3DBunch: A Novel iOS-Smartphone Application to Evaluate the Number of Grape Berries per Bunch Using Image Analysis Techniques

Abstract

Evaluating the number of berries per bunch is a vital step of grape yield estimation in viticulture but is a labour intensive task for traditional manual measurement. Therefore, this paper develops a novel smartphone application for counting berries automatically from a single image. The application, called 3DBunch, acquires images from the camera or the album on a smartphone, and then estimates the number of berries by a reconstructed 3D bunch model based on the proposed image analysis techniques that are embedded in the developed iOS app. It also presents features of visualising the statistics of the reconstructed bunch, which including of the distribution of detected berry size in pixels and the total number of berries. It also has the capability of presenting sampling related information, which includes the person who conducted the sampling, the location of samples, the dates of sampling, the variety, farm, vineyards etc. The application was evaluated both on a simulator in a commercial computer and an iPad mini 4. By analysing 291 bunch images from two varieties the app achieved an accuracy of 91% regarding berry counting per bunch. Additionally, the computational time consumed to process 100 images on iPad mini 4 was studied and returned an average of 7.51 seconds per image. Getting these results with only a smartphone and a small backing board for capturing a photo with a single bunch, 3DBunch provides an efficient way for farmers to count berries in-vivo and it is available on iOS App Store now. INDEX TERMS berry counting, bunch analysis, image analysis, iOS application, yield estimation

Vineyard Yield Estimation, Prediction, and Forecasting: A Systematic Literature Review

“…Whatever the indirect method used, they all allow a fast and non-invasive alternative to manual sampling. They allow identifying single berries in images, even taken from a simple device such as a smartphone [56][57][58] and then using different methods such as convolutional neural networks [1,59], cellular automata [60], or even sensors capable of collecting phenotypic traits of grape bunches, that are known to be related with grapevine yield [14,61], to estimate yields.…”

“…The images can be acquired using a still camera [4,10,96] in a laboratory or under field conditions, and also by other optical or multispectral proximal sensors, on-the-go using ATVs [12,40,97], other terrestrial autonomous vehicles [7,48] including autonomous robot systems [15,102,106], UAVs [101,105] that cope with the limitations of ground vehicles regarding field conditions (slopes and soil) or in a more simple way on foot with a smartphone [57].…”

“…The more challenging aspect of the approach is to transform the data collected into an actual yield estimation. The more common approach is to identify automatically individual grapes or clusters for size determination e.g., [10,15,100,113] or other vine structures [115], along with 3D reconstruction [13,57,96,104,[108][109][110] to estimate the actual yield. This requires for the most, in the model development phase, training and validation supported by manually assessing cluster weight and berry number per cluster after the image acquisition.…”

GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs

“…An example is the use of small sophisticated tools [5][6][7] or even portable generic cameras [8,9], mounted on tractors or robots for in-field image acquisition, or the use of remote sensing imagery [10]. An even better and more appealing opportunity for farmers is to employ the smartphone [11][12][13][14] they already have and use in their daily activities. This simplified approach can overcome the current procedure based on destructive sampling (cutting off and weighting a collection of grape bunches) to obtain a yield estimate, as proposed in a rich line of research initiated by Nuske and colleagues in [15,16], that can help in increasing their productivity, even if sometimes specific setups are required [17].…”

“…Such gain is boosted by the coupling of the hardware technological advancement with the simultaneous scientific leap in mathematics and computer sciences. The result is the seamless integration of the image acquisition systems into analytics workflow powered by either deterministic algorithms from computer vision [14,[18][19][20] or predictive models from stochastic learning approaches, as the basis for estimating yield as well as controlling quality. In particular, the evolution of machine learning theory in the last decade reflects on precision agriculture, too.…”