Gradient and Log-based Active Learning for Semantic Segmentation of Crop and Weed for Agricultural Robots

Rasha Sheikh, Andres Milioto, Philipp Lottes, Cyrill Stachniss, Maren Bennewitz, and Thomas Schultz
In proceedings of Int'l Conf. on Robotics and Automation (ICRA), 2020
 

Abstract

Annotated datasets are essential for supervised learning. However, annotating large datasets is a tedious and time-intensive task. This paper addresses active learning in the context of semantic segmentation with the goal of reducing the human labeling effort. Our application is agricultural robotics and we focus on the task of distinguishing between crop and weed plants from image data. A key challenge in this application is the transfer of an existing semantic segmentation CNN to a new field, in which growth stage, weeds, soil, and weather conditions differ. We propose a novel approach that, given a trained model on one field together with rough foreground segmentation, refines the network on a substantially different field providing an effective method of selecting samples to annotate for supporting the transfer. We evaluated our approach on two challenging datasets from the agricultural robotics domain and show that we achieve a higher accuracy with a smaller number of samples compared to random sampling as well as entropy based sampling, which consequently reduces the required human labeling effort.

Images

Download Paper

Download Paper

Additional Material

  • Video (MPEG-4 video, 21 MB)

Bibtex

@INPROCEEDINGS{Sheikh:ICRA20,
     author = {Sheikh, Rasha and Milioto, Andres and Lottes, Philipp and Stachniss, Cyrill and Bennewitz, Maren and
               Schultz, Thomas},
      title = {Gradient and Log-based Active Learning for Semantic Segmentation of Crop and Weed for Agricultural
               Robots},
  booktitle = {Int'l Conf. on Robotics and Automation (ICRA)},
       year = {2020},
   abstract = {Annotated datasets are essential for supervised learning. However, annotating large datasets is a
               tedious and time-intensive task. This paper addresses active learning in the context of semantic
               segmentation with the goal of reducing the human labeling effort. Our application is agricultural
               robotics and we focus on the task of distinguishing between crop and weed plants from image data. A
               key challenge in this application is the transfer of an existing semantic segmentation CNN to a new
               field, in which growth stage, weeds, soil, and weather conditions differ.
               We propose a novel approach that, given a trained model on one field together with rough foreground
               segmentation, refines the network on a substantially different field providing an effective method
               of selecting samples to annotate for supporting the transfer. We evaluated our approach on two
               challenging datasets from the agricultural robotics domain and show that we achieve a higher
               accuracy with a smaller number of samples compared to random sampling as well as entropy based
               sampling, which consequently reduces the required human labeling effort.}
}