Fruit Maturity Recognition from Agricultural, Market and Automation Perspectives

Author(s):  
Koteswar Rao Jerripothula ◽  
Sarvesh Kumar Shukla ◽  
Samyak Jain ◽  
Shudhanshu Singh
2020 ◽  
Vol 31 (6) ◽  
pp. 700-716
Author(s):  
M. Yu. Ksenofontov ◽  
D. A. Polzikov ◽  
A. V. Urus

2019 ◽  
Vol 99 (4) ◽  
pp. 444-459
Author(s):  
John A. Cline

‘Honeycrisp’ apple trees are highly prone to biennial bearing and predisposed to bitter pit. The hypothesis that tank mix sprays of ethephon (ETH), naphthaleneacetic acid (NAA), and 1-aminocyclopropane carboxylic acid (ACC) combined with calcium chloride (CaCl2) can mitigate these production problems was tested in a 3-yr study. Mature ‘Honeycrisp’ trees were treated with either three or six summer applications of 150 mg L−1 ETH or 5 mg L−1 NAA, all tank-mixed with and without CaCl2, or two or five applications of 150 mg L−1 ACC (without CaCl2). Treatments were applied at 10-d intervals and initiated between 21 and 26 June. All treatments had little effect on enhancing return bloom of ‘Honeycrisp’. NAA, ETH, and CaCl2 all influenced fruit maturity and quality at harvest to varying degrees and across years. Fruit treated with NAA were firmer compared with untreated fruit in 2 out of 3 yr, whereas overall, fruit treated with six sprays of ETH had lower fruit firmness and were more mature. NAA had less influence on fruit quality attributes at harvest than did ETH, and decreased pre-harvest fruit drop (PFD). PFD increased with ETH in 1 out of 2 yr, whereas ACC and NAA both decreased PFD in 1 out of 2 yr. Overall, ETH and NAA, with or without CaCl2, had significant but inconsistent effects on fruit quality and maturity, all dependent on the year and number of applications. Adding CaCl2 decreased fruit firmness in 2 out of 3 yr.


Weed Science ◽  
2021 ◽  
pp. 1-23
Author(s):  
Katherine M. Ghantous ◽  
Hilary A. Sandler

Abstract Applying control measures when carbohydrate levels are low can decrease the likelihood of plant survival, but little is known about the carbohydrate cycles of dewberry (Rubus spp.), a problematic weed group on cranberry farms. Weedy Rubus plants were collected from areas adjacent to production beds on commercial cranberry farms in Massachusetts, two locations per year for two years. For each site and year, four entire plants were collected at five phenological stages: budbreak, full leaf expansion, flowering, fruit maturity, and after onset of dormancy. Root sections were analyzed for total nonstructural carbohydrate (TNC; starch, sucrose, fructose, and glucose). Overall trends for all sites and years showed TNC were lowest at full leaf expansion or flowering; when sampled at dormancy, TNC concentrations were greater than or equal to those measured at budbreak. Starch, a carbohydrate form associated with long-term storage, had low levels at budbreak, leaf expansion and/or flowering with a significant increase at fruit maturity and the onset of dormancy, ending at levels higher than those found at budbreak. The concentration of soluble sugars, carbohydrate forms readily usable by plants, was highest at budbreak compared to the other four phenological samplings. Overall, our findings supported the hypothesis that TNC levels within the roots of weedy Rubus plants can be predicted based on different phenological growth stages in Massachusetts. However, recommendations for timing management practices cannot be based on TNC cycles alone; other factors such as temporal proximity to dormancy may also impact Rubus plants recovery and further research is warranted. Late-season damage should allow less time for plants to replenish carbohydrate reserves (prior to the onset of dormancy), thereby likely enhancing weed management tactics effectiveness over time. Future studies should consider tracking the relationship between environmental conditions, phenological stages, and carbohydrate trends.


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1288
Author(s):  
Cinmayii A. Garillos-Manliguez ◽  
John Y. Chiang

Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.


2021 ◽  
Vol 146 ◽  
pp. 105663
Author(s):  
Isabelle Grechi ◽  
Anne-Laure Preterre ◽  
Aude Caillat ◽  
Frédéric Chiroleu ◽  
Alain Ratnadass

Sign in / Sign up

Export Citation Format

Share Document