BEVDet Detection - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English

Autonomous driving considers its surroundings for decision making. This is one of the most complex scenarios in visual perception. BEVDet is a powerful and scalable paradigm for multi-camera 3D object detection that can be deployed on AMD FPGAs. For more details about the BEVDet model, see BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View.

The following image shows the result of BEVDet Detection.

Figure 1. BEVDet Detection Example

Table 1. BEVDet Model
No Model Name Framework
1 bevdet_pt PyTorch