English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Citrus segmentation is a key step of automatic citrus picking. While mostcurrent image segmentation approaches achieve good segmentation results bypixel-wise segmentation, these supervised learning-based methods require alarge amount of annotated data, and do not consider the continuous temporalchanges of citrus position in real-world applications. In this paper, we firsttrain a simple CNN with a small number of labelled citrus images in asupervised manner, which can roughly predict the citrus location from eachframe. Then, we extend a state-of-the-art unsupervised learning approach topre-learn the citrus's potential movements between frames from unlabelledcitrus's videos. To take advantages of both networks, we employ the multimodaltransformer to combine supervised learned static information and unsupervisedlearned movement information. The experimental results show that combing bothnetwork allows the prediction accuracy reached at 88.3$\%$ IOU and 93.6$\%$precision, outperforming the original supervised baseline 1.2$\%$ and 2.4$\%$.Compared with most of the existing citrus segmentation methods, our method usesa small amount of supervised data and a large number of unsupervised data,while learning the pixel level location information and the temporalinformation of citrus changes to enhance the segmentation effect.

Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation