In the video presentation below, a group of deep learning researchers study the problem of perceiving forest or mountain trails from a single monocular image acquired from the viewpoint of a robot traveling on the trail itself. Previous literature focused on trail segmentation, and used low-level features such as image saliency or appearance contrast; the team proposes a different approach based on a Deep Neural Network used as a supervised image classifier. By operating on the whole image at once, the system outputs the main direction of the trail compared to the viewing direction. Qualitative and quantitative results computed on a large real-world data set (which is provided for download) show that the approach outperforms alternatives, and yields an accuracy comparable to the accuracy of humans that are tested on the same image classification task. Preliminary results on using this information for quadrotor control in unseen trails are reported. This is believed to be the first paper that describes an approach to perceive forest trials which is demonstrated on a quadrotor micro aerial vehicle.
Authors: A. Giusti, J. Guzzi, D.C. Ciresan, F. He, J.P. Rodr�guez, F. Fontana, M. Faessler, C. Forster, J. Schmidhuber, G. Di Caro, D. Scaramuzza, L.M. Gambardella
A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots, IEEE Robotics and Automation Letters (RA-L), pages 661 – 667, 2016
Data sets: http://people.idsia.ch/~giusti/forest/web/
Affiliations:
Dalle Molle Institute for Artificial Intelligence (IDSIA), USI/SUPSI, Lugano Switzerland. Robotics and Perception Group, University of Zurich, Switzerland.
Sign up for the free insideBIGDATA newsletter.
Can i get the code to run the simulation?