Module ObjectDetection

This module manages the detection of object on video frame. It allows the choice of the method to mots appropriate to discriminate the particles from the free surface.

ObjectDetection.histogram_detection(img, params)

Find area corresponding to selected histogram

Parameters:

• nbr_classes – number of class in the histogram

• roi_detect – size of the ROI selected

• color_choice – type of image color (RGB,HSV,gray)

• color_band – band for the histogram measurement (RGB,HSV,gray)

Returns:

list of detected particles positions [ID trajectory, X position, Y position, size, intensity]

Return type:

list

ObjectDetection.method_DoG(img, params)

Original method of tractrac software. The detection is obtained by the convolution of the frame by a double gaussian function.

Parameters:

• img – frame treated

• peak_conv_size – size of the gaussian for filtering (in pixel)

• type_particle – Light/Dark particle

• peak_sub_pix – method for sub-pixel detection No method, Quadratic ,Gaussian

• peak_th_auto – (True/False) use automatic threshold to find maximum value on the convoluted frame

• peak_th – threshold to find maximum value on the convoluted frame

• peak_neigh – size of filter for the convoluted frame (pixel)

Returns:

list of detected particles positions [X position, Y position]

Return type:

list

ObjectDetection.method_GoodFeatureToTrack(img, params)

Shi and Tomasi Method directly availiable in openCV library

Parameters:

• img – frame treated

• max_corner – nombre maximal de détection par image

• quality_level –

• min_distance –

• block_size –

Returns:

list of detected particles positions [X position, Y position]

Return type:

list

ObjectDetection.method_threshold(img, params)

Frame thresholding with binarization to extract position, area and intensity of each particle

Parameters:

• img – frame treated

• intensity_min – minimal intensity of selected particles(in level 0-255)

• intensity_max – maximal intensity of selected particles (in level 0-255)

• size_min – minimal length of selected particles (in pixel)

• size_max – maximal length of selected particles (in pixel)

• lo – minimal intensity of selected particles for color frame (3 values ex: RGB, HSV)

• hi – maximal intensity of selected particles for color frame (3 values ex: RGB, HSV)

Returns:

list of detected particles positions [ID trajectory, X position, Y position, size, intensity]

Return type:

list

ObjectDetection.process_object_detection(img, params, id_method)

Processing selected detection method

Parameters:

• img – frame treated

• dict – dictionnary parameters

• id_method – detection method

Returns:

list of detected particles positions [ID trajectory, X position, Y position, size, intensity]

Return type:

list

ObjectDetection.select_method(param)

Function for detection method selection Several methods are possible. The good feature to track method is the most common method based on the shi method. It is original method with the opyflow software. The threshold is the simplest but needs the user calibration. The Dog Method is the original method for tractrac software The Histogram is dedicated to track of specific object.

Parameters:

dict – dictionnary parameters

Return type:

int

ObjectDetection.track_manual_detection_init(img, params)

Define the histogram of the selected ROI

Parameters:

• nbr_classes – number of class in the histogram

• color_choice – type of image color (RGB,HSV,gray)

• color_band – band for the histogram measurement (RGB,HSV,gray)

Returns:

size of the ROI selected

Return type:

list (height, width)

Returns:

histogram value in selected ROI

Return type:

list