Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture

@article{Steen2016UsingDL,
  title={Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture},
  author={Kim Arild Steen and Peter Christiansen and Henrik Karstoft and Rasmus N. J\orgensen},
  journal={J. Imaging},
  year={2016},
  volume={2},
  pages={6}
}
In this paper, an algorithm for obstacle detection in agricultural fields is presented. The algorithm is based on an existing deep convolutional neural net, which is fine-tuned for detection of a specific obstacle. In ISO/DIS 18497, which is an emerging standard for safety of highly automated machinery in agriculture, a barrel-shaped obstacle is defined as the obstacle which should be robustly detected to comply with the standard. We show that our fine-tuned deep convolutional net is capable of… CONTINUE READING

From This Paper

Results and topics from this paper.

Key Quantitative Results

  • We show that our fine-tuned deep convolutional net is capable of detecting this obstacle with a precision of 99.9% in row crops and 90.8% in grass mowing, while simultaneously not detecting people and other very distinct obstacles in the image frame.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Advanced sensor platform for human detection and protection in autonomous farming

P. Christiansen, M. Hansen, K. Steen, H. Karstoft, R. Jørgensen
In Precision Agriculture’15; Wageningen Academic Publishers: Wageningen, The Netherlands, • 2015
View 2 Excerpts

Fully Convolutional Networks for Semantic Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015

ImageNet Large Scale Visual Recognition Challenge

International Journal of Computer Vision • 2015
View 1 Excerpt

You only look once: Unified, real-time object detection

J. Redmon, S. Divvala, R. Girshick, A. Farhadi
Available online: http://arxiv.org/pdf/1506.02640v4.pdf (accessed on • 2015

Similar Papers

Loading similar papers…