intel-oneAPI

Team Name - ggbois

Problem Statement - Object Detection For Autonomous Vehicles

Team Leader Email - zubair.mh@protonmail.com

A Brief of the Prototype:

Autonomous Vehicles implement SLAM(Simulataneous Localization and Mapping) in order to implement autopilot/self driving features, however such SLAM implementations can be slow due to lack of parallelization and slow libraries. By leveraging the oneAPI's DPC++ platform and acceleration API's , we aim to create a SLAM implementation that is not only fast but accurate and production ready.

Tech Stack:

Intel oneAPI Base toolkit

• oneAPI Deep Neural Networks Library: Developing the algorithm for detecting nearby datapoints
• oneAPI DPC++/C++ Compiler: Compiling DPC++ code
• oneAPI DPC++ Library: Writing a parallelized program to seperate tasks for the CPU and the GPU
• oneAPI Threading Building Blocks: Building a threaded system for localization and mapping of detected points
• Intel Optimization for Tensorflow: Building a model for object detection
• Technologies used: Languages: SYCL, C++, Python Frameworks: OpenCV, TensorFlow

Step-by-Step Code Execution Instructions:

This Section must contain set of instructions required to clone and run the prototype, so that it can be tested and deeply analysed

What I Learned:

Write about the biggest learning you had while developing the prototype.

Process Flow:

Network Architecture:

Cost :