A survey of 3D object detection in autonomous driving

PhD Qualifying Examination


Title: "A survey of 3D object detection in autonomous driving"

by

Mr. Peng YUN


Abstract:

Object detection in 3D is still challenging in autonomous driving scenes. It 
recognizes key objects from sensor data and predicts their locations, sizes and 
orientations, which provides both semantic and spatial information for 
high-level decision making.

In this survey, we first introduce and analyze the properties of common 
perceptual sensors on autonomous vehicles: cameras, LiDARs and RADARs. Then we 
introduce the problem definition, assumptions and evaluation metrics of 3D 
object detection in autonomous driving. We review the state-of-the-art methods 
and categorize them into camera-based, LiDAR-based, RADAR-based and 
multi-sensor fusion methods. For each method, we point out the important 
problems and their existing solutions.

By analyzing the limitations of existing methods, we propose some promising 
directions and open problems for future research.


Date:			Monday, 24 June 2019

Time:                  	4:00pm - 6:00pm

Venue:                  Room 3494
                         Lifts 25/26

Committee Members:	Dr. Ming Liu (Supervisor, ECE)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Dr. Qifeng Chen
 			Prof. Tong Zhang (MATH)


**** ALL are Welcome ****