Drone Inspection Specialist
Expert in drone-based infrastructure inspection with computer vision, thermal analysis, and 3D reconstruction for insurance, property assessment, and environmental monitoring.
Decision Tree: When to Use This Skill
User mentions drones/UAV?
├─ YES → Is it about inspection or assessment of something?
│ ├─ Fire detection, smoke, thermal hotspots → THIS SKILL
│ ├─ Roof damage, hail, shingles → THIS SKILL
│ ├─ Property/insurance assessment → THIS SKILL
│ ├─ 3D reconstruction for measurement → THIS SKILL
│ ├─ Wildfire risk, defensible space → THIS SKILL
│ └─ NO (flight control, navigation, general CV) → drone-cv-expert
└─ NO → Is it about fire/roof/property assessment without drones?
├─ YES → Still use THIS SKILL (methods apply)
└─ NO → Different skill needed
Core Competencies
Fire Detection & Wildfire Risk
- Multi-Modal Detection: RGB smoke + thermal hotspot fusion
- Precondition Assessment: NDVI, fuel load, vegetation density
- Defensible Space: CAL FIRE/NFPA 1144 compliance evaluation
- Progression Tracking: Spread rate, direction prediction
Roof & Structural Inspection
- Damage Detection: Cracks, missing shingles, wear, ponding
- Hail Analysis: Impact pattern recognition, size estimation
- Thermal Analysis: Moisture detection, insulation gaps, HVAC leaks
- Material Classification: Asphalt, metal, tile, slate identification
3D Reconstruction (Gaussian Splatting)
- Pipeline: Video → COLMAP SfM → 3DGS training → Web viewer
- Measurements: Roof area, damage dimensions, property bounds
- Change Detection: Before/after comparison for claims
Insurance & Reinsurance
- Claim Packaging: Documentation meeting industry standards
- Risk Modeling: Catastrophe models, loss distributions
- Precondition Data: Satellite + drone + ground integration
Anti-Patterns to Avoid
1. "Single-Sensor Dependence"
Wrong: Using only RGB for fire detection.
Right: Multi-modal fusion (RGB + thermal) for high-confidence alerts.
| Detection Source |
Confidence |
Action |
| Thermal fire only |
70% |
Alert + verify |
| RGB smoke only |
60% |
Alert + investigate |
| Thermal + RGB |
95% |
Confirmed fire |
2. "Ignoring Hail Pattern"
Wrong: Counting damage without analyzing spatial distribution.
Right: True hail damage has RANDOM distribution. Linear or clustered patterns indicate other causes (foot traffic, age).
3. "Thermal Temperature Trust"
Wrong: Using raw thermal values without calibration.
Right: Account for:
- Emissivity of materials (roof = 0.9-0.95)
- Atmospheric transmission (humidity, distance)
- Reflected temperature from surroundings
- Time of day (thermal lag)
4. "3DGS Frame Overload"
Wrong: Extracting every frame from drone video.
Right: Extract 2-3 fps with 80% overlap. More frames ≠ better reconstruction.
| Video FPS |
Extract Rate |
Result |
| 30 |
30 (all) |
Redundant, slow processing |
| 30 |
2-3 |
Optimal quality/speed |
| 30 |
0.5 |
Insufficient overlap |
5. "Insurance Claim Speculation"
Wrong: Estimating costs without material identification.
Right: Identify material → Apply correct cost matrix.
| Material |
Repair $/sqft |
Replace $/sqft |
| Asphalt shingle |
$5-10 |
$3-7 |
| Metal |
$10-15 |
$8-14 |
| Tile |
$12-20 |
$10-18 |
| Slate |
$20-40 |
$15-30 |
6. "Defensible Space Zone Confusion"
Wrong: Treating all vegetation equally regardless of distance.
Right: CAL FIRE zones have different requirements:
| Zone |
Distance |
Requirement |
| 0 |
0-5 ft |
Ember-resistant (no combustibles) |
| 1 |
5-30 ft |
Lean, clean, green (spaced trees) |
| 2 |
30-100 ft |
Reduced fuel (selective thinning) |
Data Collection Strategy
Satellite Data (Regional Context)
- Sentinel-2: 10m resolution, NDVI, fuel moisture (SWIR bands)
- Landsat-8: 30m resolution, historical baseline, thermal band
- Planet: 3m resolution daily, change detection
- Application: Regional risk mapping, before/after events
Drone Data (Property Detail)
- RGB Mapping: 2-5cm GSD, orthomosaic, 3D model
- Thermal Survey: Moisture detection, heat signatures
- Close Inspection: Damage documentation, detail photos
- Application: Individual property assessment
Ground Truth
- Slope Measurement: GPS transects for topographic risk
- Soil Sampling: Moisture content for fire risk
- Material Verification: Confirm roof type
- Application: Calibration and validation
Quick Reference Tables
Fire Detection Confidence Levels
| Signal Combination |
Confidence |
Alert Priority |
| Thermal >150°C + Smoke |
95% |
CRITICAL |
| Thermal fire model |
80% |
HIGH |
| Hotspot >80°C |
70% |
MEDIUM |
| Smoke only |
60% |
MEDIUM |
| Hotspot 60-80°C |
50% |
LOW |
Roof Damage Severity
| Type |
Low |
Medium |
High |
Critical |
| Missing shingle |
- |
- |
Always |
- |
| Crack |
<1" |
1-3" |
>3" |
Multiple |
| Granule loss |
<10% |
10-30% |
>30% |
- |
| Ponding |
- |
Small |
Large |
Active leak |
Wildfire Risk Factors (Weighted)
| Factor |
Weight |
High Risk Indicators |
| Defensible space |
20% |
Non-compliant zones |
| Vegetation density |
20% |
NDVI >0.6, high fuel load |
| Slope |
15% |
>30% grade |
| Roof material |
10% |
Wood shake, Class C |
| Structure spacing |
10% |
<30ft between buildings |
| Access/egress |
10% |
Single road, narrow |
3DGS Quality Settings
| Quality Level |
Iterations |
Time |
Use Case |
| Preview |
7K |
5 min |
Quick check |
| Standard |
30K |
30 min |
General use |
| High |
50K |
60 min |
Documentation |
| Inspection |
100K |
3 hrs |
Damage measurement |
Reference Files
Detailed implementations in references/:
fire-detection.md - Multi-modal fire detection, thermal cameras, progression trackingroof-inspection.md - Damage detection, thermal analysis, material classificationinsurance-risk-assessment.md - Hail damage, wildfire risk, catastrophe modeling, reinsurancegaussian-splatting-3d.md - COLMAP pipeline, 3DGS training, inspection measurements
Integration Points
- drone-cv-expert: Flight control, navigation, general CV algorithms
- metal-shader-expert: GPU-accelerated 3DGS rendering
- collage-layout-expert: Visual report composition
- clip-aware-embeddings: Material/damage classification assistance
Insurance Workflow
1. Pre-Event Assessment (Underwriting)
├─ Satellite: Regional risk context
├─ Drone: Property-level risk factors
└─ Output: Risk score, premium factors
2. Post-Event Inspection (Claims)
├─ Drone survey: Damage documentation
├─ 3DGS: Measurements, change detection
└─ Output: Claim package, cost estimate
3. Portfolio Risk (Reinsurance)
├─ Aggregate: TIV, loss curves
├─ Model: AAL, PML, concentration
└─ Output: Treaty pricing, structure
Key Principle: Inspection accuracy depends on multi-source data fusion. Single-sensor assessments miss critical context. Always correlate drone findings with satellite baseline and weather data for defensible conclusions.
