Road Incident Predictor

create incidents using chainlink vrf
air quality screening and traffic monitor with live video streaming on eth using chainlink
dashboard for incidents and air quality
traffic in bad and good air quality
Ethereum scan page
live

Inspiration

Mobility is an integral part of everyone's life. According to statistics, there is one death in four minutes due to a road accident in India. This situation worsens during winters.

Our app solution will enable effective design, engineering and delivery of expert.ai aided solution to make roads safer and better using predictive analytics and automation for incident reporting and reduction in hazardous transportation with capabilities pluggable and extendable to 5 different personas: Driver, Police, Citizen, Dispatcher, Admin.

Our solution will benefit: Police Force - 360 degrees access of the incidents to the action/ administration team. They can manage the complete lifecycle of incident reporting, overall status, traffic monitoring, managing police teams. Using machine learning they can also predict the incident occurrence at any area. This will help in taking necessary actions in advance to control the traffic. They can also use the solution for effective utilization of staff members and provide road safety counselling.

Ministry of Road and Transportation: Endeavor to change the car accident scenario by use of car technology to make driving safer and monitored for drivers, authorities, as well as other 3rd parties. With a mix of hardware and software, we will provide intelligent feedback about drive quality and help analyze past incidents, as well as predict future incidents.

Citizens and Cab aggregators: Reduction in the number of road accidents.

Insurance Companies: Aggregated/ anonymized driving data and incident data will be helpful to car insurance companies.

OEMs and Dealerships: Vehicle diagnostics and in-car service consumption will be helpful for OEMs and Dealerships.

Smart Cities Policy Makers/ Government: Real time traffic flow, incident alert and parking data will be enable safer roads.

Advertisers: Customers/driver demographics will be available.

Fleet customers: fleet performance, compare against competition.

What it does Our solution offers an Artificial Intelligence-based object detection system that utilizes Ethereum, IPFS/Filecoin, Chainlink VRF, Metis, zksync, Scroll, Avalanche, Polygon zKEVM and Tron DAO blockchain solutions using polygon for sorting information obtained from a variety of cameras. With just a cell phone, users are offered a serverless solution that can detect objects in real time and more object types for better accuracy.

Our technical solution enables driver monitoring, incident management and collision avoidance: Incident-based reporting & Collision detection (even when a vehicle is parked) and video footage associated with it. Video footage for abnormal driver behaviour (complete view of the car with 2 cameras – front and back and open source video streaming), real-time alert and live streaming using open source AWS solutions and ASDI OpenAQ ((https://github.com/awslabs/open-data-registry/blob/main/datasets/openaq.yaml) dataset along with Tron DAO blockchain.

Any abnormal behaviour/activity can be displayed on the smart dashboard in the vehicle.

Built-in GPS technology useful in fleet management and tracking. Black box car tracking to be able to pre-empt and diagnose breakdowns more quickly. Recognition area built in the central control to pick up your body movements, GAIT analysis Vehicles become IoT devices which can connect to smartphones, take voice commands, change the user interface.

The decentralized Cloud-Connected Car Drives IoT Monetization. Real-time access to car availability and mobile connectivity enables better decisions making systems.

QR code dapp with CCIP, AVAX and Scroll Integration: https://drive.google.com/drive/u/1/folders/1ktW-NuwCIzN7zZpAm50Q2-0yndIL4X4f

Pitch Video: https://youtu.be/Jh_AFWc_kKI

CCIP NFT Deployment on Avalanche: https://drive.google.com/drive/folders/1txMlY2Z26xJOuEtyfC2F1Hhjq6_FDzqY

Demo Video of CCIP NFT Deployment on Avalanche: https://drive.google.com/drive/folders/1txMlY2Z26xJOuEtyfC2F1Hhjq6_FDzqY

Scroll Deployment (Admin Role): https://sepolia.scrollscan.com/address/0x89E4F30AFB281689632535e1657D15243a83b802

Scroll Deployment (Citizen Role): https://sepolia.scrollscan.com/address/0xDE16EdC78F1Af5865CCA458c8833069fDaf1Ca7b

