A Precision Pruning Strategy for Improving Efficiency of Vibratory Mechanical Harvesting of Apples

Zhang, Xin; He, Long; Majeed, Yaqoob; Whiting, Matthew; Karkee, Manoj; Zhang, Qin

doi:10.13031/trans.12825

Cited by 20 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results revealed that leaves that counted the maximum number of pixels had lower IoU than the background with the least number of pixels. Further increasing the number of images within the same pattern or adding high-resolution images can improve the network performance ( Zhang et al, 2018 ).…”

Section: Resultsmentioning

confidence: 99%

TheLNet270v1 – A Novel Deep-Network Architecture for the Automatic Classification of Thermal Images for Greenhouse Plants

et al. 2021

View full text Add to dashboard Cite

The real challenge for separating leaf pixels from background pixels in thermal images is associated with various factors such as the amount of emitted and reflected thermal radiation from the targeted plant, absorption of reflected radiation by the humidity of the greenhouse, and the outside environment. We proposed TheLNet270v1 (thermal leaf network with 270 layers version 1) to recover the leaf canopy from its background in real time with higher accuracy than previous systems. The proposed network had an accuracy of 91% (mean boundary F1 score or BF score) to distinguish canopy pixels from background pixels and then segment the image into two classes: leaf and background. We evaluated the classification (segment) performance by using more than 13,766 images and obtained 95.75% training and 95.23% validation accuracies without overfitting issues. This research aimed to develop a deep learning technique for the automatic segmentation of thermal images to continuously monitor the canopy surface temperature inside a greenhouse.

show abstract

Section: Resultsmentioning

confidence: 99%

TheLNet270v1 – A Novel Deep-Network Architecture for the Automatic Classification of Thermal Images for Greenhouse Plants

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Furthermore, shake-and-catch harvesting technology is a typical application to adapt tree architecture for fruit detachment and bruise reduction. And fruit trees planted with a precision pruning strategy and standardized agronomy can improve the efficiency of the vibratory mechanical harvesting of apples [143,144] . However, there is still no satisfactory shaking harvester to meet the requirement of commercial use for the fresh apple harvesting, which would be an important research field in the future.…”

Section: Integration Of Fruit Mechanical Harvester and Tree Agronomymentioning

confidence: 99%

Recent progress and future prospects for mechanized harvesting of fruit crops with shaking systems

Pu¹,

Wang²,

Yang³

et al. 2023

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Mechanized harvesting technologies with shaking systems for fruit industry have been widely investigated and significantly developed over the past several decades which were presented by a large amount of literature. This paper reviews the research and development progress of mechanized harvesting of fruits systematically with a focus on the theoretical study, fruit crop variety, shaking system categories, abscission chemical agents, and their actual applications. Based on the comprehensive review, mechanized harvesting systems for different fruit crops appear multifarious shaking modes with various vibratory mechanisms and structural dimensions. Major advantages in the development of fruit mechanical harvesting with effective vibratory patterns and catching frames provide a series of economic and agronomic benefits, such as reducing labor costs, promoting standardized planting, and increasing productivity. However, fruit injury and tree damage are the main reasons why mechanical shaking systems are rarely used for fresh fruit harvesting because of tenderness and frangibility of the fruit crops. Therefore, more efforts should be concentrated on the innovative shake-and-catch system with suitable frequency and amplitude to achieve low fruit damage or even nondestructive harvesting for fresh fruit market. This overview summarized the advantages and bottlenecks of these shaking systems for fruit harvesting and proposed the challenges and some constructive prospective viewpoints aimed at the major issues of mechanical harvesting techniques. In addition, employing sorting technologies to classify the postharvest fruits provide a new direction for the further development of mechanized harvesting in high-value fruit crops, as well as bring more benefits to growers and increase their interest in equipment investment on the mechanical shaking harvester for the fruit industry.

show abstract

“…In recent years, the planting area and yield of lotus in China have reached 613 thousand hm 2 and 15.48 million t, respectively. China has become a major producer and exporter of lotus seeds [3] . However, with the shortage of labor in the seasonal agricultural industry and soaring labor costs, the development of the lotus industry is facing the constraining problem of difficulties in harvesting lotus seedpods [4][5][6] .…”

Section: Introductionmentioning

confidence: 99%

Lightweight detection method for lotus seedpod in natural environment

Tang,

Wang,

et al. 2023

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

In order to solve the problems of the current target detection algorithms, such as poor discrimination of occluded targets, multiple parameters, complex networks, large amounts of computation, and not conducive to the deployment of mobile terminals, a lightweight lotus seedpod detection method based on YOLOv5s model was proposed in this study. First, the dataset was augmented by using a combination of offline and online augmentation, which improved the adaptability and robustness of the model in complex environments. Then, a lightweight Ghost convolution module was introduced to replace the original convolution, and a lightweight bidirectional feature pyramid network was designed, which could enhance the feature extraction and fusion capability of the network and reduce the amount of calculation and model size; On this basis, the combination of WIoU loss function and Mish activation function was adopted to improve the accuracy of feature extraction. Finally, the knowledge distillation training strategy was used to ensure the proposed lightweight model has the learning ability of a complex network model, improving the recall and precision of model detection. The results of the ablation study show that the proposed method effectively improves the detection performance of the YOLOv5s model for lotus seedpods. The mean average precision of the improved model was 89.7%, compared with the original YOLOv5s model increased by 2.8%, and the parameters and FLOPs were reduced by 2.36M and 7.3G, respectively. Compared with other detection algorithm models, the proposed algorithm model has the advantages of less computation, smaller model size, and higher detection precision. Therefore, the proposed improved optimization method based on the YOLOv5s model can effectively detect lotus seedpods, which provides theoretical research and technical support for intelligent picking of lotus seedpods in the actual operating environment.

show abstract

A Precision Pruning Strategy for Improving Efficiency of Vibratory Mechanical Harvesting of Apples

Cited by 20 publications

References 38 publications

TheLNet270v1 – A Novel Deep-Network Architecture for the Automatic Classification of Thermal Images for Greenhouse Plants

TheLNet270v1 – A Novel Deep-Network Architecture for the Automatic Classification of Thermal Images for Greenhouse Plants

Recent progress and future prospects for mechanized harvesting of fruit crops with shaking systems

Lightweight detection method for lotus seedpod in natural environment

Contact Info

Product

Resources

About