We propose to develop an IoT-based device that alerts nearby emergency services and primary contacts when an accident happens. We propose to develop a device using FPGA along with peripherals like an accelerometer, GPS module, and two cameras to alert the officials thereby mitigating the loss.
When a collision occurs the accelerometer sensors detect the drastic malfunction of an accelerometer. As soon as a collision is detected, the recording is stored in memory so the footage can be retrieved and used by the police for further investigation if necessary. Two memory devices will be used to store the recorded video, as soon as 60 minutes are elapsed, the recording continues in another memory device, while the other one gets cleared so that recording shall not be delayed due to the clearing process.
The FPGA along with the sensors comes in a single package(entity) along with two external cameras. The user should plug the device into the battery socket which is made available in every car which will be a power supply for the FPGA device. The user has to connect the cameras with the device and mount the cameras at the apt position which might require a technician to care of the wiring.
On top of this, the data collected from series and video will be relayed to the cloud on which we plan to implement different algorithms to further process data like average speed during the entire course, etc. Also, the video will be further processed using the algorithms on the cloud to determine various aspects which include but are not limited to the severity of accident, possible recognition of number plates.
Disclaimer: The above information describes the basic functioning of the device as a whole. The final product may include extra features and possible optimizations.

Project Proposal

1. High-level project introduction and performance expectation

High-Level Introduction

With the increase in population, the on-road vehicle count is rapidly increasing which accounts for 80% of loss of lives across the globe. We propose to develop an IoT-based device that alerts the nearby police station, the hospital along family/friends when an accident happens. We propose to develop a device using FPGA along with peripherals like an accelerometer, GPS module, two cameras, and a LIDAR scanner as a whole to alert the officials thereby mitigating the loss. The working of the device is explained on a high level in the paragraph that follows.

When the Accident happens, the drastic change in the accelerometer reading triggers the response in the sensor and immediately sends a distress signal which alerts the Police, Hospital, and family/friends. The detection method is subject to change to a better one in the final release. This device will be stand-alone with only requiring external power work without the help of mobile That being the main function of the device, we also aim to develop some additional features in it such as:

1)One camera is going to be mounted on the dashboard and the other on the rear side of the vehicle which keeps on recording. The recordings are set to get deleted after every 60 minutes until a collision is detected. As soon as a collision is detected, the recording is stored in memory so the footage can be retrieved and used by the police for further investigation if necessary. As soon as the 60 minutes are elapsed without detection of an accident, new data will be overwritten on the existing data thereby saving memory. If a collision is detected, the recording ceases and therefore the footage up to the time of collision can be retrieved.

2)When a collision is detected, all the lights will be turned on followed by a noticeable beep sound.

3)A LIDAR keeps looking for any suspicious activity ( which will be decided upon by various factors such as data from different sensors and other real-time data ) behind the vehicle and alerts the driver so they can act swiftly and avoid a mishap. This is just an alert and monitoring activities will be continuing.

The FPGA along with the sensors comes in a single entity along with two external cameras and a LIDAR sensor. The user should plug the device into the battery socket which is made available in every car. The user has to connect the cameras with the device and mount the cameras at the apt position which might require a technician to care of the installation. The LIDAR fits on top of the license plate. It has an extendible mount so that it’ll be compatible with any vehicle which is currently in use. For the management of the phone numbers to which the alert has to be sent, and to monitor other data from sensors, a user-friendly website would act as an interface between the device and the user.

On top of this, the FPGA continues to detect the text on number plates and upload them to the cloud until a collision is detected at which the data uploading shall stop so that the number plate data of the last vehicle can be known. This data will be overwritten every 2 minutes in the cloud whereas video recording locally would be overwritten every 60 minutes.

Disclaimer: The above information describes the basic functioning of the device as a whole. The final product may include extra features and possible optimizations

2. Block Diagram

3. Expected sustainability results, projected resource savings

PERFORMANCE PARAMETERS:

Accelerometer sensors:

Accelerometers can be used to measure vibration on cars, machines, buildings, process control systems, and safety installations. They can also be used to measure seismic activity, inclination, machine vibration, dynamic distance, and speed with or without the influence of gravity. We will use these sensors to detect the changes and impact on Accelerometer.

 GPS Sensors:

GPS sensors are receivers with antennas that use a satellite-based navigation system with a network of 24 satellites in orbit around the earth to provide position, velocity, and timing information.

We will these sensors to know the location of the accident or collision.

 Lidar Sensors:

A typical lidar sensor emits pulsed light waves into the surrounding environment. These pulses bounce off surrounding objects and return to the sensor. The sensor uses the time it took for each pulse to return to the sensor to calculate the distance it traveled. We will be using them to locate nearby and passing vehicles.

 Cameras:

We will be using cameras to collect the footage of the collision. We will be also using it to locate the Registration number of the vehicle.

Cloud connectivity:

Cloud can offer you the possibility of storing your files and accessing, storing, and retrieving them from any web-enabled interface. The web services interfaces are usually simple. At any time and place, you have high availability, speed, scalability, and security for your environment. We will be storing all processed data and the footage in the cloud

4. Design Introduction

We vision to develop a design consisting of the main device, two external cameras, and a LIDAR scanner. The FPGA along with its sensors comes in a single entity with a socket for external power supply from the vehicle. Two cameras will be tethered to the main device, one camera at the dashboard and the other at the rear end of the vehicle. The user can connect his phone to the device to make a backup of the video recording to make sure that the footage will be retrievable even if the device is somehow damaged. By doing so. the odds of data retrieval will be made twice. The LIDAR will be mounted on top of the license plate, making use of arrangements supported by the manufacturer. Therefore a single design will be versatile enough to fit in every vehicle regardless of the number of wheels.

Purpose of the design:

For the device to efficiently perform the mentioned actions, we have to ensure that the device will be enclosed in a hard, impact-proof casing and shall be installed in a strategic area in the vehicle so that the damage from the accident doesn’t impact the internal environment of the device. The LIDAR will have a universal mount so that it fits on top of the rear number plate without covering the vehicle registration number.

Application Scope:

The device is designed to work with almost all the on-road vehicles which are currently in use as the only requirement is a battery to power the device. The installation of the device along with the peripherals might require a basic skilled technician although the instructions will be supplied to the user.

We believe that the provided Intel FPGA will handle all the monitoring, recording, and relaying information to the cloud swiftly with the least possible delay in performing all these tasks simultaneously. In real-time, we process the video, extract the number plate data and relay it to the cloud as well as receive data from other sensors and send it to cloud. The provided FPGA is capable of running the algorithm which extracts number plate data. So it would be perfect for the enitre project.

5. Functional description and implementation

6. Performance metrics, performance to expectation

Performance metrics, performance to expectation:

Performance Parameters to reach:

1)low latency in data transmission to the cloud.

2)Optimised number plate text detection system.

3)Wide-angle LIDAR scanning.

4)Sustainability in battery consumption

5)Impact-proof casing for the main device.

7. Sustainability results, resource savings achieved

8. Conclusion

Conclusion:

 Speed is one of the most significant causes of an accident. Nowadays, vehicles are manufactured with safety systems in addition to them by using the proposed mechanism we can detect collisions.  After a collision occurs with immediate effect, the cloud sends the message to the primary contacts. A rescue measure in time with sufficient preparation at the correct place can save many lives. Thus, the proposed system can serve humanity by a great deal as human life is valuable. And we can save lives with an earlier response.