Towards Semantic Scene Segmentation for Autonomous Agricultural Vehicles

Esma Mujkic, Dan Hermann, Ole Ravn, Morten L. Bilde, Nils Axel Andersen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

The development of autonomous agricultural vehicles depends on accurate visual interpretation of the environment. Semantic pixel-wise segmentation plays an important role in achieving a more detailed description of the scene and understanding of the spatial-relationship between different objects. In this paper, a deep architecture for road scene and indoor scene segmentation, SegNet, is applied in solving the scene recognition problem for the agricultural environment. The network is trained on an agriculture image dataset collected during field operation. The problem focuses on the segmentation of five classes of structures commonly found in the fields: vegetation, grass, ground, crop field and obstacles. We apply frequency balancing to address the challenge of class imbalance and transfer learning technique. The quantitative performance of the network is evaluated using pixel accuracy and intersection over union metrics. Moreover, we present an approach for an infield qualitative validation of the trained network.
Original languageEnglish
Title of host publicationProceedings of the 16th International Conference on Control, Automation, Robotics and Vision
PublisherIEEE
Publication date2021
Pages990-995
ISBN (Print)978-1-7281-7710-6
DOIs
Publication statusPublished - 2021
Event16th International Conference on Control, Automation, Robotics and Vision (ICARCV)
- Virtual event, Shenzhen, China
Duration: 13 Dec 202015 Dec 2020
https://icarcv.sg/

Conference

Conference16th International Conference on Control, Automation, Robotics and Vision (ICARCV)
LocationVirtual event
CountryChina
CityShenzhen
Period13/12/202015/12/2020
Internet address

Fingerprint Dive into the research topics of 'Towards Semantic Scene Segmentation for Autonomous Agricultural Vehicles'. Together they form a unique fingerprint.

Cite this