CCIP Explorer transaction Link: https://ccip.chain.link/msg/0xef336e431848d66424a1fb6db41a7a3560f4265c2adfa31055aa224817158633

CCIP Transaction hash link : https://ccip.chain.link/msg/0xf83f4d78c4cc86f9190319cc746eb7f0063a4740e1d78414a2b5fada8b104f80

Sucessfull ccip trasaction hash link ; https://ccip.chain.link/msg/0x3202aab91a2c818c515e9d03412942cc7832838e7b40754e046a100916001ad2

CCIP NFT fuji -> sepholia OpenSea link : https://testnets.opensea.io/assets/sepolia/0x4c47dbeb2bec4e1bdb897430efed217c56d0270d/0

Video screen cast of frontend and qr code scanning part and nft Minting : https://drive.google.com/drive/folders/1bkBGbHS_89y1nsEF5IMn79BBSNSDY8-S

Opensea minted NFT link (CCIP) : https://testnets.opensea.io/assets/sepolia/0x4c47dbeb2bec4e1bdb897430efed217c56d0270d/4

IPFS link: https://beige-royal-slug-524.mypinata.cloud/ipfs/QmX2Bh4kETmbUnvYpxhkoAWa5NjSQqLbJeRUFRAf7idgKX?pinataGatewayToken=e6vJ4oXa8yREy_ZI1ur2ELVB-BnJMRRUabm6gdLEgiyjVHaf_aSz44fyDvFR5r7W

Design

How we built it

Chainlink: We are extending and adapting the Chainlink project "Link My Ride" to develop a decentralized first aid and ambulance platform by using Chainlink External Adapter to connect a Tesla Vehicle API to a Chainlink oracle for a peer-to-peer vehicle rental app. We wish to use it for Maruti Vehicle API and Hyundai Vehicle API too. Please visit: https://github.com/aspiringsecurity/EthTransport/tree/main/decentralized-ambulance

We are utilizing Chainlink VRF as follows:

E-Challan (Transport Receipt) Bill Generation: We are utilizing Chainlink Mix to work with Chainlink smart contracts. The bill script will deploy a smart contract to goerli and get a Random number via Chainlink VRF, which can used to identify a unique transaction/order number for the receipt or bill. Link: https://github.com/aspiringsecurity/EthTransport/tree/main/roadincidentmanagement/IPFS-Chainlink-Monitor-main

Parametric Insurance Solution in public transportation especially for project finance. We are utilizing an existing example at chainlink github repo to develop an insurance solution for public transportation. Link: https://github.com/aspiringsecurity/EthTransport/tree/main/roadincidentmanagement

Fleet and Cab Drivers and Vehicle Service Organizations Payouts: Chainlink Parametric Insurance dapp at https://github.com/aspiringsecurity/EthTransport/tree/main/Fleet-cab-drivers-service-payout

NFT and Certificate for Good Services in Repair and Vehicle services: https://github.com/aspiringsecurity/EthTransport/tree/main/dapp-tools/NFT-giveaway-certificate-service-rating

Dynamic NFT for for Good Services in Repair and Vehicle servicing: https://github.com/aspiringsecurity/EthTransport/tree/main/dapp-tools/NFT-giveaway-certificate-service-rating/Transport-SxT-dNFT

Chainlink Functions: We are learning to utilize Chainlink Functions in Transport Monitor at https://github.com/aspiringsecurity/EthTransport/tree/main/roadincidentmanagement

NFT.Storage: We are using NFT.Storage for storing a variety of offchain data like incident snapshots, alarm metadata and object types at the time of incident. Please find the video at https://drive.google.com/drive/folders/1bbHDoY1Y80EOeJP32XDngShnSjkMR55m (screencapturewithoutsound.mov file). We are storing Alarm metadata using NFT.Storage. Also, Saving/deleting alarm metadata and image to/from IPFS using NFT.Storage. We are also storing the hash returned from IPFS to Ethereum test network using NFT.Storage. Further we are using NFT.Storage for: Video analytics configuration using NFT.Storage; Camera Management: Add/edit/delete cameras with integration with Livepeer, NFT.Storage; Live streaming with Object Detection Video Analytics using Livepeer for streaming, and NFT.Storage for snapshots.

