This illustrates a use of a deep learning model called PoseNet. It defines blocks for obtaining up to 17 locations on one or more people (nose, elbow, knee, etc.). This program tracks the eyes, nose, and wrists and mirrors their movements. If a hand comes close to the face a warning is issued.data:image/png;base64,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data:image/png;base64,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

Reports the distance between two pose elements if they are visible. Otherwise a big number is reported.

confidence threshold50distance threshold100222064

Can't see both eyes so just guess how far apart they are.11

Reports a costume using the camera.

costume

Creates a costume from the video camera and passes it the 'process costume' blocks.

This reports either the confidence that the body part is correctly identified as a number between 0 and 100 or the location of a body part as two numbers. If 'stage coordinates' is true then the location matches the stage coordinates, otherwise it is between 0 and 100.

location confidenceleft right the aeye ear shoulder elbow wrist hip knee ankle nose persontruenose

confidence there is a nose

Only the nose has no left or right versions.property numberProperty numbers range from 0 to 34 to identify different information in a pose.property number

eyeearshoulderelbowwristhipkneeankle

4rightconfidence

truebody partbody part22221Confidence score

x2123

y2223

Stage100Stage100Coordinates adjusted to go from 0 to 100.

Open an interface page for different machine learning models.

training using cameratraining using camera training using microphone posenet tensorflow.js

Reports a list of poses. Use 'pose property' to get the locations of body parts and the confidences that the locations are correct.

de:ist _ leer?

false

Reports the value of the 'key' in a table that is a list of pairs of keys and values.

confidence it is a person confidence there is a nose location of nose confidence there is a left eye location of left eye confidence there is a right eye location of right eye confidence there is a left ear location of left ear confidence there is a right ear location of right ear confidence there is a left shoulder location of leff shoulder confidence there is a right shoulder location of right shoulder confidence there is a left elbow location of left elbow confidence there is a right elbow location of right elbow confidence there is a left wrist location of left wrist confidence there is a right wrist location of right wrist confidence there is a left hip location of left hip confidence there is a right hip location of right hip confidence there is a left knee location of left knee confidence there is a right knee location of right knee confidence there is a left ankle location of left ankle confidence there is a right ankle location of right ankletrue

50score,0.5056843050406314keypointsscore,0.9969497323036194part,nosepositionx,244.84248199462894y,214.41022058451395score,0.9969692826271057part,leftEyepositionx,278.6179848098755y,192.00096841184248score,0.9994669556617737part,rightEyepositionx,207.60382568359378y,187.48261706429236score,0.8197007775306702part,leftEarpositionx,308.99735809326177y,234.7467325340887score,0.9786230325698853part,rightEarpositionx,153.5744448852539y,225.06061779045908score,0.9414733648300171part,leftShoulderpositionx,359.55454406738284y,368.55197041671465score,0.7212380170822144part,rightShoulderpositionx,96.06618499755861y,383.83863247699617score,0.09950163215398788part,leftElbowpositionx,381.3642245483399y,452.38845161769694score,0.008086899295449257part,rightElbowpositionx,65.5315341949463y,416.88132149832586score,0.9721224308013916part,leftWristpositionx,295.03641265869146y,350.4256016275157score,0.9258188009262085part,rightWristpositionx,205.60816558837894y,348.28906574604673score,0.11740545183420181part,leftHippositionx,339.44617141723637y,395.09417042228745score,0.005354748107492924part,rightHippositionx,131.60441684246064y,393.1839055600373score,0.006671881768852472part,leftKneepositionx,345.8398163509369y,410.9568630242199score,0.0015517219435423613part,rightKneepositionx,120.79343826293947y,388.2956975143148score,0.004998327698558569part,leftAnklepositionx,324.90921386718753y,363.5358543869871score,0.0007001285557635128part,rightAnklepositionx,161.21215454101565y,370.312071024260959401321091014940100true1