Idea - FICS

FuseTech

Team and Contact Details

Student Name School Degree Year Email
Ali AbdullahCEMEUndergraduateFourthaliabdullah33340@yahoo.com
Muhammad Usama FaisalCEMEUndergraduateFourthfusama93@gmail.com
Mishal ArifCEMEUndergraduateFourthmishalarif09@gmail.com

Inter School Idea ? No
Do you need expertises from another area: No
If Yes please provide details of expertises you need:

Idea Details

Idea Name: FuseTech
Slogan: Making intelligence reliable
Supervisor Name: Dr. Shahzor Ahmad
Supervisor Designation: Assistant Professor
Supervisor School: CEME
Supervisor Department: Electrical
Contact number: +92 336 1572440
Email ID: s.ahmad@ceme.nust.edu.pk
Abstract:
    This project intends to adapt the literature of self-driving cars for the detection and classification of vehicles for surveillance purposes such as e-tolling, navigation of autonomous vehicles.
What is the unmet need in society that your idea will fulfill ?
    It’s critical for an autonomous vehicle to acquire accurate and real-time information of the objects in its vicinity, which will fully guarantee the safety of the passengers and vehicle in various environment.
Who needs it ? How many would benefit ?
   It is a vital system in robots as well as autonomous vehicles. The system can be adopted in any sphere of industry where perception system and depth information is important.
How will the solution works
    This project presents a 3D object detection and tracking method fusing the complementary information of the two kind of sensors, namely camera and 3D lidar. The image data from camera and the raw point cloud data from Lidar are independently processed by a ResNet Architecture and a PointNet architecture, respectively. The resulting outputs are then combined by a fusion network, which creates 3-D bounding boxes around the vehicles, which can then be used to track the vehicles.
Who are your competitors ? How is your solution different
    We are fusing the data from camera and 3D Lidar and building an end-to-end system from simple 2D object detection to 3D object detection and then to tracking.
Status: new
Entry Date & Time: 2021-01-10 (1842)