The open mine terrain and geography are captured through airborne systems as aerial images and is analyzed manually to provide valuable insights on various geographical features. This process is effort-intensive and error-prone with a long lead time. To ensure automation of the entire value chain and to provide safety to the workforce, there is a need for acquiring spatial data remotely and more frequently, and integrate the data with systems automating the ingestion, analysis and publication processes.
The client was looking for a partner with strong consulting and execution expertise around deep learning and computer vision, who could help achieve the defined business goals.
Key Challenges
- High frequency of data capture, complex aerial imageries and large data sizes
- Producing road feature data sets of active mining areas
- Training computer vision and deep learning algorithms to extract features at various altitudes
Ready to experience?
TALK TO EXPERTS
The Solution
Deep learning algorithms used on the objects at various altitudes
- Deep learning based solution to demarcate road centerlines, road edges and boundary edges of active mining areas using elevation and imagery data, and GPS snippet data for coal mine site.
- Techniques included identifying and segregating features based on different depth or elevations and stitching together multiple images to identify objects
Deep learning algorithms for aerial imagery
- Demarcate road centerlines, road edges and boundary edges of active mining areas
- Automating the entire process using advanced deep learning techniques
Benefits
Extraction of road feature data sets that are enablers for analysis of a range of safety-critical controls to produce:
Road centrelines
Road edges
Pit crest and toe (active mining) area perimeter edges
The complete process was automated through image analytic techniques which helps in reducing the execution time by 75% for a typical 1000 Km radius area
