mirror of
https://git.roussel.pro/telecom-paris/pact.git
synced 2026-02-09 10:30:17 +01:00
Début implémentation notes autres dans manager backend
This commit is contained in:
Quentin Roussel
@@ -5,116 +5,192 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv()
|
||||
|
||||
camera_id = int(os.getenv("CAMERA_ID"))
|
||||
mp_hands = mp.solutions.hands
|
||||
cap = cv2.VideoCapture(camera_id)
|
||||
|
||||
def prodScalaire(V1,V2):
|
||||
return V1[0]*V2[0]+V1[1]*V2[1]/(np.sqrt(V1[0]**2+V1[1]**2)*np.sqrt(V2[0]**2+V2[1]**2))
|
||||
|
||||
|
||||
class HandDetector():
|
||||
def __init__(self):
|
||||
self.camera_id = int(os.getenv("CAMERA_ID"))
|
||||
self.mp_drawing = mp.solutions.drawing_utils
|
||||
self.mp_drawing_styles = mp.solutions.drawing_styles
|
||||
self.mp_hands = mp.solutions.hands
|
||||
self.cap = cv2.VideoCapture(self.camera_id)
|
||||
self.hands = self.mp_hands.Hands(
|
||||
model_complexity=0,
|
||||
min_detection_confidence=0.5,
|
||||
min_tracking_confidence=0.5)
|
||||
#Paramètres
|
||||
self.BUFFER_LENGTH = 60
|
||||
self.DETECTION_THRESHOLD = 3/4
|
||||
def __init__(self):
|
||||
self.hands = mp_hands.Hands(
|
||||
model_complexity=0,
|
||||
min_detection_confidence=0.5,
|
||||
min_tracking_confidence=0.5)
|
||||
#Paramètres
|
||||
self.BUFFER_LENGTH = 200
|
||||
self.DETECTION_THRESHOLD = 1/2
|
||||
self.resultBuffer = []
|
||||
|
||||
self.resultBuffer = []
|
||||
|
||||
def reset(self):
|
||||
self.resultBuffer = []
|
||||
def reset(self):
|
||||
self.resultBuffer = []
|
||||
|
||||
def reconnaissancePouce(self,handLandmarks):
|
||||
etatDuPouce=["neutre","thumbs_down","thumbs_up"]
|
||||
i=0
|
||||
j=0
|
||||
for cpt in range (0,4):
|
||||
V1=[handLandmarks[(4*cpt)+5][0]-handLandmarks[(4*cpt)+0][0],handLandmarks[(4*cpt)+5][1]-handLandmarks[(4*cpt)+0][1]]
|
||||
V2=[handLandmarks[(4*cpt)+8][0]-handLandmarks[(4*cpt)+5][0],handLandmarks[(4*cpt)+8][1]-handLandmarks[(4*cpt)+5][1]]
|
||||
j1=np.dot(V1,V2)
|
||||
V1=[handLandmarks[(4*cpt)+6][0]-handLandmarks[(4*cpt)+5][0],handLandmarks[(4*cpt)+6][1]-handLandmarks[(4*cpt)+5][1]]
|
||||
V2=[handLandmarks[(4*cpt)+8][0]-handLandmarks[(4*cpt)+6][0],handLandmarks[(4*cpt)+8][1]-handLandmarks[(4*cpt)+6][1]]
|
||||
j2=np.dot(V1,V2)
|
||||
if (j1>0 and j2>0):
|
||||
return etatDuPouce[0]
|
||||
V1=[handLandmarks[4][0]-handLandmarks[1][0],handLandmarks[4][1]-handLandmarks[1][1]]
|
||||
V2=[handLandmarks[2][0]-handLandmarks[1][0],handLandmarks[2][1]-handLandmarks[1][1]]
|
||||
if((np.dot(V1,V2))>0 and (handLandmarks[4][1]>handLandmarks[2][1])):
|
||||
i=1
|
||||
elif(np.dot(V1,V2)>0 and handLandmarks[4][1]<handLandmarks[2][1]):
|
||||
i=2
|
||||
return etatDuPouce[i]
|
||||
def analyse_pouce(self, handLandmarks):
|
||||
etatDuPouce = ["neutre","thumbs_down","thumbs_up"]
|
||||
i = 0
|
||||
j = 0
|
||||
for cpt in range (0,4):
|
||||
V1=[handLandmarks[(4*cpt)+5][0]-handLandmarks[(4*cpt)+0][0],handLandmarks[(4*cpt)+5][1]-handLandmarks[(4*cpt)+0][1]]
|
||||
V2=[handLandmarks[(4*cpt)+8][0]-handLandmarks[(4*cpt)+5][0],handLandmarks[(4*cpt)+8][1]-handLandmarks[(4*cpt)+5][1]]
|
||||
j1=np.dot(V1,V2)
|
||||
V1=[handLandmarks[(4*cpt)+6][0]-handLandmarks[(4*cpt)+5][0],handLandmarks[(4*cpt)+6][1]-handLandmarks[(4*cpt)+5][1]]
|
||||
V2=[handLandmarks[(4*cpt)+8][0]-handLandmarks[(4*cpt)+6][0],handLandmarks[(4*cpt)+8][1]-handLandmarks[(4*cpt)+6][1]]
|
||||
j2=np.dot(V1,V2)
|
||||
if (j1>0 and j2>0):
|
||||
return etatDuPouce[0]
|
||||
V1=[handLandmarks[4][0]-handLandmarks[1][0],handLandmarks[4][1]-handLandmarks[1][1]]
|
||||
V2=[handLandmarks[2][0]-handLandmarks[1][0],handLandmarks[2][1]-handLandmarks[1][1]]
|
||||
if((np.dot(V1,V2))>0 and (handLandmarks[4][1]>handLandmarks[2][1])):
|
||||
i=1
|
||||
elif(np.dot(V1,V2)>0 and handLandmarks[4][1]<handLandmarks[2][1]):
|
||||
i=2
|
||||
return etatDuPouce[i]
|
||||
|
||||
|
||||
def detect(self):
|
||||
if self.cap.isOpened():
|
||||
success, image = self.cap.read()
|
||||
if not success:
|
||||
print("Ignoring empty camera frame.")
|
||||
# If loading a video, use 'break' instead of 'continue'.
|
||||
return False
|
||||
def loop(self):
|
||||
if cap.isOpened():
|
||||
success, image = cap.read()
|
||||
if not success:
|
||||
print("Ignoring empty camera frame.")
|
||||
# If loading a video, use 'break' instead of 'continue'.
|
||||
return False
|
||||
|
||||
# To improve performance, optionally mark the image as not writeable to
|
||||
# pass by reference.
|
||||
image.flags.writeable = False
|
||||
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
results = self.hands.process(image)
|
||||
# To improve performance, optionally mark the image as not writeable to
|
||||
# pass by reference.
|
||||
image.flags.writeable = False
|
||||
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
results = self.hands.process(image)
|
||||
|
||||
if results.multi_hand_landmarks:
|
||||
handsPositions = []
|
||||
for hand_landmarks in results.multi_hand_landmarks:
|
||||
handLandmarks = []
|
||||
# Fill list with x and y positions of each landmark
|
||||
for landmarks in hand_landmarks.landmark:
|
||||
handLandmarks.append([landmarks.x, landmarks.y])
|
||||
#On ajoute la position de chaque mains a une liste
|
||||
handsPositions.append([self.reconnaissancePouce(handLandmarks), handLandmarks])
|
||||
|
||||
#On calcule le résultat suivant la position des deux mains
|
||||
if(len(handsPositions) == 2):
|
||||
if(handsPositions[0][0] == handsPositions[1][0]):
|
||||
thumbState = handsPositions[0]
|
||||
handLandmarks = handsPositions[0][1]
|
||||
elif(handsPositions[0][0] == "neutre"):
|
||||
thumbState = handsPositions[1]
|
||||
handLandmarks = handsPositions[1][1]
|
||||
elif(handsPositions[1][0] == "neutre"):
|
||||
thumbState = handsPositions[0][0]
|
||||
handLandmarks = handsPositions[0][1]
|
||||
else:
|
||||
thumbState = "neutre"
|
||||
else:
|
||||
thumbState = handsPositions[0][0]
|
||||
handsLandmarks = handsPositions[0][1]
|
||||
if results.multi_hand_landmarks:
|
||||
handsPositions = []
|
||||
for hand_landmarks in results.multi_hand_landmarks:
|
||||
handLandmarks = []
|
||||
