Grape Bunch Detection at Different Growth Stages Using Deep Learning Quantized Models

• Type: Article in International Scientific Journal
• Date: 2021

Authors

Aguiar, AS (Author) Other; Magalhaes, SA (Author) Other; Filipe Neves Santos (Author) FEUP; Castro, L (Author) Other; Pinho, T (Author) Other; Valente, J (Author) Other; Martins, R (Author) Other; Boaventura Cunha, J (Author) Other

Journal

The Journal is awaiting validation by the Administrative Services.

Title: AGRONOMY-BASEL

Vol. 11

Final page: 1890

ISSN: 2073-4395

Publisher: MDPI

Indexing

ISI Web of Knowledge - 41 Citations

Scopus - 54 Citations

Other information

Authenticus ID: P-00V-DSK

DOI: 10.3390/agronomy11091890

Abstract (EN): The agricultural sector plays a fundamental role in our society, where it is increasingly important to automate processes, which can generate beneficial impacts in the productivity and quality of products. Perception and computer vision approaches can be fundamental in the implementation of robotics in agriculture. In particular, deep learning can be used for image classification or object detection, endowing machines with the capability to perform operations in the agriculture context. In this work, deep learning was used for the detection of grape bunches in vineyards considering different growth stages: the early stage just after the bloom and the medium stage where the grape bunches present an intermediate development. Two state-of-the-art single-shot multibox models were trained, quantized, and deployed in a low-cost and low-power hardware device, a Tensor Processing Unit. The training input was a novel and publicly available dataset proposed in this work. This dataset contains 1929 images and respective annotations of grape bunches at two different growth stages, captured by different cameras in several illumination conditions. The models were benchmarked and characterized considering the variation of two different parameters: the confidence score and the intersection over union threshold. The results showed that the deployed models could detect grape bunches in images with a medium average precision up to 66.96%. Since this approach uses low resources, a low-cost and low-power hardware device that requires simplified models with 8 bit quantization, the obtained performance was satisfactory. Experiments also demonstrated that the models performed better in identifying grape bunches at the medium growth stage, in comparison with grape bunches present in the vineyard after the bloom, since the second class represents smaller grape bunches, with a color and texture more similar to the surrounding foliage, which complicates their detection.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 23