Landslide Prediction and Analysis from Images
The beginning of 2018 was marked by unusually heavy rain falls which caused a lot of landslides in and around Pittsburgh. Fortunately, no person was insured, however, houses were destroyed and several roads had to be closed, some for months to be completely reconstructed. In this proposal we want to develop and test an inexpensive early warning and post-event analysis system. The basic idea is to collect images of the hill sides on a regular basis and analyze these images with computer vision algorithms to identify precursor events. Our group has already shown that such a data collection can be done efficiently with smartphones mounted in vehicles that drive around the area on a regular basis. In fact, this data collection system is part of a CMU spin-off that inspects road surfaces (RoadBotics, Christoph Mertz is co-founder).
From this earlier road monitoring research, we have GPS tagged images as far back as 2012. Of particular interest are images we collected about once a month around the West-End-Circle from where one can view a recent landslide. We want to analyze these images to look for changes in the 3D shape of the hill side, change of color of the surface, unusual amount of dirt on the road or any other indication of impending problems. Additionally, we want to compare those past images with current ones to see if we can get any information that is useful in the post-event analysis. E.g. one can create a 3D model of the hill side from the images and compare the geometry before and after the slide to determine how much dirt moved and where it ended up.
This project is a proof-of-concept development of an early warning and post event analysis system for landslides. A preliminary study and a meeting with the City of Pittsburgh is already planned for this Summer. We will collect new GPS tagged images and make use of images collected in the past. We will develop methods based on computer vision techniques to find indicators of impending problems in these images or information that is relevant to post-event analysis. Landslide experts and effected parties like Pittsburgh will give input and feedback to determine the relevance of the results. The goal of the project is to demonstrate the feasibility of a practical system. The PI of the project is Christoph Mertz (RI) with Amit Acharya (faculty at ECC) as adviser.
Project Update (April 2019)
The PIs continue to work with the Allegheny County to introduce the project, get feedback and receive locations that are particularly interesting for landslide research. The team has visited two sites and made measurements, i.e. took many pictures and created 3D models of the area. At the same time, the team has started to develop simulation models in ANSYS to make slope stability analysis. These models will help the team understand the static and dynamics of landslides and correlate the observed indicators with the underlying ground stability.
The team will continue to repeat measurements of the areas before investigating changes. The ANSYS model will be applied to one of the areas and we will test if the calculated instabilities correlates with the observations.
Publications: Asish Yadav Madala, “MECHANICAL AND COMPUTER VISION MODELING OF SOIL SLOPES”, semester report
City of Pittsburgh
Project Lead, Principal Project Scientist, Robotics Institute
Faculty, Civil & Environmental Engineering