The main contributions of the AutoMine dataset are as follows: 1. The first autonomous driving dataset for perception and localization in mine scenarios.
Most successful object detectors are anchor-based, which is difficult to adapt to the diversity of traffic objects.
3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving.
As a combination of various kinds of technologies, autonomous vehicles could complete a series of driving tasks by itself, such as perception, decision-making, planning, and control.
However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries.