SDK Analytics Configs¶

struct Metavision::CountingAlgorithmConfig¶

Structure to instantiate a counting configuration.

Public Functions

CountingAlgorithmConfig(int min_cluster_size, CountingMode mode = CountingMode::Mono, Metavision::timestamp accumulation_time_us = -1)¶

Constructor.

Parameters

min_cluster_size: Minimum cluster size
mode: Type of recording (mono or stereo)
accumulation_time_us: Accumulation time of the event buffer before processing (in us) If not set, the algorithm will work in synchronous mode and directly process each received event-buffer.

struct Metavision::CalibrationConfig¶

Base structure representing all the parameters needed for calibration.

Public Functions

CalibrationConfig(CountingViewSetup view_setup, float object_min_size = 5, float object_average_speed = 5, float distance_object_camera = 300)¶

Constructor.

See

The enum CountingViewSetup

Parameters

view_setup: Type of the counting setup

Parameters

object_min_size: Approximate largest dimension of the smallest object (in mm). The value must be positive. It will be refined during the calibration.
object_average_speed: Approximate average speed of an object to count (in m/s). It will be refined during the calibration.
distance_object_camera: Average distance between the flow of objects to count and the camera (in mm) Camera must look perpendicular to the object falling plan. It will be refined during the calibration.

Public Members

CountingViewSetup view_setup_¶

Type of the counting setup.

See: The enum CountingViewSetup

struct Metavision::CalibrationResults¶

Base structure representing all the parameters obtained after the calibration.

Public Functions

CalibrationResults(const std::string &calibration_file)¶

Base Constructor used when we need to load a calibration file.

Parameters

calibration_file: Calibration file to load

CalibrationResults(int width, int height, const std::string &calibration_file)¶

Constructor used when the sensor’s geometry is known, and we need to write the calibration file.

Parameters

width: Sensor’s width (in pixels)
height: Sensor’s height (in pixels)
calibration_file: Calibration file to write

void load()¶: Loads the calibration file.

void dump()¶: Writes the calibration file.

struct Metavision::SpatterTrackerAlgorithmConfig¶

Configuration to instantiate a SpatterTrackerAlgorithmConfig.

Public Functions

SpatterTrackerAlgorithmConfig(int cell_width, int cell_height, timestamp accumulation_time, int untracked_threshold = 5, int activation_threshold = 10, bool apply_filter = true, int max_distance = 50, const int min_size = 1, const int max_size = std::numeric_limits<int>::max())¶

Constructor.

Parameters

cell_width: Width of cells used for clustering
cell_height: Height of cells used for clustering
accumulation_time: Time to accumulate events and process
untracked_threshold: Maximum number of times a spatter_cluster can stay untracked before being removed
activation_threshold: Threshold distinguishing an active cell from inactive cells (i.e. minimum number of events in a cell to consider it as active)
apply_filter: If true, than applying a simple filter to remove crazy pixels
max_distance: Max distance for clusters association (in pixels)
min_size: Minimum object size (in pixels) - minimum of the object’s width and height should be larger than this value
max_size: Maximum object size (in pixels) - maximum of the object’s width and height should be smaller than this value

struct Metavision::TrackingConfig¶

Structure used to configure the TrackingAlgorithm.

Public Types

enum ClusterMaker¶

Defines the type of cluster maker used by the TrackingAlgorithm.

Values:

enumerator SIMPLE_GRID¶

enumerator MEDOID_SHIFT¶

enum DataAssociation¶

Defines type of data association used by the TrackingAlgorithm.

Values:

enumerator NEAREST¶

enumerator IOU¶

enum Initializer¶

Defines the type of initializer used by the TrackingAlgorithm. Only one method implemented for now.

Values:

enumerator SIMPLE¶

enum MotionModel¶

Defines the type of motion model used by the TrackingAlgorithm.

Values:

enumerator SIMPLE¶

enumerator INSTANT¶

enumerator SMOOTH¶

enumerator KALMAN¶

enum KalmanModel¶

Defines the Kalman motion model used by the TrackingAlgorithm.

