The essence of the project is to build a good quality stitching of images from 4 cameras and project the image onto a mesh model with acceptable performance. The project work on ~20 fps with constraints from the connection adaptor 30 fps due the synchronize frames mode. This is a research project, and for a production surround view application, I recommend using the Intel/libxcam library.
- Correction distorted object in stitched image using visual odometry (slides presentation, paper)
- Gradient domain blending (paper)
- Photometric calibration (paper)
- Pedestrian detection
- Obstacles detection
- Automatic parking system
| Device type | Device name |
|---|---|
| Camera | e-CAM30A CUMI0330 MOD |
| Connection adaptor board | e-CAM130 TRICUTX2 ADAPTOR |
| Connecting wires | High-speed 2-lane MIPI CSI-2 |
| Embedded platform | Jetson Tegra TX2 |
| Tripod | - |
- OS - Linux Ubuntu LTS v16.04
- C++ 14, Python 3.6, GLSL, C CUDA
- CMake >= v3.16
- CUDA Toolkit v9.0
- V4L2 driver
- OpenGL ES v3.2
- OpenMP
