“If the ignition is detected immediately, it can be extinguished with little expended resources or loss of life.” – WUI Operational Requirements and Capability Analysis – Report of Findings, US government1.

Fast & Accurate Dual-Sensor
Our LWIR detection is fast (as small as 2 m2 flame at 5 km).
Accurately detect fire occurrence by dual-detection (visual & infrared)
Our patented technology accurately determines fire location.
Work reliably in tough environments (dark, light polluted, hazy, windy & hilly).

Automatic & Efficient AI Recognition
Always-on Automatic AI detection. No delay nor tiredness.
Self-improving machine learning system analyses raw images on the edge
Large coverage (70k Ha per robot) and minimal manual operation.
More manpower-efficient, energy-efficient, and carbon-friendly than watchtowers and aerial fire patrol.

Intuitive & Versatile Management Platform
Easy-to-use GUI with 2D/3D maps. Supports cross platforms.
Situational awareness with real-time video & panoramic image.
Support visualization of 3rd party data via standard API.
Timestamped GIS-referenced fire records for post-event forensic and risk mitigation planning.
Figure 1: InsightFD Key Customer Benefits
2020 marks the 10th anniversary of InsightFD early wildfire detection system! Insight Robotics team was a market pioneer. We turned the idea of using visual and thermal cameras to detect wildland fire ignition to a working prototype in 2011. After years of working closely with fire crews in different countries, we converted customer inputs to product features. We reinvented the watchtower-replacement CCTV-based operation room tool to AI-based Early Wildfire Detection System. It is Fast, Accurate, Automatic, Resource-Efficient, Intuitive and Versatile (Figure 1).
Fast & Accurate
The purpose-built Dual-Sensor system in InsightFD (Figure 2) enables Fast and Accurate wildfire/forest fire/wildland fire/bushfire detection.
The traditional visual fire detection relies on operators to identify smoke. Environment visibility and light-to-sight may restrict operators from seeing smoke! Furthermore, due to the variability of shape, motion, colors, and patterns of smoke and flames, many existing visual fire detection approaches are susceptible to false alarms.


Figure 2: InsightFD 3 (left) and 1 (right) early wildfire detection systems use both visual and infrared cameras
Heat comes before smoke! We can’t beat physics.
By using both the visual and infrared cameras, the dual-sensor design overcomes visibility, ambient light, darkness, and false alarm challenges!

We use LWIR (Long Wave Infrared) sensor because
- LWIR band is better than other IR bands for imaging through smoke or aerosols.
- LWIR sensors provide more consistent images between daytime and nighttime.
- Our LWIR sensor is able to indicate the location and energy level of heat radiation emitted. This offers two distinct advantages: the scene becomes independent of lighting conditions and the sensor can easily identify any type of heat-generating body.

Figure 4: LWIR imaging (left) can better identify distant flame and heat source than visual imaging.
Below are the unique customer benefits of our Dual-Sensor design:
- Our LWIR detection is fast (as small as 2m2 flame at 5km distance). Heat comes before smoke! Flames and hot objects are best perceptible and less disturbed in the LWIR spectral range. InsightFD can see small fire far away. Whereas civilian satellites can only detect big fire several hectares (>10k m2) in size.
- Accurately detect fire occurrence by using both infrared and visual image detections. Dual-sensor and dual-detection achieve high true positive alarm rates.
- Our patented technology2 automatically determines precise fire locations. Our high pixel density LWIR sensor is mapped to the DEM (Digital Elevation Model) of the AOI (Area of interest) monitored by InsightFD. InsightFD can pinpoint the fire location up to +/- 50m! Whereas many other wildfire detections can only achieve 1km location accuracy.
- InsightFD works reliably in challenging environments (dark, light polluted, hazy, windy and hilly). LWIR imaging sensors image emitted light, not reflected light. InsightFD overcomes the reflected light limitation inherited in visual fire detection.
- Visual sensor catching images for smoke detection. Our home-grown dual-sensor system provides uncompressed raw HD images, enabling error-free image recognition. Whereas other wildfire detections use off-the-shelf cameras that offer lossy compressed images only.
- Robust IP66 weather resistance equipment. The operation temperature of -20c to +50c.

Figure 5: Our patent maps LWIR sensor pixel to DEM and can determine the precise location of fire
“Need real-time and continuous identification of heat sources and smoke to detect ignition location.” US government
1.
Let’s talk Automation and Efficiency next time. Please download our InsightFD brochure if you want to learn more about our product.
Reference: