$873 raised out of $155,009
Overview
Concept

A FREE app that detects wildfires near your home, alerts you of nearby wildfires, helps you to report wildfire easily by maps clicks

Story

What you can get from ReportFires? 

  • to help you to fight or flight, respond ahead of wildfire
  • to protect your family and community from nearby wildfires
  • to alert others of wildfires in the vicinity  

What is ReportFires? It is a FREE AI wildfire detection app. It can

  • alerts you of nearby wildfire reported by other users
  • detects wildfire near your home using Machine Learning image detection
  • helps you report wildfire location easily by map clicks

ReportFires will protect you, your family, and your community from wildfires. No matter you’re running in countryside trails in the morning, working from home in the afternoon, or watching evening TV with the family, ReportFires will alert you of nearby wildfires and allow you to take timely action! Wildfire can spread at 6 miles (10km) per hour uphill! Early alerts can help you to get your family in the car and evacuate on time, so every second counts!

ReportFires app notification
Click notification will show wildfire location map

If you see a wildfire, you can click the wildfire location on the map in ReportFires and report it. This location will be sent to the cloud servers, shared with other users nearby, as well as the local authority/wildfire service organization. You will help alert all stakeholders at once and they can react promptly! 

Report wildfire quickly by map clicks

No more sleepless nights because you are worried about wildfires ignited by lightning, broken transmission lines, or other human activity! You can put your iPhone on a tripod, connect it to a power supply, point it to the wildfire-prone area, and use ReportFires in Detect mode. It brings you peace of mind.

Put your iPhone on a tripod and point it to wildfire-prone forest. Source: clipchamp.com

ReportFires app detects wildfire smoke by analyzing live images captured by the iPhone [1] rear camera. ReportFires uses Core ML APIs to run AI Smoke Detection on iPhone.

The below video demonstrates how the ReportFires app detects wildfire. ReportFires app is analyzing, every 6 seconds, the timelapse video of the wildfires growing southwest of Jasper Ridge over by the Santa Cruz Mountains, California, 18-Aug-2020. (Video source from Standford Jasper Ridge BP.) ReportFires app bounds the wildfire smokes detected and make sound alerts.  

ReportFires will detect wildfires and their smoke 24/7, identify their approximate locations and share the information with the ReportFires community. All these are done automatically! You can use your idle iPhone to protect you and your neighbors from wildfires!

ReportFires can detect smoke and estimate the wildfire location

ReporfFires will sound to alert you when it detects wildfire.  If you are a registered user and you have a spare iPhone, you can use the spare iPhone to detect wildfire and ReportFires will send to your current iPhone alert of wildfire detected by the spare iPhone. You can protect your cat at home when you’re in the office! More than one house? A registered user can use multiple iPhones to detect wildfire and receive alerts from them.

A registered user can use multiple iPhones to detect wildfire and receive alerts from them

ReportFires is built on top of InsightFD technologies. InsightFD is the market-leading early wildfire detection solution. InsightFD can detect wildfire at 9 miles (15 km), while ReportFires can detect wildfire as far as 1.5 miles (2.4km) away [2].

ReportFires app uses Machine Learning to detect smoke
InsightFD Early Wildfire Detection System vs ReportFires app

Recent researches in the US and Australia show early detection is the most useful technology to fight wildfire.  The adoption of early detection solutions is increasing. 

InsightFD in Thailand

Hundreds of InsightFD robots are now protecting national parks, forests, public infrastructure and resorts in Asia, Europe, Central and South America.

InsightFD in Portugal

We build this app to help you and everyone to mitigate wildfire risks and damages. We will win as a team!

“The problem is bigger than any one of us, but it is not bigger than all of us!”  said New York Governor Andrew Cuomo.

 Why did we build ReportFires?

We built it because we want to help.

The Australia mega-bushfire in late 2019 was devastating. 27m acres (11m hectares) of bush, forest, and parks across Australia were burned, bigger than Portugal, about the size of Tennessee. 1 billion animals died in this tragedy, and at least 33 people have been killed.

