利用OpenCV和MediaPipe库——吸烟检测（姿态监控） - IT评测·应用市场-qidao123.com

import cv2
import numpy as np
import dlib
import mediapipe as mp
# 初始化MediaPipe手部检测
mp_hands = mp.solutions.hands
hands = mp_hands.Hands(
max_num_hands=2,
min_detection_confidence=0.7,
min_tracking_confidence=0.5
)
# 初始化dlib人脸检测
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
# 加载YOLOv3模型（需包含自定义训练的香烟类别）
net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
layer_names = net.getLayerNames()
output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers().flatten()]
with open("coco.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
def is_holding_cigarette(hand_bbox, cigarette_bboxes, iou_threshold=0.3):
"""判断手部是否持有香烟（基于IOU）"""
for cig_bbox in cigarette_bboxes:
# 计算IOU
x1 = max(hand_bbox[0], cig_bbox[0])
y1 = max(hand_bbox[1], cig_bbox[1])
x2 = min(hand_bbox[2], cig_bbox[2])
y2 = min(hand_bbox[3], cig_bbox[3])
intersection = max(0, x2 - x1) * max(0, y2 - y1)
area_hand = (hand_bbox[2] - hand_bbox[0]) * (hand_bbox[3] - hand_bbox[1])
area_cig = (cig_bbox[2] - cig_bbox[0]) * (cig_bbox[3] - cig_bbox[1])
iou = intersection / (area_hand + area_cig - intersection)
if iou > iou_threshold:
return True
return False
def detect_smoking(frame):
# 转换为RGB格式（MediaPipe需要）
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# 手部检测
hand_bboxes = []
results = hands.process(rgb_frame)
if results.multi_hand_landmarks:
for landmarks in results.multi_hand_landmarks:
# 获取手部边界框
x_coords = [lm.x * frame.shape[1] for lm in landmarks.landmark]
y_coords = [lm.y * frame.shape[0] for lm in landmarks.landmark]
x_min, x_max = min(x_coords), max(x_coords)
y_min, y_max = min(y_coords), max(y_coords)
hand_bboxes.append((x_min, y_min, x_max, y_max))
cv2.rectangle(frame, (int(x_min), int(y_min)),
(int(x_max), int(y_max)), (255, 0, 0), 2)
# YOLOv3香烟检测
cigarette_bboxes = []
blob = cv2.dnn.blobFromImage(frame, 0.00392, (320, 320), swapRB=True)
net.setInput(blob)
outs = net.forward(output_layers)
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5 and classes[class_id] == "cigarette":
center_x = int(detection[0] * frame.shape[1])
center_y = int(detection[1] * frame.shape[0])
w = int(detection[2] * frame.shape[1])
h = int(detection[3] * frame.shape[0])
x = center_x - w // 2
y = center_y - h // 2
cigarette_bboxes.append((x, y, x + w, y + h))
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
# 人脸关键点检测
mouth_positions = []
faces = detector(frame)
for face in faces:
landmarks = predictor(frame, face)
mouth_points = [(landmarks.part(i).x, landmarks.part(i).y)
for i in range(48, 68)]
mouth_center = np.mean(mouth_points, axis=0)
mouth_positions.append(mouth_center)
# 绘制嘴巴区域
cv2.polylines(frame, [np.array(mouth_points, dtype=np.int32)],
True, (0, 0, 255), 2)
# 综合判断逻辑
warning = False
for hand in hand_bboxes:
# 判断是否持烟
holding = is_holding_cigarette(hand, cigarette_bboxes)
# 计算手部中心点
hand_center = ((hand[0] + hand[2]) / 2, (hand[1] + hand[3]) / 2)
# 找最近的人脸
min_distance = float('inf')
for mouth in mouth_positions:
distance = np.sqrt((hand_center[0] - mouth[0]) ** 2 +
(hand_center[1] - mouth[1]) ** 2)
min_distance = min(min_distance, distance)
# 判断条件
if holding and min_distance < 100: # 持烟且距离<100像素
warning = True
elif min_distance < 50: # 未持烟但手部靠近嘴部
cv2.putText(frame, "Potential Smoking!",
(int(hand[0]), int(hand[1]) - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 255), 2)
if warning:
cv2.putText(frame, "WARNING: Active Smoking Detected!",
(20, 50), cv2.FONT_HERSHEY_SIMPLEX,
1, (0, 0, 255), 3, cv2.LINE_AA)
return frame
# 视频处理主循环
cap = cv2.VideoCapture(0)
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
frame = cv2.flip(frame, 1) # 镜像翻转
result = detect_smoking(frame)
cv2.imshow('Smoking Detection', result)
if cv2.waitKey(1) == 27:
break
cap.release()
cv2.destroyAllWindows()

复制代码