Unlock 30% off on Manual Testing Annual Plans this Holiday Season.

Copied to Clipboard!

How to use analyze_frame method in ATX

Best Python code snippet using ATX

test_hole_in_the_wall_model.py

Source:test_hole_in_the_wall_model.py

...100    """101    test_model = HoleInTheCameraGame()102    # creates an all black image103    test_image = np.zeros([480, 640, 3])104    test_model.analyze_frame(test_image)105    assert len(test_model.joint_candidates) == 0106def test_analyze_frame_black_image_joint_subsets():107    """108    Tests that deep pose does not return any joint subsets109    for an empty black image.110    """111    test_model = HoleInTheCameraGame()112    test_image = np.zeros([480, 640, 3])113    test_model.analyze_frame(test_image)114    assert len(test_model.joint_subsets) == 0115def test_analyze_frame_white_image_joint_candidates():116    """117    Tests that deep pose does not find any joints118    for a white image.119    """120    test_model = HoleInTheCameraGame()121    # creates an all white image122    test_image = np.ones([480, 640, 3]) * 255123    test_model.analyze_frame(test_image)124    assert len(test_model.joint_candidates) == 0125def test_analyze_frame_white_image_joint_subsets():126    """127    Tests that deep pose does not return any joint subsets128    for a white image.129    """130    test_model = HoleInTheCameraGame()131    test_image = np.ones([480, 640, 3]) * 255132    test_model.analyze_frame(test_image)133    assert len(test_model.joint_subsets) == 0134def test_analyze_frame_no_legs_joint_candidates():135    """136    Tests that deep pose does not find extra joints137    for a mask containing only the upper body of a person.138    """139    test_model = HoleInTheCameraGame()140    # reads a stored image used to create game masks141    test_image = cv2.imread("images/poses/first_mask.png")142    test_model.analyze_frame(test_image)143    assert len(test_model.joint_candidates) == 14144def test_analyze_frame_no_legs_num_joint_subsets():145    """146    Test that deep pose only finds one person's joint subset147    when there's only one person in the image.148    """149    test_model = HoleInTheCameraGame()150    test_image = cv2.imread("images/poses/first_mask.png")151    test_model.analyze_frame(test_image)152    assert len(test_model.joint_subsets) == 1153def test_analyze_frame_no_legs_first_joint_subset():154    """155    Test that the only joint subset found by deep pose contains all156    expected information, including 17 joint positions and three157    values about the accuracy of the fit.158    """159    test_model = HoleInTheCameraGame()160    test_image = cv2.imread("images/poses/first_mask.png")161    test_model.analyze_frame(test_image)162    assert len(test_model.joint_subsets[0]) == 20163def test_analyze_frame_half_upper_joint_candidates():164    """165    Tests that deep pose does not find extra joints166    for a mask containing only the upper body of a person.167    """168    test_model = HoleInTheCameraGame()169    # splits the image in half to test behavior on a cut off person170    test_image = cv2.imread("images/poses/first_mask.png")[:, 0:325, :]171    test_model.analyze_frame(test_image)172    assert len(test_model.joint_candidates) == 7173def test_analyze_frame_half_upper_num_joint_subsets():174    """175    Tests that deep pose only found one joint subset for an image176    with only half a person.177    """178    test_model = HoleInTheCameraGame()179    test_image = cv2.imread("images/poses/first_mask.png")[:, :325, :]180    test_model.analyze_frame(test_image)181    assert len(test_model.joint_subsets) == 1182def test_analyze_frame_half_upper_first_joint_subset():183    """184    Test that the only joint subset found by deep pose contains all185    expected information, including 17 joint positions and three186    values about the accuracy of the fit.187    """188    test_model = HoleInTheCameraGame()189    test_image = cv2.imread("images/poses/first_mask.png")[:, :325, :]190    test_model.analyze_frame(test_image)191    assert len(test_model.joint_subsets[0]) == 20192def test_analyze_frame_other_half_upper_joint_candidates():193    """194    Tests that deep pose only found one joint subset for an image195    with only the other half a person.196    """197    test_model = HoleInTheCameraGame()198    test_image = cv2.imread("images/poses/first_mask.png")[:, 350:, :]199    test_model.analyze_frame(test_image)200    assert len(test_model.joint_candidates) == 7201def test_analyze_frame_other_half_upper_num_joint_subsets():202    """203    Tests that deep pose only found one joint subset for an image204    with only the other half a person.205    """206    test_model = HoleInTheCameraGame()207    test_image = cv2.imread("images/poses/first_mask.png")[:, 350:, :]208    test_model.analyze_frame(test_image)209    assert len(test_model.joint_subsets) == 1210def test_analyze_frame_other_half_upper_first_joint_subset():211    """212    Test that the only joint subset