# Fill list with x and y positions of each landmark
|
||||
for landmarks in hand_landmarks.landmark:
|
||||
handLandmarks.append([landmarks.x, landmarks.y])
|
||||
#On ajoute la position de chaque mains a une liste
|
||||
handsPositions.append([self.analyse_pouce(handLandmarks), handLandmarks])
|
||||
|
||||
#On calcule le résultat suivant la position des deux mains
|
||||
if(len(handsPositions) == 2):
|
||||
if(handsPositions[0][0] == handsPositions[1][0]):
|
||||
thumbState = handsPositions[0]
|
||||
handLandmarks = handsPositions[0][1]
|
||||
elif(handsPositions[0][0] == "neutre"):
|
||||
thumbState = handsPositions[1]
|
||||
handLandmarks = handsPositions[1][1]
|
||||
elif(handsPositions[1][0] == "neutre"):
|
||||
thumbState = handsPositions[0][0]
|
||||
handLandmarks = handsPositions[0][1]
|
||||
else:
|
||||
thumbState = "neutre"
|
||||
else:
|
||||
thumbState = handsPositions[0][0]
|
||||
handsLandmarks = handsPositions[0][1]
|
||||
|
||||
self.resultBuffer.append(thumbState)
|
||||
if(len(self.resultBuffer) > self.BUFFER_LENGTH):
|
||||
self.resultBuffer.pop(0)
|
||||
|
||||
thumbsUpCount = sum(map(lambda x : x == "thumbs_up", self.resultBuffer))
|
||||
thumbsDownCount = sum(map(lambda x : x == "thumbs_down", self.resultBuffer))
|
||||
self.resultBuffer.append(thumbState)
|
||||
if(len(self.resultBuffer) > self.BUFFER_LENGTH):
|
||||
self.resultBuffer.pop(0)
|
||||
|
||||
thumbsUpCount = sum(map(lambda x : x == "thumbs_up", self.resultBuffer))
|
||||
thumbsDownCount = sum(map(lambda x : x == "thumbs_down", self.resultBuffer))
|
||||
|
||||
if(thumbsUpCount > self.DETECTION_THRESHOLD * self.BUFFER_LENGTH):
|
||||
result = "thumbs_up"
|
||||
elif(thumbsDownCount > self.DETECTION_THRESHOLD * self.BUFFER_LENGTH):
|
||||
result = "thumbs_down"
|
||||
else:
|
||||
result = False
|
||||
if(thumbsUpCount > self.DETECTION_THRESHOLD * self.BUFFER_LENGTH):
|
||||
result = "thumbs_up"
|
||||
elif(thumbsDownCount > self.DETECTION_THRESHOLD * self.BUFFER_LENGTH):
|
||||
result = "thumbs_down"
|
||||
else:
|
||||
result = False
|
||||
|
||||
progress = 0
|
||||
if thumbState == "thumbs_up":
|
||||
progress = thumbsUpCount / (self.BUFFER_LENGTH * self.DETECTION_THRESHOLD)
|
||||
elif thumbState == "thumbs_down":
|
||||
progress = thumbsDownCount / (self.BUFFER_LENGTH * self.DETECTION_THRESHOLD)
|
||||
|
||||
if(thumbState != "neutre"):
|
||||
return thumbState, handLandmarks[9], np.linalg.norm(np.array(handLandmarks[9]) - np.array(handLandmarks[0])), result, progress
|
||||
return False
|
||||
progress = 0
|
||||
if thumbState == "thumbs_up":
|
||||
progress = thumbsUpCount / (self.BUFFER_LENGTH * self.DETECTION_THRESHOLD)
|
||||
elif thumbState == "thumbs_down":
|
||||
progress = thumbsDownCount / (self.BUFFER_LENGTH * self.DETECTION_THRESHOLD)
|
||||
|
||||
if(thumbState != "neutre"):
|
||||
return thumbState, handLandmarks[9], np.linalg.norm(np.array(handLandmarks[9]) - np.array(handLandmarks[0])), result, progress
|
||||
return False
|
||||
|
||||
|
||||
|
||||
class FingerCountDetector():
|
||||
