Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

511 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Overview

The RideHal is Qualcomm ADAS hardware abstraction layer that provides user friendly APIs to access the Qualcomm ADAS hardware accelerator. It is ADAS service oriented to provide user friendly component and utils to cover the perception and compute vision related task.

Documents

Check this INDEX.

Below is a summary information of the current implemented components.

Component QNX HOST HGY Ubuntu Library Processor Feaures
Camera YES YES qcarcam Camera camera streaming
Remap YES YES FastADAS CPU, HTP0, HTP1, GPU Color Conversion, ROI Crop, Downscaling, Undistortion
C2D YES NO C2D GPU Color Conversion, ROI Crop, Resize
QnnRuntime YES YES QNN CPU, GPU, HTP0, HTP1 AI model inference
VideoEncoder YES YES vidc VPU Encode image to video frame
VideoDecoder YES YES vidc VPU Decode video frame to image
Voxelization YES YES FastADAS, OpenCL CPU, HTP0, HTP1, GPU create pilliar
PostCenterPoint YES YES FastADAS CPU, HTP0, HTP1 extract bounding boxes
CL2DFlex YES Yes OpenCL GPU Color Conversion, Resize, ROI Crop, Undistortion
GL2DFlex NO YES OpenGL GPU Color Conversion, ROI Crop, Resize
OpticalFlow YES YES EVA EVA Optical flow
DepthFromStereo YES YES EVA EVA Depth From Stereo

How to build

For how to build the RideHal package in simple steps with internal scripts, check this README.

For how to build the RideHal package manually, check this:

How to run

For how to run the RideHal package, check this README.

For how to run the RideHal E2E perception pipeline sample, check this README.

About

No description, website, or topics provided.

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages