libXCam is a project for extended camera(not limited in camera) features and focus on image quality improvement and video analysis. There are lots features supported in image pre-processing, image post-processing and smart analysis. This library makes GPU/CPU/ISP working together to improve image quality. OpenCL is used to improve performance in different platforms.
Other
589
stars
229
forks
source link
How to get better Car Surround view with fisheye cameras? #807
Hi Wei Zong,
With OCamCalib toolbox generated intrinsics and extrinsics ,according to_
'RRfin is a 3x3xM matrix, where M correspond to the respective image number. The first two columns of RRfin identify the ROTATION matrix (which is given by the column vectors Rx and Ry; Rz can be obtained as cross product between Rx and Ry). The third column of RRfin identifies the TRANSLATION vector of the checkerboard (i.e. [tx;ty;tz])'_get extrinsics parameters.
Then I am getting the following output, which is very bad, where as the one which you generated is far better. Can you please let me know what all configurations you used and also if you did any changes to calibration parameters ?
some parameter I used:
input_width = 1920;input_height = 1080;output_width = 2880;output_height = 960;
topview_width = 1920;topview_height = 1020;
input_format = V4L2_PIX_FMT_YUV420; uint32_t fisheye_num = 4;
cam_model = CamB4C1080P; module = SVModuleGLES; GeoMapScaleMode ScaleSingleConst;
FeatureMatchMode fm_mode = FMNone;FisheyeDewarpMode dewarp_mode = DewarpBowl;
data_param.zip
Hi Wei Zong, With OCamCalib toolbox generated intrinsics and extrinsics ,according to_ 'RRfin is a 3x3xM matrix, where M correspond to the respective image number. The first two columns of RRfin identify the ROTATION matrix (which is given by the column vectors Rx and Ry; Rz can be obtained as cross product between Rx and Ry). The third column of RRfin identifies the TRANSLATION vector of the checkerboard (i.e. [tx;ty;tz])'_get extrinsics parameters. Then I am getting the following output, which is very bad, where as the one which you generated is far better. Can you please let me know what all configurations you used and also if you did any changes to calibration parameters ? some parameter I used: input_width = 1920;input_height = 1080;output_width = 2880;output_height = 960; topview_width = 1920;topview_height = 1020; input_format = V4L2_PIX_FMT_YUV420; uint32_t fisheye_num = 4; cam_model = CamB4C1080P; module = SVModuleGLES; GeoMapScaleMode ScaleSingleConst; FeatureMatchMode fm_mode = FMNone;FisheyeDewarpMode dewarp_mode = DewarpBowl;
data_param.zip