def __init__(self):
|
||||
self.BUFFER_LENGTH = 20
|
||||
self.DETECTION_THRESHOLD = 1/2
|
||||
self.hands = mp_hands.Hands(static_image_mode=False, max_num_hands=2, min_detection_confidence=0.5, min_tracking_confidence=0.5)
|
||||
self.buffer = []
|
||||
|
||||
def reset(self):
|
||||
self.buffer = []
|
||||
|
||||
def getResult(self):
|
||||
stats = [0] * 10
|
||||
for grade in self.buffer:
|
||||
stats[grade-1] = stats[grade-1]+1
|
||||
stats = [stat / self.BUFFER_LENGTH for stat in stats]
|
||||
print(stats)
|
||||
|
||||
if max(stats) > self.DETECTION_THRESHOLD:
|
||||
return stats.index(max(stats)) + 1
|
||||
|
||||
def prodScalaire(self,V1,V2):
|
||||
return (V1[0]*V2[0]+V1[1]*V2[1])/((V1[0]**2+V1[1]**2)**(1/2)*(V2[0]**2+V2[1]**2)**(1/2)) #produit scalaire normalisé
|
||||
|
||||
#Fait le prod scalaire entre deux vecteurs formées par les points d'index (id0,id1) et (id2,id3) dans la liste landmarks
|
||||
def prodScalaireDoigts(self,landmarks,id0,id1,id2,id3):
|
||||
V0= [landmarks[id0].x - landmarks[id1].x, landmarks[id0].y - landmarks[id1].y]
|
||||
V1= [landmarks[id2].x - landmarks[id3].x, landmarks[id2].y - landmarks[id3].y]
|
||||
return self.prodScalaire(V0,V1)
|
||||
# initialisation de la caméra
|
||||
|
||||
#Donne le nombre de doigts levé pour un landmak de main donnée
|
||||
def analyseMain(self,hand_landmarks):
|
||||
finger_count = 0
|
||||
pouce = self.prodScalaireDoigts(hand_landmarks,2,0,4,2)
|
||||
index = self.prodScalaireDoigts(hand_landmarks,8,6,6,0)
|
||||
majeur = self.prodScalaireDoigts(hand_landmarks,12,10,10,0)
|
||||
annulaire= self.prodScalaireDoigts(hand_landmarks,16,14,14,0)
|
||||
auriculaire = self.prodScalaireDoigts(hand_landmarks,20,18,18,0)
|
||||
|
||||
if pouce > 0.905135675:
|
||||
finger_count += 1
|
||||
if index > 0:
|
||||
finger_count += 1
|
||||
if majeur > 0:
|
||||
finger_count += 1
|
||||
if annulaire > 0:
|
||||
finger_count += 1
|
||||
if auriculaire > 0:
|
||||
finger_count += 1
|
||||
return finger_count
|
||||
|
||||
def loop(self):
|
||||
if cap.isOpened():
|
||||
# lecture de la vidéo
|
||||
ret, frame = cap.read()
|
||||
|
||||
# conversion de l'image en RGB
|
||||
image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
||||
|
||||
# détection des mains
|
||||
results = self.hands.process(image)
|
||||
|
||||
if results.multi_hand_landmarks:
|
||||
# détection du nombre de doigts levés
|
||||
finger_count = 0
|
||||
if len(results.multi_hand_landmarks) >0 :
|
||||
finger_count += self.analyseMain(results.multi_hand_landmarks[0].landmark)
|
||||
if len(results.multi_hand_landmarks) >1 :
|
||||
finger_count += self.analyseMain(results.multi_hand_landmarks[1].landmark)
|
||||
self.buffer.append(finger_count)
|
||||
if(len(self.buffer) > self.BUFFER_LENGTH):
|
||||
self.buffer.pop(0)
|
||||
return self.getResult()
|
||||
|
||||
if __name__ == "__main__":
|
||||
h = HandDetector()
|
||||
while(1):
|
||||
print(h.detect())
|
||||
h = FingerCountDetector()
|
||||
while(1):
|
||||
print(h.loop())
|
||||
|
||||
Reference in New Issue
Block a user