scene_flow_calibT_scene_flow_calibSceneFlowCalibSceneFlowCalibscene_flow_calib (算子)

名称

scene_flow_calibT_scene_flow_calibSceneFlowCalibSceneFlowCalibscene_flow_calib — 计算两个立体图像对之间的标定场景流。

签名

scene_flow_calib(ImageRect1T1, ImageRect2T1, ImageRect1T2, ImageRect2T2, Disparity : : SmoothingFlow, SmoothingDisparity, GenParamName, GenParamValue, CamParamRect1, CamParamRect2, RelPoseRect : ObjectModel3D)

描述

scene_flow_calibscene_flow_calibSceneFlowCalibSceneFlowCalibSceneFlowCalibscene_flow_calib computes the calibrated scene flow between two consecutive rectified stereo image pairs. The scene flow is the three-dimensional position and motion of surface points in a dynamic scene. The movement in the images can be caused by objects that move in the world or by a movement of the camera (or both) between the acquisition of the two image pairs.

The scene flow is returned as the 3D object model ObjectModel3DObjectModel3DObjectModel3DObjectModel3DobjectModel3Dobject_model_3d. The 3D object model contains the coordinates of the reconstructed 3D points. Furthermore, the 3D flow is encoded in the 3D object model by the attributes '&flow_x'"&flow_x""&flow_x""&flow_x""&flow_x""&flow_x", '&flow_y'"&flow_y""&flow_y""&flow_y""&flow_y""&flow_y", and '&flow_z'"&flow_z""&flow_z""&flow_z""&flow_z""&flow_z".

The two consecutive stereo image pairs of the image sequence are passed in ImageRect1T1ImageRect1T1ImageRect1T1ImageRect1T1imageRect1T1image_rect_1t1, ImageRect2T1ImageRect2T1ImageRect2T1ImageRect2T1imageRect2T1image_rect_2t1, ImageRect1T2ImageRect1T2ImageRect1T2ImageRect1T2imageRect1T2image_rect_1t2, and ImageRect2T2ImageRect2T2ImageRect2T2ImageRect2T2imageRect2T2image_rect_2t2. Each stereo image pair must be rectified. Note that the images can be rectified by using the operators calibrate_camerascalibrate_camerasCalibrateCamerasCalibrateCamerasCalibrateCamerascalibrate_cameras, gen_binocular_rectification_mapgen_binocular_rectification_mapGenBinocularRectificationMapGenBinocularRectificationMapGenBinocularRectificationMapgen_binocular_rectification_map, and map_imagemap_imageMapImageMapImageMapImagemap_image。

The camera geometry of the rectified binocular camera system is specified by its internal camera parameters CamParamRect1CamParamRect1CamParamRect1CamParamRect1camParamRect1cam_param_rect_1 of the rectified camera 1 and CamParamRect2CamParamRect2CamParamRect2CamParamRect2camParamRect2cam_param_rect_2 of the rectified camera 2, and the pose RelPoseRectRelPoseRectRelPoseRectRelPoseRectrelPoseRectrel_pose_rect that defines the pose of the rectified camera 2 in relation to the rectified camera 1. These camera parameters can be obtained from the operators calibrate_camerascalibrate_camerasCalibrateCamerasCalibrateCamerasCalibrateCamerascalibrate_cameras and gen_binocular_rectification_mapgen_binocular_rectification_mapGenBinocularRectificationMapGenBinocularRectificationMapGenBinocularRectificationMapgen_binocular_rectification_map。The focal length and scale factor of the rectified camera system 1 and 2 must be equal.

Furthermore, a single-channel DisparityDisparityDisparityDisparitydisparitydisparity image is required, which specifies for each pixel (r,c1) of the image ImageRect1T1ImageRect1T1ImageRect1T1ImageRect1T1imageRect1T1image_rect_1t1 a matching pixel (r,c2) of ImageRect2T1ImageRect2T1ImageRect2T1ImageRect2T1imageRect2T1image_rect_2t1 according to the equation c2=c1+d(r,c1), where d(r,c) is the DisparityDisparityDisparityDisparitydisparitydisparity at pixel (r,c). The disparity image can be computed using binocular_disparitybinocular_disparityBinocularDisparityBinocularDisparityBinocularDisparitybinocular_disparity or binocular_disparity_mgbinocular_disparity_mgBinocularDisparityMgBinocularDisparityMgBinocularDisparityMgbinocular_disparity_mg。

To calculate the calibrated scene flow, internally scene_flow_uncalibscene_flow_uncalibSceneFlowUncalibSceneFlowUncalibSceneFlowUncalibscene_flow_uncalib is first executed. The results are then converted to 3D points and 3D flow vectors using the stereo camera geometry parameters described above.