Values:

enumerator CONSTANT_VELOCITY¶

enumerator CONSTANT_ACCELERATION¶

enum KalmanPolicy¶

Defines the Kalman policy model used by the TrackingAlgorithm.

Values:

enumerator ADAPTIVE_NOISE¶

enumerator MEASUREMENT_TRUST¶

enum Tracker¶

Defines the type of tracker used by the TrackingAlgorithm.

Values:

enumerator ELLIPSE¶

enumerator CLUSTERKF¶

enum EllipseUpdateFunction¶

Ellipse tracker related parameters.

Values:

enumerator UNIFORM¶

enumerator GAUSSIAN¶

enumerator SIGNED_GAUSSIAN¶

enumerator TRUNCATED_GAUSSIAN¶

Public Members

bool print_timings_ = false¶: If enabled, displays a profiling summary.

ClusterMaker cluster_maker_ = ClusterMaker::SIMPLE_GRID ¶: Type of cluster maker to use.

int cell_width_ = 10¶: Grid clustering cell’s width (in pixels).

int cell_height_ = 10¶: Grid clustering cell’s height (in pixels).

timestamp cell_deltat_ = 1000¶: Grid clustering cell’s time delta (in us).

int activation_threshold_ = 5¶: Minimum number of events needed to activate the grid.

float medoid_shift_spatial_dist_ = 5¶: Maximum spatial distance (using Manhattan distance) for two events to be in the same cluster.

timestamp medoid_shift_temporal_dist_ = 10000¶: Maximum temporal distance for two events to be in the same cluster.

int medoid_shift_min_size_ = 2¶: Minimum width and height for a cluster to be considered valid and given to the tracking engine.

DataAssociation data_association_ = DataAssociation::IOU ¶: Type of data association to use.

double max_dist_ = 150.¶: Nearest data association related parameters. Maximum distance between cluster’s centroid and tracker’s position.

double iou_max_dist_ = 150.¶: IOU data association related parameters. Maximum distance between cluster’s centroid and tracker’s position.

Initializer initializer_ = Initializer::SIMPLE ¶

Simple initializer related parameters.

Type of initializer to use.

MotionModel motion_model_ = MotionModel::SIMPLE ¶: Type of motion model to use.

double smooth_mm_alpha_vel_ = 0.001¶: Smooth motion model related parameters.

double kalman_motion_model_pos_trans_std_ = 0.0001¶: Standard deviation of the transition noise for the tracker’s position.

double kalman_motion_model_vel_trans_std_ = 0.05¶: Standard deviation of the transition noise for the tracker’s velocity.

double kalman_motion_model_acc_trans_std_ = 1e-9¶: Standard deviation of the transition noise for the tracker’s acceleration.

double kalman_motion_model_pos_obs_std_ = 100¶: Standard deviation of the observation noise for the tracker’s position.

double kalman_motion_model_init_factor_ = 1e12¶: Factor to multiply to noise variance at initialization.

double kalman_motion_model_avg_events_per_pixel_ = 1¶: Expected average events per pixel rate in events/us.

timestamp kalman_motion_model_min_dt_ = 1000¶: Minimal timestep at which to compute Kalman filter.

KalmanPolicy kalman_motion_model_policy_ = KalmanPolicy::ADAPTIVE_NOISE ¶: Policy used in the Kalman Filter.

KalmanModel kalman_motion_model_motion_model_ = KalmanModel::CONSTANT_VELOCITY ¶: Motion model used in the Kalman filter.

Tracker tracker_ = Tracker::CLUSTERKF ¶: Type of tracker to use.

timestamp delta_ts_for_prediction_ = 5000¶: Delta ts (in us) for the position prediction.

timestamp ts_to_stop_ = 100000¶: Time (in us) to wait without having updated a tracker before deleting it.

enum Metavision::CountingMode¶

Type of recording (mono or stereo)

Values:

enumerator Mono¶

enumerator Stereo¶

enum Metavision::CountingViewSetup¶

Enum to indicate the type of the counting setup. Currently, only mono is supported, but it might be extended to other setups in the future.

Values:

enumerator Mono¶: Monocular counting setup.