Polygon: We are utilizing ZoraModuleManager, and ZoraProtocolFeeSettings in our our dapp and deploying it on Polygon after registering the Zora market module.

Chainlink and Polygon zKEVM: We are using Chainlink and Polygon zKEVM to develop a platform where users can issue, manage and transfer credits of ratings earned for vehicle owners and their respective vehicles via pollution checks, green fuel adoption in vehicles:

User creation procedure; User identification with NFC tags; Create credits of ratings earned via pollution checks, green fuel assets; Issue green credits for vehicles via pollution checks; List your green credits per vehicle; Handle multiple vehicles.

Polygon zKEVM Public Goods: We are using Polygon zKEVM to develop a platform where government authorities linked with Transport department like Pollution check control department, Municipality portal can issue, manage and transfer credits of ratings earned by vehicle owners and their respective vehicles via pollution checks, green fuel adoption in vehicles. This is especially useful for fleet management vehicles managed by the government for public goods delivery (Example: GeM portal goods in India) where co-incentives can be provided to contract organizations for good performance in pollution checks, green fuel adoption (switching away from diesel fuel to CNG). The workflow is as follows:

Fleet role creation procedure; Fleet vehicles identification with NFC tags; Create credits of ratings earned via pollution checks, green fuel assets; Issue green credits for fleet vehicles via pollution checks by Transport department like Pollution check control; List green credits per fleet vehicle; Handle multiple vehicles.

Chainlink Developer Tooling: We are developing tools and plugins for the green credits platform along with an alarm viewer dapp. The alarm viewer can be used in case a vehicles' quarterly pollution check is due or has not been completed one week before the penalty set by the government authorities. This alarm viewer can be further extended by the developers to build community tools, analytics and visualization tooling by adding features like pollution check performance ratings and raising alarms and notifications when the registry of a vehicle to operate in a region expires (example: 15 years for petrol vehicles and 10 years for diesel vehicles in Delhi). The alarm viewer application can also be extended for the use case where the pollution testing equipment does not give optimal results, which is very much true when a vehicle has traveled more than 45,000 kms.

Consensys's Infura and Metamask tools with Optimism NFT marketplace and Scalability of Decentralized Public Goods, Mobility Network Enablement: Optimism NFT marketplace for vehicle's spare parts and also for early-stage detection and prevention of incidents using Infura; NFC tags of vehicles for enabling sharing of government assets and service/repair of vital assets. Improving Data Transparency in Incident Management Using Ethereum Blockchain, Infura, Metamask and Optimism NFT marketplace. Optimism NFT marketplace for NFC tags of vehicles for enabling sharing of government assets and service/repair of vital assets. We are also using Optimism to enable scaling of the decentralized public goods mobility network and effective management and communication setup for services utilized in Operations and Maintenance across multiple regions.

XMTP: We are implementing XMTP Chat for Transport administrators in a particular region with CyberConnect functions.

We are extending and adapting the Chainlink project "Link My Ride" to develop a decentralized first aid and ambulance platform by using Chainlink External Adapter to connect a Tesla Vehicle API to a Chainlink oracle for a peer-to-peer vehicle rental app. We wish to use it for Maruti Vehicle API and Hyundai Vehicle API too.

We have developed a road incident management system using Javascript, HTML5, SAP's UI5 on the front end using open source video streaming system, Tron DAO, expert.ai language models, ASDI OpenAQ ((https://github.com/awslabs/open-data-registry/blob/main/datasets/openaq.yaml) and crowdsourcing marketplace enabled by Chainlink VRF for enabling sharing of government assets like toll prepaid card, car details information for interstate travel, driving license management and quarterly pollution check and control powered by Ethercalc (SocialCalc), Polygon, NFTPorts for infrastructure and access of data from Polygon blockchains, NFT.Storage, Lit protocol for security and neume for data retrieval and at the road incident spot for better coordination and immediate action.