For a description of the remaining parameters of scene_flow_calibscene_flow_calibSceneFlowCalibSceneFlowCalibSceneFlowCalibscene_flow_calib, please refer to scene_flow_uncalibscene_flow_uncalibSceneFlowUncalibSceneFlowUncalibSceneFlowUncalibscene_flow_uncalib。

执行信息

多线程类型：可重入（与非独占算子并行运行）。
多线程作用域：全局（可从任何线程调用）。
在内部数据级别上自动并行化。

此算子返回一个句柄。请注意，即使该句柄被用作特定算子的输入参数，这些算子仍可能改变此句柄类型的实例状态。

参数

ImageRect1T1ImageRect1T1ImageRect1T1ImageRect1T1imageRect1T1image_rect_1t1 (输入对象) singlechannelimage(-array) → object (byte / uint2 / real)

Input image 1 at time 。

ImageRect2T1ImageRect2T1ImageRect2T1ImageRect2T1imageRect2T1image_rect_2t1 (输入对象) singlechannelimage(-array) → object (byte / uint2 / real)

Input image 2 at time 。

ImageRect1T2ImageRect1T2ImageRect1T2ImageRect1T2imageRect1T2image_rect_1t2 (输入对象) singlechannelimage(-array) → object (byte / uint2 / real)

Input image 1 at time 。

ImageRect2T2ImageRect2T2ImageRect2T2ImageRect2T2imageRect2T2image_rect_2t2 (输入对象) singlechannelimage(-array) → object (byte / uint2 / real)

Input image 2 at time 。

DisparityDisparityDisparityDisparitydisparitydisparity (输入对象) singlechannelimage(-array) → object (real)

Disparity between input images 1 and 2 at time 。

SmoothingFlowSmoothingFlowSmoothingFlowSmoothingFlowsmoothingFlowsmoothing_flow (输入控制) number → (real / integer)

Weight of the regularization term relative to the data term (derivatives of the optical flow).

默认值： 40.0

建议值： 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0

限制： SmoothingFlow > 0.0

SmoothingDisparitySmoothingDisparitySmoothingDisparitySmoothingDisparitysmoothingDisparitysmoothing_disparity (输入控制) number → (real / integer)

Weight of the regularization term relative to the data term (derivatives of the disparity change).

默认值： 40.0

建议值： 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0

限制： SmoothingDisparity > 0.0

GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (输入控制) attribute.name(-array) → (string)

Parameter name(s) for the algorithm.

默认值： 'default_parameters' "default_parameters" "default_parameters" "default_parameters" "default_parameters" "default_parameters"

建议值： 'default_parameters'"default_parameters""default_parameters""default_parameters""default_parameters""default_parameters", 'warp_levels'"warp_levels""warp_levels""warp_levels""warp_levels""warp_levels", 'warp_zoom_factor'"warp_zoom_factor""warp_zoom_factor""warp_zoom_factor""warp_zoom_factor""warp_zoom_factor", 'warp_last_level'"warp_last_level""warp_last_level""warp_last_level""warp_last_level""warp_last_level", 'outer_iter'"outer_iter""outer_iter""outer_iter""outer_iter""outer_iter", 'inner_iter'"inner_iter""inner_iter""inner_iter""inner_iter""inner_iter", 'sor_iter'"sor_iter""sor_iter""sor_iter""sor_iter""sor_iter", 'omega'"omega""omega""omega""omega""omega"

GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (输入控制) attribute.value(-array) → (string / integer / real)

Parameter value(s) for the algorithm.

默认值： 'accurate' "accurate" "accurate" "accurate" "accurate" "accurate"

建议值： 'very_accurate'"very_accurate""very_accurate""very_accurate""very_accurate""very_accurate", 'accurate'"accurate""accurate""accurate""accurate""accurate", 'fast'"fast""fast""fast""fast""fast", 'very_fast'"very_fast""very_fast""very_fast""very_fast""very_fast", 0, 1, 2, 3, 4, 5, 6, 0.5, 0.6, 0.7, 0.75, 3, 5, 7, 2, 3, 1.9

CamParamRect1CamParamRect1CamParamRect1CamParamRect1camParamRect1cam_param_rect_1 (输入控制) campar → (real / integer / string)

Internal camera parameters of the rectified camera 1.

CamParamRect2CamParamRect2CamParamRect2CamParamRect2camParamRect2cam_param_rect_2 (输入控制) campar → (real / integer / string)

Internal camera parameters of the rectified camera 2.

RelPoseRectRelPoseRectRelPoseRectRelPoseRectrelPoseRectrel_pose_rect (输入控制) pose → (real / integer)

Pose of the rectified camera 2 in relation to the rectified camera 1.

元素数量： 7

ObjectModel3DObjectModel3DObjectModel3DObjectModel3DobjectModel3Dobject_model_3d (输出控制) object_model_3d(-array) → (handle)

3D 对象模型的句柄。

结果

如果参数值正确，算子 scene_flow_calibscene_flow_calibSceneFlowCalibSceneFlowCalibSceneFlowCalibscene_flow_calib 返回值 2 ( H_MSG_TRUE )。如果输入为空（没有可用输入图像）则可设置行为通过 set_system('no_object_result',<Result>)set_system("no_object_result",<Result>)SetSystem("no_object_result",<Result>)SetSystem("no_object_result",<Result>)SetSystem("no_object_result",<Result>)set_system("no_object_result",<Result>)。如有必要，则抛出异常。

可能的前趋

binocular_disparitybinocular_disparityBinocularDisparityBinocularDisparityBinocularDisparitybinocular_disparity, binocular_disparity_mgbinocular_disparity_mgBinocularDisparityMgBinocularDisparityMgBinocularDisparityMgbinocular_disparity_mg

替代

scene_flow_uncalibscene_flow_uncalibSceneFlowUncalibSceneFlowUncalibSceneFlowUncalibscene_flow_uncalib, optical_flow_mgoptical_flow_mgOpticalFlowMgOpticalFlowMgOpticalFlowMgoptical_flow_mg

参考文献

A. Wedel, C. Rabe, T. Vaudrey, T. Brox, U. Franke and D. Cremers: “Efficient dense scene flow from sparse or dense stereo data”; In: Proceedings of the 10th European Conference on Computer Vision: Part I, pages 739-751. Springer-Verlag, 2008.

模块

基础

算子