Agent skill · research science · aradotso
netryx-street-level-geolocation
netryx-street-level-geolocation — an agent skill for coding agents.
Why this skill is useful
Adds a complete geolocation pipeline with executable scripts for indexing and searching street-level photos that aren't available in public documentation.
What it needs
Requires git, pip, python3 installed locally. Requires gemini account access. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash git clone https://github.com/sparkyniner/Netryx-OpenSource-Next-Gen-Street-Level-Geolocation.git cd Netryx-OpenSource-Next-Gen-Street-Level-Geolocation python3 -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt pip install git+https://github.com/cvg/LightGlue.git # required pip install kornia # optional: Ultra Mode (LoFTR) bash export GEMINIAPIKEY="yourkeyhere" # from https://aistudio.google.com bash brew install python-tk@3.11 # match your Python version netryx/ ├── testsuper.py # Main GUI application (entry point) ├── cosplaceutils.py # CosPlace model loading + descriptor extraction ├── buildindex.py # Standalone high-performance index builder ├── requirements.txt ├── cosplaceparts/ # Raw .npz embedding chunks (written during indexing) └── index/ ├── cosplacedescriptors.npy # All 512-dim global descriptors └── metadata.npz # lat/lon, heading, panoid per descriptor bash python testsuper.py bash python buildindex.py Query image → 512-dim CosPlace descriptor flipped image → 512-dim descriptor → Cosine similarity against index (single matrix multiply, <1s) → Haversine radius filter → Top 500–1000 candidates For each candidate: Download Street View panorama (8 tiles, stitched) → Rectilinear crop at indexed heading → Multi-FOV crops: 70°, 90°, 110° → ALIKED (CUDA) or DISK (MPS/CPU) keypoint extraction → LightGlue deep feature matching vs query keypoints → RANSAC geometric verification → inlier count Best match = highest inlier count Processes 300–500 candidates in 2–5 minutes Top 15 candidates: → Heading refinement: ±45° at 15° steps, 3 FOVs → Spatial consensus: cluster into 50m cells → Confidence scoring: clustering strength + uniqueness ratio → Final GPS coordinates LoFTR detector-free dense matching (handles blur/low-contrast) Descriptor hopping: re-search index using matched panorama's descriptor Neighborhood expansion: search all panoramas within 100m of best match python cosplaceutils.py exposes model loadin …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/netryx-street-level-geolocation