Automatic Muck Pile Characterization from UAV Images

Fabian Schenk, Alexander Tscharf, Gerhard Mayer, Friedrich Fraundorfer

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


In open pit mining it is essential for processing and production scheduling to receive fast and accurate information about the fragmentation of a muck pile after a blast. In this work, we propose a novel machine-learning method that characterizes the muck pile directly from UAV images. In contrast to state-of-the-art approaches, that require heavy user interaction, expert knowledge and careful threshold settings, our method works fully automatically. We compute segmentation masks, bounding boxes and confidence values for each individual fragment in the muck pile on multiple scales to generate a globally consistent segmentation. Additionally, we recorded lab and real-world images to generate our own dataset for training the network. Our method shows very promising quantitative and qualitative results in all our experiments. Further, the results clearly indicate that our method generalizes to previously unseen data.
Original languageEnglish
Title of host publicationISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Number of pages8
Publication statusPublished - 2019
EventISPRS Geospatial Week: Unmanned Aerial Vehicles in Geomatics (UAVg) 2019 - University of Twente, Enschede, Netherlands
Duration: 10 Jun 201914 Jun 2019


ConferenceISPRS Geospatial Week
Internet address


  • UAVs
  • Semantic Segmentation
  • Mining
  • Machine learning
  • Convolutional neural networks


Dive into the research topics of 'Automatic Muck Pile Characterization from UAV Images'. Together they form a unique fingerprint.

Cite this