2019 Mega-bushfire in Australia. Source: Eden Hills Country Fire Service’s Facebook page

All the images and videos are heartbreaking. We felt and feel the pain. We hope we would help.

The coronavirus outbreak has postponed new InsightFD deployments. We don’t know when the pandemic will end, but we know climate change will continue to bring devastating forest fires. It will be disastrous if the double whammy of coronavirus and wildfire strike at the same time! Amid the new normal of social distancing, we want to provide the means to mitigate wildfire risks and damages even if more InsightFD deployments are postponed.

An InsightFD deployment was delayed by 3 months due to social distancing

What can we do to help most people?

Under our market-leading InsightFD architecture, we develop ReportFires, a wildfire detection app that can be run from smartphones. No need to buy or install any extra hardware. And we will offer the app for FREE.

Protect your family & community. Fight or flight before it’s too late. Source: Wikimedia Commons

InsightFD protects forests, lives, and communities from wildfires. ReportFires app helps people to get early alerts of nearby wildfires and to take timely action to save lives.

“And a second is like it: You shall love your neighbor as yourself.” Matthew 22:39

 How does ReportFires work?

InsightFD is the most popular automatic early wildfire detection solution. 

Customer Benefits of InsightFD Early Wildfire Detection System
  • Data capturing: InsightFD robot is a dual-sensor system that detects blackbody radiation and visual signals of smoke. A network of robots is carefully positioned and calibrated to monitor a forest area in each deployment based on the forest topography. Each robot will rotate and tilt 24/7 to optimize its monitoring coverage. InsightFD robot can detect wildfire within a range of 9 miles (15km).
  • Detection: AI-Engine edge computer, which attached to each InsightFD robot, will process the captured thermal and visual images. Edge computing reduces data transmission between sensors and the centralized management system. The expert system and the RoboticsCats AI Smoke Detection will analyze the images to detect wildfires. The edge computer calculates the fire size and location, and sends the information and images to the management system.
  • Alert and Reporting: Insight Globe (IG) management system is centralized control and data repository of the whole system. It collects detected wildfire information from each AI-Engine. IG processes the information, performs advanced data analytics, and provides visual/sound/email alerts to IG users. IG visualizes the wildfire locations in 2D and 3D maps. IG users can control and move robots to capture real-time video. IG users review wildfire locations and situational information, develop firefighting plans, and arrange firefighters and suppression resources to control wildfires. IG supports user access via standard web browsers and Insight Globe Mobile app.
The system architecture of InsightFD Early Wildfire Detection System

With the advancement in consumer technologies, nowadays iPhones are powerful to do complex parallel computations. iPhone 5S and later models support iOS 11 and Core ML, the Machine Learning framework developed by Apple. Core ML models run strictly on the user’s device and remove any need for a network connection, keeping app responsive and users’ data private. Core ML allows us to do three things:

  • real-time predictions of live images on the device
  • run application without a network connection. It is important since Internet connectivity is not always available in WUI (Wildland-Urban-Interface)
  • the image data never leaves the device for detection purposes. User privacy is our top priority.
Apple Core ML integrates Machine Learning into apps. Source: apple.com

Referencing the InsightFD architecture, ReportFires uses the iPhone to play the role of InsightFD robot and edge computer. Users can use ReportFires app to locate wildfire manually or to detect wildfire smoke automatically. The wildfire information will be shared with the public.