found by deep pose contains all213    expected information, including 17 joint positions and three214    values about the accuracy of the fit.215    """216    test_model = HoleInTheCameraGame()217    test_image = cv2.imread("images/poses/first_mask.png")[:, 350:, :]218    test_model.analyze_frame(test_image)219    assert len(test_model.joint_subsets[0]) == 20220def test_parse_for_joint_positions_black_image():221    """222    Test that when analyzing the deep pose result, there are no joint223    positions that can be found or parsed for in a black image.224    """225    test_model = HoleInTheCameraGame()226    test_image = np.zeros([480, 640, 3])227    test_model.analyze_frame(test_image)228    test_model.parse_for_joint_positions()229    assert test_model.joint_positions == {}230def test_parse_for_joint_positions_white_image():231    """232    Test that when analyzing the deep pose result, there are no joint233    positions that can be found or parsed for in a white image.234    """235    test_model = HoleInTheCameraGame()236    test_image = np.ones([480, 640, 3]) * 255237    test_model.analyze_frame(test_image)238    test_model.parse_for_joint_positions()239    assert test_model.joint_positions == {}240def test_parse_for_joint_positions_no_legs_joints_detected():241    """242    Test that when analyzing and parsing through the deep pose result, the243    joints that are expected to be missing (9, 10, 11, 12 as these are the leg244    joint) are mapped to a [-1, -1] position and the others are not mapped to245    [-1, -1].246    """247    test_model = HoleInTheCameraGame()248    test_image = cv2.imread("images/poses/first_mask.png")249    test_model.analyze_frame(test_image)250    test_model.parse_for_joint_positions()251    for key, value in test_model.joint_positions.items():252        if key in ["9", "10", "12", "13"]:253            if value != [-1, -1]:254                assert False255        else:256            if value == [-1, -1]:257                assert False258    assert True259def test_parse_for_joint_positions_no_legs_found_joint_positions():260    """261    Test for when analyzing the parsing through the deep pose result, the262    existing joints (joints not in the legs) are mapped to positions that lie263    within the pixel bounds of the inputted image.264    """265    test_model = HoleInTheCameraGame()266    test_image = cv2.imread("images/poses/first_mask.png")267    test_model.analyze_frame(test_image)268    test_model.parse_for_joint_positions()269    for key, value in test_model.joint_positions.items():270        if key not in ["9", "10", "12", "13"]:271            if value[0] > 640 or value[0] < 0 or value[1] > 480 or value[1] < 0:272                assert False273    assert True274def test_parse_for_joint_positions_half_upper_joints_detected():275    """276    Test that when analyzing and parsing through the deep pose result, the277    joints that are expected to be missing (1, 5, 6, 7, 8, 9, 10, 11, 12, 13,278    18 as these are the leg joint or upper body joints that are not included in279    the inputted image) are mapped to a [-1, -1] position and the others are280    not mapped to [-1, -1].281    """282    test_model = HoleInTheCameraGame()283    test_image = cv2.imread("images/poses/first_mask.png")[:, :325, :]284    test_model.analyze_frame(test_image)285    test_model.parse_for_joint_positions()286    for key, value in test_model.joint_positions.items():287        if key in ["1", "5", "6", "7", "8", "9", "10", "11", "12", "13", "17"]:288            if value != [-1, -1]:289                assert False290        else:291            if value == [-1, -1]:292                assert False293    assert True294def test_parse_for_joint_positions_half_upper_found_joint_positions():295    """296    Test for when analyzing the parsing through the deep pose result, the297    existing joints (joints not in the legs or half of the upper body) are298    mapped to positions that lie within the pixel bounds of the inputted image.299    """300    test_model = HoleInTheCameraGame()301    test_image = cv2.imread("images/poses/first_mask.png")[:, :325, :]302    test_model.analyze_frame(test_image)303    test_model.parse_for_joint_positions()304    for key, value in test_model.joint_positions.items():305        if key not in ['1', '5', '6', '7', '8', '9', '10', '11', '12', '13',306                       '17']:307            if value[0] > 640 or value[0] < 0 or value[1] > 480 or value[1] < 0:308                assert False309    assert True310def test_parse_for_joint_positions_other_half_upper_joints_detected():311    """312    Test that when analyzing and parsing through the deep pose result, the313    joints that are expected to be missing (0, 2, 3, 4, 8, 9, 10, 11, 12, 13,314    14, 15, 16 as these are the leg joint or upper body joints that are not315    included in the inputted image) are mapped to a [-1, -1] position and the316    others are not mapped to [-1, -1].317    """318    test_model = HoleInTheCameraGame()319    test_image = cv2.imread("images/poses/first_mask.png")[:, 350:, :]320    test_model.analyze_frame(test_image)321    test_model.parse_for_joint_positions()322    for key, value in test_model.joint_positions.items():323        if key in ['0', '2', '3', '4', '8', '9', '10', '12', '13', '14', '15',324                   '16']:325            if value != [-1, -1]:326                assert False327        else:328            if value == [-1, -1]:329                assert False330    assert True331def test_parse_for_joint_positions_other_half_upper_found_joint_positions():332    """333    Test for when analyzing the parsing through the deep pose result, the334    existing joints (joints not in the legs or half of the upper body) are335    mapped to positions that lie within the pixel bounds of the inputted image.336    """337    test_model = HoleInTheCameraGame()338    test_image = cv2.imread("images/poses/first_mask.png")[:, 350:, :]339    test_model.analyze_frame(test_image)340    test_model.parse_for_joint_positions()341    for key, value in test_model.joint_positions.items():342        if key not in ['0', '2', '3', '4', '8', '9', '10', '12', '13', '14',343                       '15', '16']:344            if value[0] > 640 or value[0] < 0 or value[1] > 480 or value[1] < 0:345                assert False346    assert True347def test_compute_accuracy_white_image_total_score():348    """349    Test that the computed fit accuracy is 0 when a white image is analyzed and350    compared to existing joint positions. Based on this computed accuracy, the351    total score should be updated to be 0.352    """353    test_model = HoleInTheCameraGame()354    test_image = np.ones([480, 640, 3]) * 255355    test_csv = "mask_joint_positions/first_mask.csv"356    test_model.analyze_frame(test_image)357    test_model.parse_for_joint_positions()358    test_model.compute_accuracy(test_csv)359    assert test_model.total_score == 0360def test_compute_accuracy_white_image_trial_score():361    """362    Test that the computed fit accuracy is 0 when a white image is analyzed and363    compared to existing joint positions. Based on this computed accuracy, the364    trial score should be updated to be 0.365    """366    test_model = HoleInTheCameraGame()367    test_image = np.ones([480, 640, 3]) * 255368    test_csv = "mask_joint_positions/first_mask.csv"369    test_model.analyze_frame(test_image)370    test_model.parse_for_joint_positions()371    test_model.compute_accuracy(test_csv)372    assert test_model.trial_score == 0373def test_compute_accuracy_same_image_total_score():374    """375    Test that when an image is analyzed and compared to against joint positions376    obtained from the same image, the accuracy is a 100% match and the total377    score is updated to reflect such (100).378    """379    test_model = HoleInTheCameraGame()380    test_image = cv2.imread("images/poses/first_mask.png")381    test_csv = "mask_joint_positions/first_mask.csv"382    test_model.analyze_frame(test_image)383    test_model.parse_for_joint_positions()384    test_model.compute_accuracy(test_csv)385    assert test_model.total_score == 100.0386def test_compute_accuracy_same_image_trial_score():387    """388    Test that when an image is analyzed and compared to against joint positions389    obtained from the same image, the accuracy is a 100% match and the trial390    score is updated to reflect such (100).391    """392    test_model = HoleInTheCameraGame()393    test_image = cv2.imread("images/poses/first_mask.png")394    test_csv = "mask_joint_positions/first_mask.csv"395    test_model.analyze_frame(test_image)396    test_model.parse_for_joint_positions()397    test_model.compute_accuracy(test_csv)398    assert test_model.trial_score == 100.0399def test_compute_accuracy_same_image_total_score_three_trials():400    """401    Test that when an image is analyzed and compared to against joint positions402    obtained from the same image, the accuracy is a 100% match three times in a403    row. This is reflected in the total score as it is updated three times with404    a score of 100, yielding a total score of 300.405    """406    test_model = HoleInTheCameraGame()407    test_image = cv2.imread("images/poses/first_mask.png")408    test_csv = "mask_joint_positions/first_mask.csv"409    for _ in range(3):410        test_model.analyze_frame(test_image)411        test_model.parse_for_joint_positions()412        test_model.compute_accuracy(test_csv)413    assert test_model.total_score == 300.0414def test_compute_accuracy_same_image_trial_score_three_trials():415    """416    Test that when an image is analyzed and compared to against joint positions417    obtained from the same image, the accuracy is a 100% match three times in a418    row. For the trial score, this should only reflect 100 as it stores the419    most recent trial score.420    """421    test_model = HoleInTheCameraGame()422    test_image = cv2.imread("images/poses/first_mask.png")423    test_csv = "mask_joint_positions/first_mask.csv"424    for _ in range(3):425        test_model.analyze_frame(test_image)426        test_model.parse_for_joint_positions()427        test_model.compute_accuracy(test_csv)428    assert test_model.trial_score == 100.0429def test_computer_accuracy_diff_image_total_score():430    """431    Test that when an image is analyzed and compared to against a different432    image's joint positions, the accuracy is below 70%. This simulates a failed433    trial of the real game where a user's position is different than the434    expected position. This is reflected by the total score being less than 70.435    """436    test_model = HoleInTheCameraGame()437    test_image = cv2.imread("images/poses/second_mask.png")438    test_csv = "mask_joint_positions/first_mask.csv"439    test_model.analyze_frame(test_image)440    test_model.parse_for_joint_positions()441    test_model.compute_accuracy(test_csv)442    assert test_model.total_score < 70443def test_computer_accuracy_diff_image_trial_score():444    """445    Test that when an image is analyzed and compared to against a different446    image's joint positions, the accuracy is below 70%. This simulates a failed447    trial of the real game where a user's position is different than the448    expected position. This is reflected by the trial score being less than 70.449    """450    test_model = HoleInTheCameraGame()451    test_image = cv2.imread("images/poses/second_mask.png")452    test_csv = "mask_joint_positions/first_mask.csv"453    test_model.analyze_frame(test_image)454    test_model.parse_for_joint_positions()455    test_model.compute_accuracy(test_csv)456    assert test_model.trial_score < 70457def test_computer_accuracy_diff_image_total_score_three_trials():458    """459    Test that when an image is analyzed and compared to against a different460    image's joint positions, the accuracy is below 70%. This is done three461    different times to ensure that total score is properly updated and has462    a value less than the passing value for three total iterations.463    """464    test_model = HoleInTheCameraGame()465    test_image = cv2.imread("images/poses/second_mask.png")466    test_csv = "mask_joint_positions/first_mask.csv"467    for _ in range(3):468        test_model.analyze_frame(test_image)469        test_model.parse_for_joint_positions()470        test_model.compute_accuracy(test_csv)471    assert test_model.total_score < 210472def test_computer_accuracy_diff_image_trial_score_three_trials():473    """474    Test that when an image is analyzed and compared to against a different475    image's joint positions three different times, the accuracy is below 70%476    and the trial score only stores the accuracy of the most recent trial.477    """478    test_model = HoleInTheCameraGame()479    test_image = cv2.imread("images/poses/second_mask.png")480    test_csv = "mask_joint_positions/first_mask.csv"481    for _ in range(3):482        test_model.analyze_frame(test_image)483        test_model.parse_for_joint_positions()484        test_model.compute_accuracy(test_csv)485    assert test_model.trial_score < 70486def test_check_win_same_image():487    """488    This function checks to make sure the model correctly determines a win when489    an image is analyzed against joints generated from the same exact image.490    """491    test_model = HoleInTheCameraGame()492    test_image = cv2.imread("images/poses/first_mask.png")493    test_csv = "mask_joint_positions/first_mask.csv"494    test_model.analyze_frame(test_image)495    test_model.parse_for_joint_positions()496    test_model.compute_accuracy(test_csv)497    assert test_model.check_win()498def test_check_win_diff_image():499    """500    This function checks to make sure the model correctly determines a loss501    when an image is analyzed against joints generated from a different image.502    """503    test_model = HoleInTheCameraGame()504    test_image = cv2.imread("images/poses/second_mask.png")505    test_csv = "mask_joint_positions/first_mask.csv"506    test_model.analyze_frame(test_image)507    test_model.parse_for_joint_positions()508    test_model.compute_accuracy(test_csv)509    assert not test_model.check_win()510def test_check_win_two_iterations():511    """512    Tests to make sure the check_win function correctly determines a win513    followed by a loss in succession.514    """515    test_model = HoleInTheCameraGame()516    test_image = cv2.imread("images/poses/first_mask.png")517    test_csv = "mask_joint_positions/first_mask.csv"518    test_model.analyze_frame(test_image)519    test_model.parse_for_joint_positions()520    test_model.compute_accuracy(test_csv)521    if not test_model.check_win():522        assert False523    test_image = cv2.imread("images/poses/second_mask.png")524    test_model.analyze_frame(test_image)525    test_model.parse_for_joint_positions()526    test_model.compute_accuracy(test_csv)527    if test_model.check_win():528        assert False...

