SDK CV3D Python bindings API

class metavision_sdk_cv3d.Edgelet2dDetectionAlgorithm
static get_empty_output_buffer()metavision_sdk_cv3d.EventEdgelet2dBuffer

This function returns an empty buffer of events of the correct type, which can later on be used as output_buf when calling process_events()

process(*args, **kwargs)

Overloaded function.

  1. process(self: metavision_sdk_cv3d.Edgelet2dDetectionAlgorithm, time_surface: metavision_sdk_core.MostRecentTimestampBuffer, in_events: numpy.ndarray[metavision_sdk_base._EventCD_decode], out_edgelets: metavision_sdk_cv3d.EventEdgelet2dBuffer) -> None

  2. process(self: metavision_sdk_cv3d.Edgelet2dDetectionAlgorithm, time_surface: metavision_sdk_core.MostRecentTimestampBuffer, in_events: metavision_sdk_base.EventCDBuffer, out_edgelets: metavision_sdk_cv3d.EventEdgelet2dBuffer) -> None

class metavision_sdk_cv3d.Edgelet2dTrackingAlgorithm
class Parameters
property median_outlier_threshold

Distance to the median position of the support points’ matches above which a match is considered as outlier.

property n_support_points

Number of points sampled along the edgelet’s direction.

property search_radius

Radius in which matches are looked for each edgelet’s side.

property support_points_distance

Distance in pixels between the sampled points.

property threshold

Time tolerance used in the tracking.

static get_empty_edgelet_buffer()metavision_sdk_cv3d.EventEdgelet2dBuffer

This function returns an empty buffer of events of the correct type, which can later on be used as output_buf when calling process_events()

process(*args, **kwargs)

Overloaded function.

  1. process(self: metavision_sdk_cv3d.Edgelet2dTrackingAlgorithm, time_surface: metavision_sdk_core.MostRecentTimestampBuffer, target: int, in_edgelets: numpy.ndarray[Metavision::EventEdgelet2d], out_edgelets: metavision_sdk_cv3d.EventEdgelet2dBuffer) -> list

  2. process(self: metavision_sdk_cv3d.Edgelet2dTrackingAlgorithm, time_surface: metavision_sdk_core.MostRecentTimestampBuffer, target: int, in_edgelets: metavision_sdk_cv3d.EventEdgelet2dBuffer, out_edgelets: metavision_sdk_cv3d.EventEdgelet2dBuffer) -> list

class metavision_sdk_cv3d.Model3d
class EdgeBuffer

Buffer of 3D model’s edges.

numpy(self: metavision_sdk_cv3d.Model3d.EdgeBuffer)numpy.ndarray[Metavision::Model3d::Edge]

Converts to a numpy array

class Face

Structure defining 3D model’s face.

edges_indexes_numpy(self: metavision_sdk_cv3d.Model3d.Face)numpy.ndarray[numpy.uint64]

Indexes to the model’s edges that form this face (Numpy array).

property normal

Face’s normal

class FaceBuffer

Buffer of 3D model’s faces.

class VertexBuffer

Buffer of 3D model’s vertices.

property edges

All the edges forming the 3D model’s faces.

property faces

All the faces forming the 3D model.

property vertices

All the vertices forming the 3D model.

class metavision_sdk_cv3d.Model3dDetectionAlgorithm
class Parameters
property fitted_edges_ratio_

Matched edges to visible edges ratio above which a pose estimation is attempted.

property flow_radius_

Radius used to estimate the normal flow which gives the edge’s orientation.

property n_fitting_pts_

Minimum required number of matches for line fitting.

property search_radius_

Radius in which matches are looked for for each support point.

property support_point_step_

Distance, in pixels in the distorted image, between two support points.

property variance_threshold_

Variance of the support points around the fitted line below which an edge is considered matched.

process_events(*args, **kwargs)

Overloaded function.

  1. process_events(self: metavision_sdk_cv3d.Model3dDetectionAlgorithm, in_events: numpy.ndarray[metavision_sdk_base._EventCD_decode], out_T_c_w: metavision_sdk_cv3d.EigenMatrix4f) -> tuple

  2. process_events(self: metavision_sdk_cv3d.Model3dDetectionAlgorithm, in_events: metavision_sdk_base.EventCDBuffer, out_T_c_w: metavision_sdk_cv3d.EigenMatrix4f) -> tuple

set_init_pose(self: metavision_sdk_cv3d.Model3dDetectionAlgorithm, T_c_w: metavision_sdk_cv3d.EigenMatrix4f)None
class metavision_sdk_cv3d.Model3dTrackingAlgorithm
class Parameters
property default_acc_time_us_

Default accumulation time used when the tracking is starting (i.e. the N last poses have not been estimated yet).

property most_recent_weight_

Weight attributed to the more recent matches.

property n_last_poses_

Number of past poses to consider to compute the accumulation time.

property oldest_weight_

Weight attributed to the oldest matches.

property search_radius_

Radius in which matches are looked for for each support point.

property support_point_step_

Distance, in pixels in the distorted image, between two support points.

process_events(*args, **kwargs)

Overloaded function.

  1. process_events(self: metavision_sdk_cv3d.Model3dTrackingAlgorithm, in_events: numpy.ndarray[metavision_sdk_base._EventCD_decode], out_T_c_w: metavision_sdk_cv3d.EigenMatrix4f) -> bool

  2. process_events(self: metavision_sdk_cv3d.Model3dTrackingAlgorithm, in_events: metavision_sdk_base.EventCDBuffer, out_T_c_w: metavision_sdk_cv3d.EigenMatrix4f) -> bool

set_previous_camera_pose(self: metavision_sdk_cv3d.Model3dTrackingAlgorithm, ts: int, T_c_w: metavision_sdk_cv3d.EigenMatrix4f)None
metavision_sdk_cv3d.draw_edges(cam_geometry: metavision_sdk_cv.CameraGeometry, T_c_w: metavision_sdk_cv3d.EigenMatrix4f, model: metavision_sdk_cv3d.Model3d, edges: set, image: numpy.ndarray, color: List[int])None

Draws the selected edges of a 3D model into the output frame.

metavision_sdk_cv3d.load_model_3d_from_json(path: str)object

Loads a 3D model from a JSON file.

metavision_sdk_cv3d.select_visible_edges(T_c_w: metavision_sdk_cv3d.EigenMatrix4f, model: metavision_sdk_cv3d.Model3d)set

Selects the visible edges of a 3D model given a camera’s pose.