Tea Sprout Picking Point Identification Based on Improved DeepLabV3+

Abstract

Tea sprout segmentation and picking point localization via machine vision are the core technologies of automatic tea picking. This study proposes a method of tea segmentation and picking point location based on a lightweight convolutional neural network named MC-DM (Multi-Class DeepLabV3+ MobileNetV2 (Mobile Networks Vision 2)) to solve the problem of tea shoot picking point in a natural environment. In the MC-DM architecture, an optimized MobileNetV2 is used to reduce the number of parameters and calculations. Then, the densely connected atrous spatial pyramid pooling module is introduced into the MC-DM to obtain denser pixel sampling and a larger receptive field. Finally, an image dataset of high-quality tea sprout picking points is established to train and test the MC-DM network. Experimental results show that the MIoU of MC-DM reached 91.85%, which is improved by 8.35% compared with those of several state-of-the-art methods. The optimal improvements of model parameters and detection speed were 89.19% and 16.05 f/s, respectively. After the segmentation results of the MC-DM were applied to the picking point identification, the accuracy of picking point identification reached 82.52%, 90.07%, and 84.78% for single bud, one bud with one leaf, and one bud with two leaves, respectively. This research provides a theoretical reference for fast segmentation and visual localization of automatically picked tea sprouts.

Keywords

• DeepLabv3+
• deep learning
• semantic segmentation
• picking point identification