OpenCV(Open Source Computer Vision Library)是一个开源的计算机视觉和机器学习软件库。OpenCV-Python是其Python接口,结合了OpenCV C++ API和Python语言的特点,使得在Python中实现高效、强大的计算机视觉任务变得简单。
在Python环境中,通常可以使用pip进行安装:
pip install opencv-python
如果需要包含OpenCV的contrib模块,可以使用:
pip install opencv-contrib-python
import cv2
image = cv2.imread('image.jpg')
cv2.imshow('Image', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imwrite('gray_image.jpg', gray_image)
cap = cv2.VideoCapture('video.mp4')
while True:
ret, frame = cap.read()
if not ret:
break
gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imshow('Video', gray_frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
OpenCV提供了预训练的Haar级联分类器,可以用于检测图像中的人脸。以下是一个简单的示例:
import cv2
# 加载Haar级联分类器
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
# 读取图像
img = cv2.imread('group_photo.jpg')
# 转换为灰度图
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 检测人脸
faces = face_cascade.detectMultiScale(gray, 1.1, 4)
# 为每个检测到的人脸画矩形
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2)
# 显示结果
cv2.imshow('Detected Faces', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
OpenCV中的Meanshift和Camshift算法可以用于跟踪视频中的移动对象。
import cv2
# 初始化视频捕获对象
cap = cv2.VideoCapture('tracking_video.mp4')
# 读取第一帧
ret, frame = cap.read()
# 设置初始跟踪窗口
x, y, w, h = 300, 200, 100, 50
track_window = (x, y, w, h)
# 设置ROI用于跟踪
roi = frame[y:y+h, x:x+w]
# 转换为HSV并创建掩模
hsv_roi = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv_roi, np.array((0., 60., 32.)), np.array((180., 255., 255.)))
# 计算直方图,用于反向投影
roi_hist = cv2.calcHist([hsv_roi], [0], mask, [180], [0, 180])
cv2.normalize(roi_hist, roi_hist, 0, 255, cv2.NORM_MINMAX)
# 设置终止条件,迭代10次或移动至少1 pt
term_crit = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1)
while True:
ret, frame = cap.read()
if not ret:
break
# 转换为HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
dst = cv2.calcBackProject([hsv], [0], roi_hist, [0, 180], 1)
# 应用Meanshift获取新位置
ret, track_window = cv2.meanShift(dst, track_window, term_crit)
# 在图像上绘制它
x, y, w, h = track_window
img2 = cv2.rectangle(frame, (x, y), (x+w, y+h), 255, 2)
cv2.imshow('Meanshift Tracking', img2)
k = cv2.waitKey(60) & 0xff
if k == 27:
break
cv2.destroyAllWindows()
cap.release()
使用SIFT、SURF等算法进行特征提取和匹配,可以用于图像拼接、3D重建等。
import cv2
import numpy as np
# 读取两幅图像
img1 = cv2.imread('box.png', cv2.IMREAD_GRAYSCALE)
img2 = cv2.imread('box_in_scene.png', cv2.IMREAD_GRAYSCALE)
# 初始化SIFT检测器
sift = cv2.SIFT_create()
# 计算关键点和描述符
kp1, des1 = sift.detectAndCompute(img1, None)
kp2, des2 = sift.detectAndCompute(img2, None)
# 使用BFMatcher进行匹配
bf = cv2.BFMatcher()
matches = bf.knnMatch(des1, des2, k=2)
# 应用比率测试
good = []
for m, n in matches:
if m.distance < 0.75 * n.distance:
good.append(m)
# 绘制匹配结果
img3 = cv2.drawMatches(img1, kp1, img2, kp2, good, None, flags=2)
cv2.imshow('Feature Matches', img3)
cv2.waitKey(0)
cv2.destroyAllWindows()
深度学习模型和算法时,OpenCV-Python可能需要额外的依赖项,如TensorFlow、PyTorch或ONNX Runtime等。
import cv2
import tensorflow as tf
# 加载TensorFlow的物体检测模型(假设已经有一个冻结的GraphDef模型)
model_path = 'frozen_inference_graph.pb'
labels_path = 'mscoco_label_map.pbtxt'
num_classes = 90
# 加载模型和标签
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(model_path, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# 加载标签
label_map = label_map_util.load_labelmap(labels_path)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=num_classes, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
# 读取图像
image_np = np.array(cv2.imread('object_detection.jpg'))
# 执行物体检测
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# 扩展图像维度
image_np_expanded = np.expand_dims(image_np, axis=0)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# 运行模型
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={
image_tensor: image_np_expanded})
# 可视化结果
v = visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
# 显示图像
cv2.imshow('Object Detection', image_np)
cv2.waitKey(0)
cv2.destroyAllWindows()
import cv2
# 加载人脸识别模型(假设已经训练好了)
face_recognizer = cv2.face.LBPHFaceRecognizer_create()
face_recognizer.read('face_model.yml')
# 加载Haar级联分类器
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
# 启动视频捕获
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read()
if not ret:
break
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.1, 4)
for (x, y, w, h) in faces:
face_roi = gray[y:y+h, x:x+w]
# 进行预测
label, confidence = face_recognizer.predict(face_roi)
cv2.putText(frame, str(label), (x, y-5), cv2.FONT_HERSHEY_PLAIN, 1.5, (0, 255, 0), 2)
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.imshow('Face Recognition', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
OpenCV-Python是一个非常强大的工具,它为计算机视觉任务提供了一个丰富的函数库。通过结合深度学习和其他机器学习技术,OpenCV-Python可以用于解决复杂的问题,如图像识别、物体检测、人脸识别等。随着技术的发展,OpenCV-Python也在不断更新和改进,以支持更多的功能和算法。如果您对特定功能或应用有更多的问题,欢迎继续提问。
更多【开源-开源计算机视觉库opencv-python详解】相关视频教程:www.yxfzedu.com