3D OBJECT DETECTION FOR AUTONOMOUS VEHICLES

The dynamic evolution of Machine learning technologies starts the inception of confirmed accuracy of prospects which were hard to imagine few decades ago are now easily executable with various variation of a single field. In today’s situation, self-driving cars have gained a lot of traction but there is a huge gap in expectation and the current state. On those lines, our project focuses on 3D Object Detection of autonomous vehicles. In recent years, there has been a significant increase in research interest supporting the development of the autonomous vehicle. The task of environment sensing is known as perception, and often consists of several subtasks such as object classification, detection, 3D position estimation, and simultaneous localization. It features simultaneous object detection and association for stereo images, 3D box estimation using 2D information, alignment for 3D box refinement.