  • Data capturing: iPhone rear camera takes images of the nearby forest. ReportFires app provides visual aims to help the user to position the iPhone to optimize its viewing angle and detection coverage. The higher the vertical distance between the iPhone and treetops, the larger the wildfire smoke detection range. An iPhone at 1500-ft (500m) altitude can detect wildfire smoke about 1.5 miles (2.4km) away from it.
  • Detection: ReportFires app is a stateful wildfire smoke detection software program. It includes a customized iOS version of the RoboticsCats AI Smoke Detection system. The AI algorithm analyses images at regular intervals. ReportFires app does detection on edge to minimize data transmission between the iPhone and the centralized backend management system. ReportFires will track the iPhone GPS location, altitude, camera heading direction, and tilt angle. The AI detection algorithm is stateful to reduce false positives. When the ReportFires app detects wildfire smoke, it will estimate the 2D real-world locations of the wildfires. ReportFires app will send the detected wildfire information and images to ReportFires backend system running in the cloud. 
  • Alert and Reporting: ReportFire will generate a sound alert when it detects smoke. The ReportFires backend system will send wildfire alert notifications to those users who are within 6-mile (10km) distance from the wildfires reported or detected by the app. The corresponding firefighting authority will receive the wildfire alerts too and can review, verify, and dismiss them, using the ReportFires mobile app or web app. The authority formulates the firefighting plan. Both ReportFires users and firefighting authority can take timely actions based on the information provided by the ReportFires app.  
The system architecture of ReportFires app

The customized iOS version of our RoboticsCats AI Smoke Detection System is running on Core ML. It detects wildfire smoke using Machine Learning-based (ML) image detection. 

RoboticsCats AI Smoke Detection is using Machine Learning algorithm

InsightFD is a purpose-built integrated hardware and software system to early detect wildfires at long distances in a tough forest environment. ReportFires app resembles InsightFD in automatic detection of wildfire smokes within a few miles or kilometers from your home.

RoboticsCats AI Smoke Detection can detect wildfires in daytime and nighttime

The core technologies we use to build the ReportFires app are Crowd-sourcing, Artificial intelligence, and the internet of Things.

Crowd-sourcing, Artificial intelligence, internet of Things.

Crowd-sourcing, Artificial intelligence, internet of Things.

Are you getting it?

InsightFD in Hong Kong

Timeline

We launched the ReportFires version 1 early this year in the form of a web app[3]. It is an MVP (minimal viable product) and we used it to engage public users, to articulate our ideas, and to collect customer feedback. It is an essential journey to develop ReportFires version 2 in the form of a mobile app. With the guidance from our advisor in San Jose, we decided to build v2 last May. It took us one month to build v1, and another six months to build v2 with the help of many partners and stakeholders! 


User Feedback


Why back us?

We want to help, and we are helping. We invite you to join us.

ReportFires is a free app. We fund the development with our internal resources. We are doing it for common good. We’re proud and joyful to do so.

We hope to launch the mobile app sooner to help more people earlier. Fast-track development will inflate the engineering cost. The popularity of the app will increase operating expenses. We have some great ideas in the product roadmap, and we need additional financial resources and sponsors to make v3 and v4 happen. We are a small company, and we cannot fund all these future developments.

We need your help. We believe you want to support us. Your support will help us to serve our neighbors. Your participation will make the journey more beautiful.

Rewards

Please come to get our beautiful rewards: Glif tripod mount & laptop camera cover
RoboticsCats camera cover is a must-have for iPad users. No more unwanted online meeting video. Not available in Apple Store. Only here in Kickstarter.





 About RoboticsCats.com

RoboticsCats.com is a technology company formed by talents from Hong Kong, Brisbane, Jakarta, Kuala Lumpur and Taipei. We focus on computer vision, AI and IoT. We develop and provide early wildfire detection and environmental monitoring solutions. Our solutions help national parks, forestry, wildfire services,  world heritages, private plantations, and infrastructure companies around the world to mitigate wildfire risks and damages.

Asgard is not a place

Remarks:

1: ReportFires support devices with iOS 13+. Detect mode location estimation supports the following iPhone models: iPhone 8,  iPhone 8 Plus,  iPhone XR, iPhone XR Max, iPhone XS,  iPhone XS Max, iPhone 11, iPhone 11 Pro, iPhone 11 Pro Max, iPhone SE (2nd Gen). Will support older iPhones to estimate wildfire locaton in future versions.

2: The iPhone is assumed to be positioned at 1500-feet or 500 meters altitude and tilted 30 degrees from the horizon.

3: reportfires.roboticscats.com is a web app to report fires and protect our country parks

Country
Links