main_view.py

Source:main_view.py

...62        lbl_frame = tk.Label(self.data_frame, text="Fetcher")63        lbl_frame.grid(row=0, column=0, columnspan=2, pady=20)64        lbl_frame.config(font=("Courier", 20))65        self.add_input_form(self.data_frame)66    def add_analyze_frame(self):67        self.analyze_frame = tk.Frame(self)68        self.analyze_frame.grid(row=0, column=1, padx=10, sticky='n')69        # Frame title70        lbl_frame = tk.Label(self.analyze_frame, text="Analyzer")71        lbl_frame.grid(row=0, column=0, columnspan=3, pady=20)72        lbl_frame.config(font=("Courier", 20))73        self.add_plot_frame(self.analyze_frame)74    def rm_analyze_frame(self):75        if self.analyze_frame is not None:76            self.analyze_frame.grid_forget()77    def rm_plot_frame(self):78        if self.plot_frame is not None:79            self.plot_frame.grid_forget()80    81    def add_plot_frame(self, frame):82        # Period Label83        self.plot_frame = tk.Frame(frame, bd=10, relief='raised')84        self.plot_frame.grid(row=1, column=0, columnspan=3, ipadx=5, ipady=5)85        lbl_period = tk.Label(self.plot_frame, text='Period')86        lbl_period.grid(row=1, column=0, padx=(10, 0))87        # Period Entry88        self.period_entry = tk.Entry(self.plot_frame)...

