Abstract
Pumpkins are economically and nutritionally valuable vegetables with increasing popularity and acreage across Europe. Successful commercialization, however, require detailed pre-harvest information about number and weight of the fruits. To get a non-destructive and cost-effective yield estimation, we developed an image processing methodology for high-resolution RGB data from Unmanned aerial vehicle (UAV) and applied this on a Hokkaido pumpkin farmer’s field in North-western Germany. The methodology was implemented in the programming language Python and comprised several steps, including image pre-processing, pixel-based image classification, classification post-processing for single fruit detection, and fruit size and weight quantification. To derive the weight from two-dimensional imagery, we calculated elliptical spheroids from lengths of diameters and heights. The performance of this processes was evaluated by comparison with manually harvested ground-truth samples and cross-checked for misclassification from randomly selected test objects. Errors in classification and fruit geometry could be successfully reduced based on the described processing steps. Additionally, different lighting conditions, as well as shadows, in the image data could be compensated by the proposed methodology. The results revealed a satisfactory detection of 95% (error rate of 5%) from the field sample, as well as a reliable volume and weight estimation with Pearson’s correlation coefficients of 0.83 and 0.84, respectively, from the described ellipsoid approach. The yield was estimated with 1.51 kg m−2 corresponding to an average individual fruit weight of 1100 g and an average number of 1.37 pumpkins per m2. Moreover, spatial distribution of aggregated fruit densities and weights were calculated to assess in-field optimization potential for agronomic management as demonstrated between a shaded edge compared to the rest of the field. The proposed approach provides the Hokkaido producer useful information for more targeted pre-harvest marketing strategies, since most food retailers request homogeneous lots within prescribed size or weight classes.
Highlights
Pumpkins (Cucurbita spp.) are produced on 2 million ha of land worldwide and becoming increasingly popular across Europe [1]
After the Unmanned aerial vehicle (UAV) flight, a total of 100 randomly selected Hokkaido pumpkins were measured for diameter and height, and the exact position of each pumpkin fruit was located by differential GPS
The diameter refers to the largest horizontal extension of the pumpkin, whereas the height is determined by the distance between the stem and the blossom end
Summary
Pumpkins (Cucurbita spp.) are produced on 2 million ha of land worldwide and becoming increasingly popular across Europe [1]. To overcome those main challenges in the above-mentioned papers were related to the detection of single restrictions, the studies used techniques from the currently very successful field of deep fruits which overlap [11] or were partially hidden under leaves [13] To overcome those learning, allowing the shape of a fruit to be learned using a neural network. Sensors 2021, 21, 118 restrictions, the studies used techniques from the currently very successful field of deep learning, allowing the shape of a fruit to be learned using a neural network These models usually require a large amount of training data to outperform classical methods [15] and are very computationally expensive to train. Timated number and yield distribution of the fruits within the study area was investigated and evaluated to derive agronomic implications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