1---2name: drone-inspection-specialist-23description: Advanced CV for infrastructure inspection including forest fire detection, wildfire precondition assessment, roof inspection, hail damage analysis, thermal imaging, and 3D Gaussian Splatting reconstruction. Expert in multi-modal detection, insurance risk modeling, and reinsurance data pipelines. Activate on "fire detection", "wildfire risk", "roof inspection", "hail damage", "thermal analysis", "Gaussian Splatting", "3DGS", "insurance inspection", "defensible space", "property assessment", "catastrophe modeling", "NDVI", "fuel load". NOT for general drone flight control, SLAM, path planning, or sensor fusion (use drone-cv-expert), GPU shader development (use metal-shader-expert), or generic object detection without inspection context (use clip-aware-embeddings).4---56# Drone Inspection Specialist78Expert in drone-based infrastructure inspection with computer vision, thermal analysis, and 3D reconstruction for insurance, property assessment, and environmental monitoring.910## Decision Tree: When to Use This Skill1112```13User mentions drones/UAV?14├─ YES → Is it about inspection or assessment of something?15│ ├─ Fire detection, smoke, thermal hotspots → THIS SKILL16│ ├─ Roof damage, hail, shingles → THIS SKILL17│ ├─ Property/insurance assessment → THIS SKILL18│ ├─ 3D reconstruction for measurement → THIS SKILL19│ ├─ Wildfire risk, defensible space → THIS SKILL20│ └─ NO (flight control, navigation, general CV) → drone-cv-expert21└─ NO → Is it about fire/roof/property assessment without drones?22 ├─ YES → Still use THIS SKILL (methods apply)23 └─ NO → Different skill needed24```2526## Core Competencies2728### Fire Detection & Wildfire Risk29- **Multi-Modal Detection**: RGB smoke + thermal hotspot fusion30- **Precondition Assessment**: NDVI, fuel load, vegetation density31- **Defensible Space**: CAL FIRE/NFPA 1144 compliance evaluation32- **Progression Tracking**: Spread rate, direction prediction3334### Roof & Structural Inspection35- **Damage Detection**: Cracks, missing shingles, wear, ponding36- **Hail Analysis**: Impact pattern recognition, size estimation37- **Thermal Analysis**: Moisture detection, insulation gaps, HVAC leaks38- **Material Classification**: Asphalt, metal, tile, slate identification3940### 3D Reconstruction (Gaussian Splatting)41- **Pipeline**: Video → COLMAP SfM → 3DGS training → Web viewer42- **Measurements**: Roof area, damage dimensions, property bounds43- **Change Detection**: Before/after comparison for claims4445### Insurance & Reinsurance46- **Claim Packaging**: Documentation meeting industry standards47- **Risk Modeling**: Catastrophe models, loss distributions48- **Precondition Data**: Satellite + drone + ground integration4950## Anti-Patterns to Avoid5152### 1. "Single-Sensor Dependence"53**Wrong**: Using only RGB for fire detection.54**Right**: Multi-modal fusion (RGB + thermal) for high-confidence alerts.55| Detection Source | Confidence | Action |56|------------------|------------|--------|57| Thermal fire only | 70% | Alert + verify |58| RGB smoke only | 60% | Alert + investigate |59| Thermal + RGB | 95% | Confirmed fire |6061### 2. "Ignoring Hail Pattern"62**Wrong**: Counting damage without analyzing spatial distribution.63**Right**: True hail damage has RANDOM distribution. Linear or clustered patterns indicate other causes (foot traffic, age).6465### 3. "Thermal Temperature Trust"66**Wrong**: Using raw thermal values without calibration.67**Right**: Account for:68- Emissivity of materials (roof = 0.9-0.95)69- Atmospheric transmission (humidity, distance)70- Reflected temperature from surroundings71- Time of day (thermal lag)7273### 4. "3DGS Frame Overload"74**Wrong**: Extracting every frame from drone video.75**Right**: Extract 2-3 fps with 80% overlap. More frames ≠ better reconstruction.76| Video FPS | Extract Rate | Result |77|-----------|--------------|--------|78| 30 | 30 (all) | Redundant, slow processing |79| 30 | 2-3 | Optimal quality/speed |80| 30 | 0.5 | Insufficient overlap |8182### 5. "Insurance Claim Speculation"83**Wrong**: Estimating costs without material identification.84**Right**: Identify material → Apply correct cost matrix.85| Material | Repair $/sqft | Replace $/sqft |86|----------|--------------|----------------|87| Asphalt shingle | $5-10 | $3-7 |88| Metal | $10-15 | $8-14 |89| Tile | $12-20 | $10-18 |90| Slate | $20-40 | $15-30 |9192### 6. "Defensible Space Zone Confusion"93**Wrong**: Treating all vegetation equally regardless of distance.94**Right**: CAL FIRE zones have different requirements:95| Zone | Distance | Requirement |96|------|----------|-------------|97| 0 | 0-5 ft | Ember-resistant (no combustibles) |98| 1 | 5-30 ft | Lean, clean, green (spaced trees) |99| 2 | 30-100 ft | Reduced fuel (selective thinning) |100101## Data Collection Strategy102103### Satellite Data (Regional Context)104- **Sentinel-2**: 10m resolution, NDVI, fuel moisture (SWIR bands)105- **Landsat-8**: 30m resolution, historical baseline, thermal band106- **Planet**: 3m resolution daily, change detection107- **Application**: Regional risk mapping, before/after events108109### Drone Data (Property Detail)110- **RGB Mapping**: 2-5cm GSD, orthomosaic, 3D model111- **Thermal Survey**: Moisture detection, heat signatures112- **Close Inspection**: Damage documentation, detail photos113- **Application**: Individual property assessment114115### Ground Truth116- **Slope Measurement**: GPS transects for topographic risk117- **Soil Sampling**: Moisture content for fire risk118- **Material Verification**: Confirm roof type119- **Application**: Calibration and validation120121## Quick Reference Tables122123### Fire Detection Confidence Levels124| Signal Combination | Confidence | Alert Priority |125|-------------------|------------|----------------|126| Thermal >150°C + Smoke | 95% | CRITICAL |127| Thermal fire model | 80% | HIGH |128| Hotspot >80°C | 70% | MEDIUM |129| Smoke only | 60% | MEDIUM |130| Hotspot 60-80°C | 50% | LOW |131132### Roof Damage Severity133| Type | Low | Medium | High | Critical |134|------|-----|--------|------|----------|135| Missing shingle | - | - | Always | - |136| Crack | <1" | 1-3" | >3" | Multiple |137| Granule loss | <10% | 10-30% | >30% | - |138| Ponding | - | Small | Large | Active leak |139140### Wildfire Risk Factors (Weighted)141| Factor | Weight | High Risk Indicators |142|--------|--------|---------------------|143| Defensible space | 20% | Non-compliant zones |144| Vegetation density | 20% | NDVI >0.6, high fuel load |145| Slope | 15% | >30% grade |146| Roof material | 10% | Wood shake, Class C |147| Structure spacing | 10% | <30ft between buildings |148| Access/egress | 10% | Single road, narrow |149150### 3DGS Quality Settings151| Quality Level | Iterations | Time | Use Case |152|---------------|------------|------|----------|153| Preview | 7K | 5 min | Quick check |154| Standard | 30K | 30 min | General use |155| High | 50K | 60 min | Documentation |156| Inspection | 100K | 3 hrs | Damage measurement |157158## Reference Files159160Detailed implementations in `references/`:161- `fire-detection.md` - Multi-modal fire detection, thermal cameras, progression tracking162- `roof-inspection.md` - Damage detection, thermal analysis, material classification163- `insurance-risk-assessment.md` - Hail damage, wildfire risk, catastrophe modeling, reinsurance164- `gaussian-splatting-3d.md` - COLMAP pipeline, 3DGS training, inspection measurements165166## Integration Points167168- **drone-cv-expert**: Flight control, navigation, general CV algorithms169- **metal-shader-expert**: GPU-accelerated 3DGS rendering170- **collage-layout-expert**: Visual report composition171- **clip-aware-embeddings**: Material/damage classification assistance172173## Insurance Workflow174175```1761. Pre-Event Assessment (Underwriting)177 ├─ Satellite: Regional risk context178 ├─ Drone: Property-level risk factors179 └─ Output: Risk score, premium factors1801812. Post-Event Inspection (Claims)182 ├─ Drone survey: Damage documentation183 ├─ 3DGS: Measurements, change detection184 └─ Output: Claim package, cost estimate1851863. Portfolio Risk (Reinsurance)187 ├─ Aggregate: TIV, loss curves188 ├─ Model: AAL, PML, concentration189 └─ Output: Treaty pricing, structure190```191192---193194**Key Principle**: Inspection accuracy depends on multi-source data fusion. Single-sensor assessments miss critical context. Always correlate drone findings with satellite baseline and weather data for defensible conclusions.
curiositech