main.py

Source:main.py

1import mwt_functions as mwt2import numpy as np3import cv2 as cv4# Get Test Video5# cap = cv.VideoCapture('scene1.mp4')6# video_temp = video_resize('F:/æµ·æµªæµé/æ°æ®é/Pexels Videos 1757800.mp4')7cap = cv.VideoCapture("scene1.mp4")8last_frame = int(cap.get(cv.CAP_PROP_FRAME_COUNT))9frame_rate = int(cap.get(cv.CAP_PROP_FPS))10# Create some random colors11color = np.random.randint(0, 255, (100, 3))12# Grab First Frame w/ Grayscale Vers.13ret, old_frame = cap.read()14old_gray = cv.cvtColor(old_frame, cv.COLOR_BGR2GRAY)15ret, old_thresh = cv.threshold(old_gray, 230, 255, cv.THRESH_BINARY)16# Create a mask image for drawing purposes17mask = np.zeros_like(old_frame)18mask[..., 1] = 25519# Create Initial Variables20frame_num = 121tracked_waves = []22recognized_waves = []23period = []24stable_wavelength = 025while True:26    # Get Current Frame & Grayscale Vers.27    ret, frame = cap.read()28    # Check if at end29    if not ret:30        break31    gray = cv.cvtColor(frame,cv.COLOR_BGR2GRAY)32    #33    # Preprocessing34    #35    # Threshold image to only show the white part of waves36    ret, thresh = cv.threshold(gray, 205, 255, cv.THRESH_BINARY)37    # Resize Image38    analyze_frame = cv.resize(thresh, None,fx=0.25,fy=0.25,interpolation=cv.INTER_AREA)39    # Denoise Thresholded image40    analyze_frame = cv.fastNlMeansDenoising(analyze_frame, 5)41    # Remove Small Artifacts42    analyze_frame = cv.morphologyEx(analyze_frame, cv.MORPH_OPEN, cv.getStructuringElement(cv.MORPH_RECT, (3, 3)))43    #44    # Get Waves (Detections)45    #46    sections = []47    #_, contours, hierarchy = cv.findContours(48    contours, hierarchy = cv.findContours(49        image=analyze_frame,50        mode=cv.RETR_EXTERNAL,51        method=cv.CHAIN_APPROX_NONE,52        hierarchy=None,53        offset=None)54    for contour in contours:55        if mwt.keep_contour(contour):56            sections.append(mwt.Section(contour, frame_num))57    #58    # Update Waves (Tracking)59    #60    wave_points = []61    wave_slopes = []62    for wave in tracked_waves:63        wave.update_searchroi_coors()64        #65        analyze_frame = wave.update_points(analyze_frame, 1/0.25)66        if wave.update_death(frame_rate, frame_num):67            print("Wave Traveled " + str(wave.travel_dist) +68                  "m in " + str(wave.time_alive) + "s")69        if frame_num == last_frame:70            wave.death = frame_num71        if wave.update_centroid(frame_rate):72            period.append(frame_num)73        wave.update_boundingbox_coors()74        wave.update_displacement()75        wave.update_mass()76        wave.update_recognized()77        # Update Data Structures78        # frame = mwt.draw_line(frame, wave.slope, wave.intercept,  1 / 0.25)79        wave_points.append(wave.centroid)80        wave_slopes.append(wave.slope)81    dead_recognized_waves = [wave for wave in tracked_waves82                             if wave.death is not None83                             and wave.recognized is True]84    recognized_waves.extend(dead_recognized_waves)85    tracked_waves = [wave for wave in tracked_waves if wave.death is None]86    tracked_waves.sort(key=lambda x: x.birth, reverse=True)87    for wave in tracked_waves:88        other_waves = [wav for wav in tracked_waves if not wav == wave]89        if mwt.will_be_merged(wave, other_waves):90            wave.death = frame_num91    tracked_waves = [wave for wave in tracked_waves if wave.death is None]92    tracked_waves.sort(key=lambda x: x.birth, reverse=False)93    #94    # Calculate Stats (Recognition)95    #96    for section in sections:97        if not mwt.will_be_merged(section, tracked_waves):98            tracked_waves.append(section)99    # Draw detection boxes on original frame for visualization.100    frame = mwt.draw(tracked_waves, frame, 1 / 0.25)101    #102    # Show Updated Frames103    #104    # Calculate Wavelength (avg)105    avg_slope = np.mean(wave_slopes)106    wavelengths = [mwt.calc_dist_lines(j, i, avg_slope) for i, j in zip(wave_points[:-1], wave_points[1:])]107    avg_wavelength = np.round(np.mean(wavelengths), 2)108    if np.isnan(avg_wavelength) or avg_wavelength == 0:109        avg_wavelength = stable_wavelength110    else:111        stable_wavelength = avg_wavelength112    # Calculate Period113    # Get diff. between each wave reaching point114    if len(period) > 1:115        periods = [(j-i)/frame_rate for i, j in zip(period[:-1], period[1:])]116        avg_period = np.round(np.mean(periods), 2)117        temp_freq = np.round(1/avg_period, 2)118        main_stats = "Stats\nWavelength: {}m\nPeriod: {}s\nTemporal Frequency: {} wave/s"\119            .format(np.round(avg_wavelength,2), avg_period, temp_freq)120    else:121        main_stats = "Stats\nWavelength: {}m\nPeriod: n/a\nTemporal Frequency: n/a"\122            .format(avg_wavelength)123    for i, j in enumerate(main_stats.split('\n')):124        frame = cv.putText(125                    frame,126                    text=j,127                    org=(20, (50 + i * 45)),128                    fontFace=cv.FONT_HERSHEY_COMPLEX_SMALL,129                    fontScale=1.5,130                    color=(200, 200, 200),131                    thickness=2,132                    lineType=cv.LINE_AA)133    # Show Test Point used for Period134    frame = cv.circle(frame, (1040, 600), 4, (0,0,0), thickness=4)135    cv.imshow("original", frame)136    cv.imshow("thresholded", analyze_frame)137    if cv.waitKey(1) & 0xFF == ord('q'):138        break139    old_frame = frame.copy()140    old_thresh = analyze_frame.copy()141    frame_num = frame_num + 1142cap.release()...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.