Vision System for Automatic On-Tree Kiwifruit Counting and Yield Estimation

Mekhalfi, Mohamed Lamine; Nicolò, Carlo; Ianniello, Ivan; Calamita, Federico; Goller, Rino; Barazzuol, Maurizio; Melgani, Farid

doi:10.3390/s20154214

Cited by 30 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preharvest fruit yield estimation (i.e., fruit yield is the amount of fruit product in Kg per −1 tree or Kg ha −1 ) is critical for strategic market planning for both small-scale farmers and large-scale farming companies. Therefore, the total yield was estimated by multiplying mean fruit weight by the total number of fruits per tree (fruit load) [33,34]. In addition, we calculated yield efficiency (kg m −3 ) by dividing the yield for an individual tree by its respective canopy volume.…”

Section: Yield Estimation and Yield Efficiencymentioning

confidence: 99%

Fruit weight and yield estimation models for five avocado cultivars in Ethiopia

Mokria¹,

Gebrekirstos²,

Said³

et al. 2022

Environ. Res. Commun.

View full text Add to dashboard Cite

Avocado (Persea Americana Mill.) is an important tree crop and proved to be a very rewarding commercial crop for export and local consumptions. Due to high local and global market demand, avocado plantation and production is considerably increasing in many parts of Ethiopia. Thus, pre-harvest yield estimation is necessary for market planning, monitoring, and tracking long-term productivity. Though there are studies on various characteristics of avocado tree, not much has been documented about its productivity due to lack of easy and non-destructive ways to estimate yield. Hence, this study was conducted to develop cultivar-specific and mixed-cultivar fruit weight estimation models using single and multiple predictors including fruit length and diameter. We harvested and weighted 1800 fruits from five cultivars grown in 30 smallholder farmlands. The highest mean fruit load was recorded for Nabal (281 (±36 Fruit. tree-1) and Hass 249 (±27 Fruit. tree-1). A large proportion of avocado fruits were in the range that are commercially valuable. The correlation between fruit load and crown diameter were positive for each cultivar and it was stronger for Ettinger (r = 0.7, p < 0.01, n = 30), followed by Nabal (r = 0.64, P < 0.01, n = 30). We observed that fruit weight correlates significantly (P < 0.01) with fruit diameter and length. Our best models explained 80% for Ettinger, 78% for Fuerte, 80% for Hass, 63% for Nabal, 72% for Reed and 72% for multiple cultivars. Estimated yield was nearly 45 kg. tree-1 for Ettinger, Fuerte, Hass, Reed and 90 Kg. tree-1 for Nabal. The equations developed in this study are suitable for conducting pre-harvest yield estimation and monitoring changes in avocado productivity. Such information is critical for planned marketing and support government initiatives towards making horticulture sector as a possible engine for poverty alleviation and national economic growth.

show abstract

Section: Yield Estimation and Yield Efficiencymentioning

confidence: 99%

Fruit weight and yield estimation models for five avocado cultivars in Ethiopia

Mokria¹,

Gebrekirstos²,

Said³

et al. 2022

Environ. Res. Commun.

View full text Add to dashboard Cite

show abstract

“…Work in precision agriculture has been conducted for several decades but has taken off more recently with significant advances in robotics and machine vision. Most of the automation work in this area has focused on harvesting [Silwal et al, 2017;Williams et al, 2019;Williams et al, 2020b], or pollination [Amador and Hu, 2017;Ohi et al, 2018;Williams et al, 2020a;Williams et al, 2021] tasks to supplement the workforce directly. However, yield estimation is a critical area for planning the overall workload throughout the season, and accurate crop yield measurements can provide key information for predicting workload throughout the year.…”

Section: Related Workmentioning

confidence: 99%

Seeing the Fruit for the Leaves: Towards Automated Apple Fruitlet Thinning

Qureshi¹,

Loh²,

Kwon³

et al. 2023

Preprint

View full text Add to dashboard Cite

Following a global trend, the lack of reliable access to skilled labour is causing critical issues for the effective management of apple orchards. One of the primary challenges is maintaining skilled human operators capable of making precise fruitlet thinning decisions. Thinning requires accurately measuring the true crop load for individual apple trees to provide optimal thinning decisions on an individual basis. A challenging task due to the dense foliage obscuring the fruitlets within the tree structure. This paper presents the initial design, implementation, and evaluation details of the vision system for an automatic apple fruitlet thinning robot to meet this need. The platform consists of a UR5 robotic arm and stereo cameras which enable it to look around the leaves to map the precise number and size of the fruitlets on the apple branches. We show that this platform can measure the fruitlet load on the apple tree to with 84% accuracy in a real-world commercial apple orchard while being 87% precise.

show abstract

“…The experimental results showed that the tracking confidence was greatly enhanced after algorithm improvement. However, this method did not work for a long time and only performed counting for videos within 30 s. Mekhalfi et al (2020) proposed a counting method using LAB color space and Adaboost to determine the location of kiwi fruit. The disadvantages of this method were its inability to achieve real‐time operation and its poor robustness.…”

Section: Related Workmentioning

confidence: 99%

An efficient online citrus counting system for large‐scale unstructured orchards based on the unmanned aerial vehicle

Xiong

Wang

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

The accurate detection and counting of fruits in natural environments are key steps for the early yield estimation of orchards and the realization of smart orchard production management. However, existing citrus counting algorithms have two primary limitations: the performance of counting algorithms needs to be improved, and their system operation efficiency is low in practical applications. Therefore, in this paper, we propose a novel end-to-end orchard fruit counting pipeline that can be used by multiple unmanned aerial vehicles (UAVs) in parallel to help overcome the above problems. First, to obtain on-board camera images online, an innovative UAV live broadcast platform was developed for the orchard scene. Second, for this challenging specific scene, a detection network named Citrus-YOLO was designed to detect fruits in the video stream in real-time. Then, the DeepSort algorithm was used to assign a specific ID to each citrus fruit in the online UAV scene and track the fruits across video frames. Finally, a nonuniform distributed counter was proposed to correct the fruit count during the tracking process, and this can significantly reduce the counting errors caused by tracking failure. This is the first work to realize online and end-to-end counting in a field orchard environment. The experimental resultsshow that the F1 score and mean absolute percentage error of the method are 89.07% and 12.75%, respectively, indicating that the system can quickly and accurately achieve fruit counting in large-scale unstructured citrus orchards.

show abstract

Vision System for Automatic On-Tree Kiwifruit Counting and Yield Estimation

Cited by 30 publications

References 34 publications

Fruit weight and yield estimation models for five avocado cultivars in Ethiopia

Fruit weight and yield estimation models for five avocado cultivars in Ethiopia

Seeing the Fruit for the Leaves: Towards Automated Apple Fruitlet Thinning

An efficient online citrus counting system for large‐scale unstructured orchards based on the unmanned aerial vehicle

Contact Info

Product

Resources

About