The data constitutes two stereo image pairs collected from cameras mounted on a vehicle while driving on a highway. Nodar’s proprietary calibration technology is used for calibrating the cameras on a frame-to-frame basis to account for any temporal shift introduced during operation, and the stereo-depth is estimated. The resulting depth maps have high Figure-Of-Merit (FOM) values, a key metric used to evaluate the quality of the calibration. This can also be validated from our high pointcloud density, delivering 25 million ****points per second. The information-rich pointclouds are further processed by Nodar’s proprietary detection and tracking technology to identify object position and velocity in the Bird’s Eye View (BEV).
Traveling south on Bundesautobahn 9 near exit 48 to Schnaittach.
The full data can be accessed here: AWS S3 link
| Horizontal Field of View | 30 degrees |
|---|---|
| Baseline | 1.14 meters |
| Resolution | 5.4 MP |
| Bit depth | 8 bit |
| Frame rate | 10 FPS |
A top-bot image is created by vertically concatenating the raw left and right camera image, as shown below:
Assuming pin-hole model for the camera, we get the following intrinsics for our left camera (1) and right camera (2):
| i1_fx = 5272.71 i1_fy = 5274.13 i1_cx = 1417.59 i1_cy = 994.018 i1_k1 = -0.195605 i1_k2 = 0.402684 i1_k3 = -0.935523 i1_k4 = 0 i1_k5 = 0 i1_k6 = 0 i1_p1 = 0.00339975 i1_p2 = -0.000324877 | i2_fx = 5279.79 i2_fy = 5280.33 i2_cx = 1437.7 i2_cy = 964.039 i2_k1 = -0.202667 i2_k2 = 0.401772 i2_k3 = -0.615096 i2_k4 = 0 i2_k5 = 0 i2_k6 = 0 i2_p1 = 0.00369797 i2_p2 = -0.000676622 |
| --- | --- |
We choose the center of the left rectified image as our frame of reference, where the z-axis faces in the forward direction and the y-axis points in the downward direction. Consequently, the right camera is located along the x-axis in our chosen frame of reference.
The translation (in m) and rotation (in degrees) for the right-camera w.r.t our frame of reference is shown below:
Tx = 1.139583858358012 Ty = 0.02517260139586513 Tz = -0.01382679868870892 theta_x = 0.3867545791285434 theta_y = -0.1121154102308677 theta_z = 1.125803146503237
We follow the Z-Y-X Euler angle rotation convention. Consequently, the overall rotation matrix can be established by R = R_z * R_y * R_x.
The left-rectified image shows the image from the left camera after rectification, as shown below: