On-tree apple fruit size estimation using stereo vision with deep learning-based occlusion handling

Mirbod, Omeed; Choi, Daeun; Heinemann, P.; Marini, Richard P.; He, Long

doi:10.1016/j.biosystemseng.2022.12.008

Cited by 28 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently advanced machine learning techniques have been extensively applied for fruit size estimation in agriculture [17]. For example, Omeed et al [18] used a Convolutional Neural Network (CNN) model for on-tree kiwifruit detection and size estimation. Li et al [19] employed a Random Forest algorithm to estimate matured apple size using 3D images captured with a structured light-based imaging system.…”

Section: Related Studymentioning

confidence: 99%

Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques

Sapkota,

Ahmed,

Churuvija

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Detecting and estimating size of apples during the early stages of growth is crucial for predicting yield, pest management, and making informed decisions related to crop-load management, harvest and post-harvest logistics, and marketing. Traditional fruit size measurement methods are laborious and timeconsuming. This study employs the state-of-the-art YOLOv8 object detection and instance segmentation algorithm in conjunction with geometric shape fitting techniques on 3D point cloud data to accurately determine the size of immature green apples (or fruitlet) in a commercial orchard environment. The methodology utilized two RGB-D sensors: Intel RealSense D435i and Microsoft Azure Kinect DK. Notably, the YOLOv8 instance segmentation models exhibited proficiency in immature green apple detection, with the YOLOv8m

show abstract

Section: Related Studymentioning

confidence: 99%

Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques

Sapkota,

Ahmed,

Churuvija

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, Momtaz et al, (2023) [38] observed the size improvement with certain chemicals like urea, NAA, ethephon, and potassium iodide treatments. Mirbod et al, (2023) [36] revealed that bending of branches in May and June led to improved fruit size (length and diameter) fruit weight.…”

Section: Fruit Sizementioning

confidence: 99%

Systems of crop regulation in guava and their assessment

Singh,

Saha,

et al. 2024

Int. J. Adv. Biochem. Res.

View full text Add to dashboard Cite

The guava (Psidium guajava L.) is a fruit that has the potential to be profitable as well as being nutrient-rich. It has two seasons of blooming. However, in terms of production and quality, both season crops differ. The basic principle of crop regulation is based on the fact that guava flowers appear on new tender, vigorous on developing vegetative growth and the plant is compelled to be dormant and after the resumption, it (tree) produces bumper flowers and results in a heavy yield of better quality. Above all, such a cropping pattern results in increased grower returns while keeping control over consistent, high-quality fruit production. On the contrary, continuous blooming would result in lower yield along with extra watch and ward and marketing costs. Henceforth various techniques are used to regulate guava crops including withholding irrigation, flower bud thinning or removal, pruning level technique. All these techniques help to lower fruit set during the rainy season along with incline production in winter season. This paper includes all previous efforts concerning regulations/recommendations to date and future perspectives.

show abstract

“…As the caliper method is labor-intensive, alternative methods are sought [14]; however the method is commonly used to verify the truth of alternate procedures, i.e., as a validation device [14,23,[25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

“…Fruit may be partly occluded by leaves or other fruit in images of whole tree canopies. Detected partly occluded fruit should be included in fruit counting applications, but for a fruit sizing pipeline these detections should either be rejected, e.g., as undertaken by [13] and Neupane et al [40], or the geometry of the fruit must be reconstructed from visible portions of the fruit, e.g., as undertaken by Wang and Chen [41], Gené-Mola et al [42], and Mirbod, Choi, Heinemann, Marini, and He [28].…”

Section: Introductionmentioning

confidence: 99%

Fruit Sizing in Orchard: A Review from Caliper to Machine Vision with Deep Learning

Neupane

Pereira

Koirala

et al. 2023

Sensors

View full text Add to dashboard Cite

Forward estimates of harvest load require information on fruit size as well as number. The task of sizing fruit and vegetables has been automated in the packhouse, progressing from mechanical methods to machine vision over the last three decades. This shift is now occurring for size assessment of fruit on trees, i.e., in the orchard. This review focuses on: (i) allometric relationships between fruit weight and lineal dimensions; (ii) measurement of fruit lineal dimensions with traditional tools; (iii) measurement of fruit lineal dimensions with machine vision, with attention to the issues of depth measurement and recognition of occluded fruit; (iv) sampling strategies; and (v) forward prediction of fruit size (at harvest). Commercially available capability for in-orchard fruit sizing is summarized, and further developments of in-orchard fruit sizing by machine vision are anticipated.

show abstract

On-tree apple fruit size estimation using stereo vision with deep learning-based occlusion handling

Cited by 28 publications

References 14 publications

Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques

Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques

Systems of crop regulation in guava and their assessment

Fruit Sizing in Orchard: A Review from Caliper to Machine Vision with Deep Learning

Contact Info

Product

Resources

About