский

Citations

0
YOLOv8n-DDA-SAM: Accurate Cutting-Point Estimation for Robotic Cherry-Tomato Harvesting DOI Creative Commons
Gengming Zhang, Hao Cao, Yangwen Jin

et al.

Agriculture, Journal Year: 2024, Volume and Issue: 14(7), P. 1011 - 1011

Published: June 26, 2024

Accurately identifying cherry-tomato picking points and obtaining their coordinate locations is critical to the success of robots. However, previous methods for semantic segmentation alone or combining object detection with traditional image processing have struggled accurately determine point due challenges such as leaves well targets that are too small. In this study, we propose a YOLOv8n-DDA-SAM model adds branch target achieve desired compute point. To be specific, YOLOv8n used initial model, dynamic snake convolutional layer (DySnakeConv) more suitable stems in neck model. addition, large kernel attention mechanism adopted backbone use ADown convolution resulted better fusion stem features certain decrease number parameters without loss accuracy. Combined SAM, mask effectively obtained then accurate by simple shape-centering calculation. As suggested experimental results, proposed significantly improved from models not only detecting but also stem’s masks. [email protected] F1-score, achieved 85.90% 86.13% respectively. Compared original YOLOv8n, YOLOv7, RT-DETR-l YOLOv9c, has 24.7%, 21.85%, 19.76%, 15.99% F1-score increased 16.34%, 12.11%, 10.09%, 8.07% respectively, 6.37M. branch, does it need produce relevant datasets, its mIOU 11.43%, 6.94%, 5.53%, 4.22% 12.33%, 7.49%, 6.4%, 5.99% compared Deeplabv3+, Mask2former, DDRNet SAN summary, can satisfy requirements high-precision provides strategy system cherry-tomato.

Language: Английский

Citations

3
End-to-end stereo matching network with two-stage partition filtering for full-resolution depth estimation and precise localization of kiwifruit for robotic harvesting DOI

Xudong Jing,

Hanhui Jiang,

Shiao Niu

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 225, P. 109333 - 109333

Published: Aug. 20, 2024

Language: Английский

Citations

3
Growth characteristics based multi-class kiwifruit bud detection with overlap-partitioning algorithm for robotic thinning DOI

Haojie Dang,

Leilei He,

Yufei Shi

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 229, P. 109715 - 109715

Published: Dec. 6, 2024

Language: Английский

Citations

1