Dynamic Object Removal from Unpaired Images for Agricultural Autonomous Robots

Hiroyasu Akada, Masaki Takahashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Recently, the demand for agricultural autonomous robots has been increasing. Using the technology of vision-based robotic environmental recognition, they can generally follow farmers to support their work activities, such as conveyance of the harvest. However, a major issue arises in that dynamic objects (including humans) often enter images that the robots rely on for environmental recognition tasks. These dynamic objects degrade the performance of image recognition considerably, resulting in collisions with crops or ridges when the robots are following the worker. To address the occlusion issue, generative adversarial network (GAN) solutions can be adopted as they feature a generative capability to reconstruct the area behind dynamic objects. However, precedented GAN methods basically presuppose paired image datasets to train their networks, which are difficult to prepare. Therefore, a method based on unpaired image datasets is desirable in real-world environments, such as a farm. For this purpose, we propose a new approach by integrating the state-of-the-art neural network architecture, CycleGAN, and Mask R CNN. Our system is trained with a human-tracking dataset collected by an agricultural autonomous robot in a farm. We evaluate the performance of our system both qualitatively and quantitatively for the task of human removal in images.

Original languageEnglish
Title of host publicationIntelligent Autonomous Systems 16 - Proceedings of the 16th International Conference IAS-16
EditorsMarcelo H. Ang Jr, Hajime Asama, Wei Lin, Shaohui Foong
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages13
ISBN (Print)9783030958916
Publication statusPublished - 2022
Event16th International Conference on Intelligent Autonomous Systems, IAS-16 2020 - Virtual, Online
Duration: 2021 Jun 222021 Jun 25

Publication series

NameLecture Notes in Networks and Systems
Volume412 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389


Conference16th International Conference on Intelligent Autonomous Systems, IAS-16 2020
CityVirtual, Online


  • Agricultural autonomous robot
  • CycleGAN
  • Dynamic object removal
  • Generative adversarial network

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications


Dive into the research topics of 'Dynamic Object Removal from Unpaired Images for Agricultural Autonomous Robots'. Together they form a unique fingerprint.

Cite this