RDE-YOLOv7: An Improved Model Based on YOLOv7 for Better Performance in Detecting Dragon Fruits

Zhou, Jialiang; Zhang, Yueyue; Wang, Jinpeng

doi:10.3390/agronomy13041042

Cited by 18 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhu Lixue et al [26] proposed a dragon fruit image segmentation and attitude assessment method based on an improved U-Net to achieve a three-dimensional attitude assessment of dragon fruits, providing tech-nical support for the automated and accurate picking of intelligent dragon-fruit-picking robots, but it is not suitable in the following cases: in a picking environment with a small fruit size, high density, and complex environment, the visual recognition effect will be reduced. Jialiang Zhou et al [27] proposed a dragon fruit detection method based on RDE-YOLOv7 to identify and locate dragon fruits more accurately, which theoretically supports the development of dragon-fruit-picking robots, which have a very high recognition accuracy for a single fruit, but its visual recognition effect decreases in picking environments with a high fruit density and complex environment. Bin Zhang et al [28] suggested the integration of a lightweight network, specifically an enhanced version of YOLOv5s, to achieve the consistent detection of dragon fruits across diverse orchard conditions and weather patterns, and the improved model has good robustness, which offers a good solution for dragon-fruit-picking robotics, providing a theoretical foundation and technical support.…”

Section: Introductionmentioning

confidence: 90%

Designing and Testing a Picking and Selecting Integrated Remote-Operation-Type Dragon-Fruit-Picking Device

Yao,

Qiu,

Sun

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In order to effectively solve the problems of the complex growth state of dragon fruit and how the picking process is mostly manual, this study designed a picking and selecting integrated remote-operation-type dragon-fruit-picking device. Based on SOLIDWORKS 2020 software for the three-dimensional digital design and overall assembly of key components, the structure and working theory of the machine are introduced. By improving the high-recognition-rate dragon fruit target detection algorithm based on YOLOv5, better recognition and locating effects were achieved for targets with a small size and high density, as well as those in bright-light scenes. Serial communication, information acquisition, and the precise control of each picking action were realized by building the software and hardware platforms of the picking device control system. By analyzing the working principle of the mechanical system and the mechanics of the machine picking process, the critical factors affecting the net picking rate and damage rate of the dragon-fruit-picking device were confirmed. Based on the force and parameter analysis of the test results, it was confirmed that the machine had an optimal picking influence when the flexible claw closing speed was 0.029 m/s, the electric cylinder extending speed was 0.085 m/s, and the mechanical arm moving speed was 0.15 m/s. The net picking rate of the device reached 90.5%, and the damage rate reached 2.9%. The picking device can complete the picking of a single dragon fruit, as well as a plurality of fruits grown at a growing point, and integrates the integration of picking fruits, removing bad fruits, and sorting fruits, which can improve the efficiency of dragon fruit harvesting and replace manual work.

show abstract

Section: Introductionmentioning

confidence: 90%

Designing and Testing a Picking and Selecting Integrated Remote-Operation-Type Dragon-Fruit-Picking Device

Yao,

Qiu,

Sun

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…YOLOv7 is a real-time object detection algorithm ( Soeb et al., 2023 ), which has evolved from YOLOv5 and has faster inference speed, improved detection accuracy, and reduced computational complexity. The algorithm consists of three main parts: the input layer, backbone layer, and output layer ( Tang et al., 2023 ), and uses either a loss function with or without an auxiliary training head ( Zhou et al., 2023 ).…”

Section: Methodsmentioning

confidence: 99%

Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network

Fan,

An,

Wang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

The viability of Zea mays seed plays a critical role in determining the yield of corn. Therefore, developing a fast and non-destructive method is essential for rapid and large-scale seed viability detection and is of great significance for agriculture, breeding, and germplasm preservation. In this study, hyperspectral imaging (HSI) technology was used to obtain images and spectral information of maize seeds with different aging stages. To reduce data input and improve model detection speed while obtaining more stable prediction results, successive projections algorithm (SPA) was used to extract key wavelengths that characterize seed viability, then key wavelength images of maize seed were divided into small blocks with 5 pixels ×5 pixels and fed into a multi-scale 3D convolutional neural network (3DCNN) for further optimizing the discrimination possibility of single-seed viability. The final discriminant result of single-seed viability was determined by comprehensively evaluating the result of all small blocks belonging to the same seed with the voting algorithm. The results showed that the multi-scale 3DCNN model achieved an accuracy of 90.67% for the discrimination of single-seed viability on the test set. Furthermore, an effort to reduce labor and avoid the misclassification caused by human subjective factors, a YOLOv7 model and a Mask R-CNN model were constructed respectively for germination judgment and bud length detection in this study, the result showed that mean average precision (mAP) of YOLOv7 model could reach 99.7%, and the determination coefficient of Mask R-CNN model was 0.98. Overall, this study provided a feasible solution for detecting maize seed viability using HSI technology and multi-scale 3DCNN, which was crucial for large-scale screening of viable seeds. This study provided theoretical support for improving planting quality and crop yield.

show abstract

“…To evaluate the performance of the model, precision (P), recall (R), and mean average precision (mAP) are used [56]. These above metrics are calculated as follows:…”

Section: Evaluation Metricsmentioning

confidence: 99%

ODN-Pro: An Improved Model Based on YOLOv8 for Enhanced Instance Detection in Orchard Point Clouds

Pan,

Xiao,

et al. 2024

Agronomy

View full text Add to dashboard Cite

In an unmanned orchard, various tasks such as seeding, irrigation, health monitoring, and harvesting of crops are carried out by unmanned vehicles. These vehicles need to be able to distinguish which objects are fruit trees and which are not, rather than relying on human guidance. To address this need, this study proposes an efficient and robust method for fruit tree detection in orchard point cloud maps. Feature extraction is performed on the 3D point cloud to form a two-dimensional feature vector containing three-dimensional information of the point cloud and the tree target is detected through the customized deep learning network. The impact of various feature extraction methods such as average height, density, PCA, VFH, and CVFH on the detection accuracy of the network is compared in this study. The most effective feature extraction method for the detection of tree point cloud objects is determined. The ECA attention module and the EVC feature pyramid structure are introduced into the YOLOv8 network. The experimental results show that the deep learning network improves the precision, recall, and mean average precision by 1.5%, 0.9%, and 1.2%, respectively. The proposed framework is deployed in unmanned orchards for field testing. The experimental results demonstrate that the framework can accurately identify tree targets in orchard point cloud maps, meeting the requirements for constructing semantic orchard maps.

show abstract

RDE-YOLOv7: An Improved Model Based on YOLOv7 for Better Performance in Detecting Dragon Fruits

Cited by 18 publications

References 22 publications

Designing and Testing a Picking and Selecting Integrated Remote-Operation-Type Dragon-Fruit-Picking Device

Designing and Testing a Picking and Selecting Integrated Remote-Operation-Type Dragon-Fruit-Picking Device

Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network

ODN-Pro: An Improved Model Based on YOLOv8 for Enhanced Instance Detection in Orchard Point Clouds

Contact Info

Product

Resources

About