DAEMLABS
We built an autonomous drone intelligence platform that generates aerial maps, detects potential landmines and hazardous objects using AI-powered computer vision, and computes safe navigation routes using pathfinding algorithms — enabling faster and safer terrain assessment in high-risk environments.
Landmine-contaminated areas remain one of the most dangerous challenges in post-conflict and military environments. Traditional surveying methods are slow, expensive, and place human operators directly in harm's way. Existing drone solutions often stop at image collection, leaving analysts to manually inspect footage and identify threats. We needed a system capable of automatically mapping terrain, detecting hazards, and generating safe navigation paths from aerial imagery.
Built a modular drone intelligence pipeline combining aerial image stitching, YOLO-based object detection enhanced with SAHI sliced inference, obstacle-aware A* path planning, and a voice-command control system. The platform converts drone footage into high-resolution orthomosaic maps, identifies potential hazards across large environments, applies configurable safety margins, and computes optimal routes that avoid detected danger zones. A speech-driven command pipeline enables hands-free mission control with confirmation-based execution for operational safety.
Generated high-resolution aerial maps from multiple drone video streams
Detected small hazardous objects reliably using YOLO + SAHI sliced inference
Improved detection accuracy on large stitched maps without downscaling
Computed safe navigation routes automatically using A* path planning
Applied configurable safety buffers around detected hazards
Enabled voice-controlled mission operations with command confirmation
Reduced manual terrain analysis and route planning effort
Created a fully modular platform for mapping, detection, navigation, and control