A fast convex hull algorithm inspired by human visual perception

Liu, Runzong; Tang, Yuan Yan; Chan, Patrick P. K.

doi:10.1007/s11042-018-6185-0

Cited by 3 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The greater the ratio of chord to arc, the straighter the pod's shape, the smaller the ratio, the more curved the pods. In this paper, first, the perimeter of the soybean pods contour was counted, and the polygon contour of the soybean pods was obtained by using the convex hull algorithm (Liu et al, 2018). Then, starting from the middle point on the left side of the contour, the vector angles of the two points close to the contour were calculated, and the two angles with the largest difference were obtained by dislocation subtraction.…”

Section: (4) Calculation Of the Chord And Arc Lengthmentioning

confidence: 99%

Recognition of soybean pods and yield prediction based on improved deep learning model

Guan

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

As a leaf homologous organ, soybean pods are an essential factor in determining yield and quality of the grain. In this study, a recognition method of soybean pods and estimation of pods weight per plant were proposed based on improved YOLOv5 model. First, the YOLOv5 model was improved by using the coordinate attention (CA) module and the regression loss function of boundary box to detect and accurately count the pod targets on the living plants. Then, the prediction model was established to reliably estimate the yield of the whole soybean plant based on back propagation (BP) neural network with the topological structure of 5-120-1. Finally, compared with the traditional YOLOv5 model, the calculation and parameters of the proposed model were reduced by 17% and 7.6%, respectively. The results showed that the average precision (AP) value of the improved YOLOv5 model reached 91.7% with detection rate of 24.39 frames per millisecond. The mean square error (MSE) of the estimation for single pod weight was 0.00865, and the average coefficients of determination R2 between predicted and actual weight of a single pod was 0.945. The mean relative error (MRE) of the total weight estimation for all potted soybean plant was 0.122. The proposed method can provide technical support for not only the research and development of the pod’s real-time detection system, but also the intelligent breeding and yield estimation.

show abstract

Section: (4) Calculation Of the Chord And Arc Lengthmentioning

confidence: 99%

Recognition of soybean pods and yield prediction based on improved deep learning model

Guan

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

A fast 3D object recognition algorithm using plane-constrained point pair features

Xiao

Gao

Dongqing

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Improved Convex Hull Algorithm Applied to Body Size Measurements

Fang

Sun

Chen

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The Quickhull algorithm is a very efficient convex hull algorithm for many engineering application. Although it can be applied in the clothing industry, its conventional formulation requires massive computational resources when processing point clouds from concave parts of the human body. Thus, we improve the Quickhull algorithm and apply it to accurately estimate human body dimensions. Assuming body symmetry with respect to the sagittal plane, some concave points can be quickly deleted to reduce the number of recursions, enhancing the overall calculation efficiency. Compared with the traditional Quickhull algorithm, the efficiency of the improved algorithm increases by 15.1–24.4%. Additionally, the computation time of the improved Quickhull algorithm is about three-quarters that of Graham’s scan. We expect that this study provides insights on the application of body size measurement and estimation based on 3D scan data.

show abstract

A fast convex hull algorithm inspired by human visual perception

Cited by 3 publications

References 34 publications

Recognition of soybean pods and yield prediction based on improved deep learning model

Recognition of soybean pods and yield prediction based on improved deep learning model

A fast 3D object recognition algorithm using plane-constrained point pair features

Improved Convex Hull Algorithm Applied to Body Size Measurements

Contact Info

Product

Resources

About