We are using DAOtooling for coordination with a social focus around community collaboration for road incidents and alarms using Tron DAO.

ENS Username: transportdao.eth

How it works:

Camera Management: Add/edit/delete cameras with a front end application with NFTPorts integration, NFT.Storage (IPFS/Filecoin) for snapshots of road incident, Sequence wallet for toll ticketing, neume for data retrieval.

Object Detection using open source AWS solutions, air quality measurements with ASDI OpenAQ ((https://github.com/awslabs/open-data-registry/blob/main/datasets/openaq.yaml) and Pytorch/Tensorflow deep learning library using CNN neural networks.

Video analytics configuration using NFT.Storage, Litprotocol for security and neume for data retrieval.

Live streaming with Object Detection Video Analytics using open source AWS for streaming, Litprotocol for security and NFT.Storage for snapshots.

Alarm storage using Ethereum. Save/delete alarm metadata and image to/from IPFS using NFT.Storage. Store the hash returned from IPFS to Ethereum test network using NFT.Storage, Litprotocol for security and neume for data retrieval.. Provide links to alarms and blockchain transaction details.

Alarm Viewer: Add alarms with a single touch. Open the Alarm Settings menu from the home page. Add an alarm, set the wallpaper or choose an alarm tone. You can also delete an existing alarm. We are using Sequence wallet for NFT marketplace of alarm clock wallpapers and background ringtones purchase and auction. We are also extending and adapting Turtle Music using NFT Experiments for music curators for alarm clock. We are using DAOtooling for coordination with a social focus around community collaboration for road incidents and alarms.

Challenges we ran into AWS deployment: We were using PV (paravirtual) based classic instance. We were required to convert PV (paravirtual) instance to an HVM (Hardware Virtual Machine) and convert it from a classic instance to a VPC instance. We faced a number of challenges in converting our PV instance to an HVM instance as our instance was not reachable via ssh. We arrived at a good conclusion on the issue by doing the following: Created an ami of current classic instance. Launch a new instance from this ami after shifting to vpc as the base with new VPC security groups and updated volume. The newly launched instance is working and we are able to ssh and has the code base. We purchased the developer support plan using AWS credits and have being shared key pointers on converting our VPC based PV instance to a VPC based HVM instance. This challenge would not have been solved without the support of AWS team.

The insurance providers have to manually upload the incident and vehicle data to create the insurance based NFT. It is not a problem for a small set of vehicles where we can use csv to json conversion using open source libraries like phpexcel in ethercalc but problematic for larger number of vehicles. At this juncture, the insurance providers have to manually connect their wallet and create the insurance claim NFT.

Accomplishments that we're proud of A greater and more seamless flow of information within a transportation infrastructure, created by electronic incident record management service (E.I.R.M.S), encompasses and leverages digital progress and can transform the way road safety can be delivered and efforts sustained.

E.I.R.M.S helps in improved coordination. E.I.R.M.S helps in making road safety ecosystem proactive and authentic. E.I.R.M.S with the help of computer aided detection will help in early prediction and prevention of incidents.

What we learned We can utilize SocialCalc, Machine Learning Models coupled with decentralized Polygon zKEVM, NFT.Storage, network tools, ethereum based infrastructure tools for analysis and prediction of incidents to provide early stage detection and prevention of accidents. We also witnessed the great eco-system available to developers to learn and contribute in the Ethereum eco-system.

What's next for Road Incident Predictor The platform is currently running on AWS, Polygon testnet and SAP Hana platform. We still need focus on key performance indicators like throughput and measure the performance of our smart contracts before moving to mainnet. We plan to utilize tools like blocktest for measuring and benchmarking our smart contracts and unit tests on a variety of key parameters like throughput, latency. We also wish to test our solution using AWS templates on compliance and security. We need to spend quality time learning analytics, prediction methods and utilizing and developing open source datasets.