PyFastTrack package

Detector

class pyfasttrack.base_detector.BaseDetector

Bases: object

Abstract class to implement an objects detector.

abstract detect(image)

Abstract method to be implemented.

This method will take a full image with all the objects to detect and will return a list of tuples (mask, left_corner_coordinate [x, y]) with one object by mask, the object represented by non-zero pixels and the background by zero pixels.

Parameters

imagendarray: The full image.

Returns

dict: List of (mask, left_corner_coord).

get_direction(mask, features)

Get the object direction.

The object orientation is updated with the correct direction.

Parameters

maskndarray: Mask of one object.
featuresdict: Object features.

Returns

bool: Is object left oriented.
ndarray: Rotated mask.
ndarray: Rotation matrix.

get_features(mask)

Get the object features using equivalent ellipse.

Parameters

maskndarray: Mask of one object.

static modulo(angle)

Provide the mathematical 2pi modulo.

Parameters

maskfloat: Angle in radian.

Returns

float: Angle between 0->2pi

process(image)

Process one image.

Parameters

imagendarray: The full image.

Returns

list: List of detected objects and their features.

class pyfasttrack.ft_detector.FtDetector(params)

Bases: BaseDetector

Implement the classic FastTrack detector.

detect(image)

Detect objects

Parameters

imagendarray: Image as GRAYSCALE.

Returns

list: List of masks as [(mask, left_corner), …].

set_background(image)

Set the background image.

Parameters

imagendarray: Background image.

class pyfasttrack.yolo_detector.YoloDetector(params)

Bases: BaseDetector

detect(image)

Detect objects

Parameters

imagendarray: Image as BGR.

Returns

list: List of masks as [(mask, left_corner), …].

Tracker

class pyfasttrack.tracker.Tracker(params=None, detector=None)

Bases: object

Tracker class to determine assignment from previous and current coordinates.

static angle_difference(a, b)

Get the minimal difference, a-b), between two angles.

Parameters

afloat: First angle.
bfloat: Second angle.

Returns

float: a-b.

assign(prev, current)

Find the optimal assignent.

Parameters

prevlist: List of dict. Each dict is one object with 4 key “0”, “1”, “2”, “3”. 0,1,2 is the {center, orientation} of the head, tail and body respectively. 3 is {area, perim} of the object.
currentlist: List of dict. Each dict is one object with 4 key “0”, “1”, “2”, “3”. 0,1,2 is the {center, orientation} of the head, tail and body respectively. 3 is {area, perim} of the object.

Returns

list: Assignment.

clean(current, counter, lost, idty)

Delete objects that were lost. Only counter is copied in this function. Other lists act as pointer.

Parameters

currentlist: List to clean.
counterlist: Counter of losses.
lostlist: Lost objects.
idtylist: Objects’ identity

Returns

list: Cleaned list.
list: Updated counter.

compute_cost(var, norm)

Compute the cost.

Parameters

varList: List of variable.
normlist: Normalization coefficient associated to var.

Returns

float: Cost.

static div(a, b)

Division by zero, a/0=0.

Parameters

afloat: Dividend.
bfloat: Divisor.

Returns

float: a/b.

find_lost(assignment)

Find object lost at previous step.

Parameters

assignmentlist: Assignment indexes.

Returns

list: Indexes of lost objects.

initialize(image)

Initialize the tracker.

Parameters

imagendarray: Image, channels depending on the detector.

Returns

list: List of detected objects as dict.

process(image)

Process an image.

Parameters

imagendarray: Image, channels depending on the detector.

Returns

list: List of detected objects as dict.

reassign(past, current, order)

Reassign current based on order.

Parameters

prevlist: List of dict of previous detections.
currentlist: List of dict of current detections.
orderlist: Reassingment

Returns

list: Reordered current.

set_detector(detector)

Set the detector.

Parameters

detectorBaseDetector: Detector that is an implementation of the BaseDetector.

set_params(params)

Set the parameters.

Parameters

paramsdict: Parameters.

Data

class pyfasttrack.data.Configuration

Bases: object

Class to read and write configuration files compatible with FastTrack.

get_key(key)

Get a parameter from its key.

Parameters

keystr: Key.

Returns

Any: Parameter.

get_keys(keys)

Get parameters from their keys.

Parameters

keyslist: List of keys.

Returns

List: Parameters.

read_db(path)

Read a configuration file from database.

Parameters

pathstr: Path pointing to the sqlite database.

Returns

Dict: Parameters.

read_toml(path)

Read a configuration file from text file.

Parameters

pathstr: Path pointing to the toml file.

Returns

Dict: Parameters.

write_toml(path)

Write a configuration file.

Parameters

pathstr: Path pointing to the toml file.

class pyfasttrack.data.Result(path)

Bases: object

Class to write result files compatible with FastTrack.

add_data(dat)

Append data in the database.

Parameters

datdict or list of dicts: Data.