![]() |
VisionWorks Toolkit ReferenceDecember 18, 2015 | 1.2 Release |
The Median Flow Algorithm.
This algorithm estimates a median flow vector of a set of points.
The primitive uses the following identifiers:
vxGetKernelByEnum
function;"com.nvidia.nvx.median_flow"
for vxGetKernelByName
function.
It takes a set of points at a single timestamp and the successive timestamp. Presumably, this set belongs to a single object and the algorithm estimates a single offset vector of this object called the median flow. It also estimates how the scale of the object changed.
Functions | |
vx_node | nvxMedianFlowNode (vx_graph graph, vx_array prev_pts, vx_array next_pts, vx_array pts_fb, vx_array out, vx_bool estimate_scale, vx_bool filter_flow_by_err, vx_float32 error_fb_thresh) |
[Graph] Computes median flow. More... | |
vx_status | nvxuMedianFlow (vx_context context, vx_array prev_pts, vx_array next_pts, vx_array pts_fb, vx_array out, vx_bool estimate_scale, vx_bool filter_flow_by_err, vx_float32 error_fb_thresh) |
[Immediate] Computes median flow. More... | |
vx_node nvxMedianFlowNode | ( | vx_graph | graph, |
vx_array | prev_pts, | ||
vx_array | next_pts, | ||
vx_array | pts_fb, | ||
vx_array | out, | ||
vx_bool | estimate_scale, | ||
vx_bool | filter_flow_by_err, | ||
vx_float32 | error_fb_thresh | ||
) |
[Graph] Computes median flow.
[in] | graph | Specifies the graph. |
[in] | prev_pts | Specifies the input previous points list. Only VX_TYPE_KEYPOINT and NVX_TYPE_POINT2F item types are supported. |
[in] | next_pts | Specifies the input next points list. It must have the same item type and number of items as prev_pts. |
[in] | pts_fb | [optional] Specifies the backward points list. It must have the same item type and number of items as prev_pts. |
[out] | out | Specifies the output median flow. It is a one element NVX_TYPE_POINT3F array. x and y fields of the first element represent estimated displacement, z field represents estimated scale change. In case of estimation failure \( (0, 0, -1) \) is returned. |
[in] | estimate_scale | Specifies whether to estimate scale change. |
[in] | filter_flow_by_err | Specifies whether to filter out points with a high error value. |
[in] | error_fb_thresh | [optional] Specifies the threshold for forward-backward errors. Pass a nonpositive value to disable forward-backward filtering. |
vxGetStatus
).vx_status nvxuMedianFlow | ( | vx_context | context, |
vx_array | prev_pts, | ||
vx_array | next_pts, | ||
vx_array | pts_fb, | ||
vx_array | out, | ||
vx_bool | estimate_scale, | ||
vx_bool | filter_flow_by_err, | ||
vx_float32 | error_fb_thresh | ||
) |
[Immediate] Computes median flow.
[in] | context | Specifies the context. |
[in] | prev_pts | Specifies the input previous points list. Only VX_TYPE_KEYPOINT and NVX_TYPE_POINT2F item types are supported. |
[in] | next_pts | Specifies the input next points list. It must have the same item type and number of items as prev_pts. |
[in] | pts_fb | [optional] Specifies the backward points list. It must have the same item type and number of items as prev_pts. |
[out] | out | Specifies the output median flow. It is a one element NVX_TYPE_POINT3F array. x and y fields of the first element represent estimated displacement, z field represents estimated scale change. In case of estimation failure \( (0, 0, -1) \) is returned. |
[in] | estimate_scale | Specifies whether to estimate scale change. |
[in] | filter_flow_by_err | Specifies whether to filter out points with a high error value. |
[in] | error_fb_thresh | [optional] Specifies the threshold for forward-backward errors. Pass a nonpositive value to disable forward-backward filtering. |
vx_status
enumerator. VX_SUCCESS | No errors. |
VX_ERROR_INVALID_REFERENCE | Supplied parameters are not a valid references. |
VX_ERROR_INVALID_PARAMETERS | Supplied parameters are not valid. |
VX_ERROR_INVALID_SCOPE | Supplied parameters are virtual objects, which can't be used in immediate mode. |
VX_FAILURE | Internal error in primitive implementation, check log for detailed information (Framework: Log). |