Python OpenCV学习笔记之:图像Lucas-Kanad流光算法
2016-12-08 00:00
836 查看
摘要: 代码地址:https://github.com/juxiangwu/tensorflow-learning/tree/master/opencv
# -*- coding: utf-8 -*- """ 图像Lucas-Kanad流光算法 Lucas-Kanad算法请参考:http://www.cnblogs.com/hrlnw/p/3600291.html """ import numpy as np import cv2 cap = cv2.VideoCapture(0) # ShiTomasi角点检测参数 feature_params = dict( maxCorners = 100, qualityLevel = 0.3, minDistance = 7, blockSize = 7 ) # lucas kanade算法参数 lk_params = dict( winSize = (15,15), maxLevel = 2, criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 0.03)) # 随机颜色 color = np.random.randint(0,255,(100,3)) # 读取第一张帧并进行角点检测 ret, old_frame = cap.read() while True: ret, old_frame = cap.read() if ret == True: break old_gray = cv2.cvtColor(old_frame, cv2.COLOR_BGR2GRAY) p0 = cv2.goodFeaturesToTrack(old_gray, mask = None, **feature_params) mask = np.zeros_like(old_frame) while True: ret, frame = cap.read() frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # 计算流光 p1, st, err = cv2.calcOpticalFlowPyrLK(old_gray, frame_gray, p0, None, **lk_params) if p1 is None or p0 is None: cv2.imshow("frame",frame) continue # 选择条件好的点 good_new = p1[st == 1] good_old = p0[st == 1] # 绘制跟踪 for i, (new, old) in enumerate(zip(good_new, good_old)): a, b = new.ravel() c, d = old.ravel() mask = cv2.line(mask, (a, b), (c, d), color[i].tolist(), 2) frame = cv2.circle(frame, (a, b), 5, color[i].tolist(), -1) img = cv2.add(frame, mask) cv2.imshow('frame',mask) k = cv2.waitKey(10) & 0xFF if k == 27: break # 更新点和帧 old_gray = frame_gray.copy() p0 = good_new.reshape(-1, 1, 2) cap.release() cv2.destroyAllWindows()
相关文章推荐
- Python OpenCV学习笔记之:图像梯度处理:Laplacian,Sobel算子
- Python OpenCV学习笔记之:计算彩色图像各通道的直方图及图像区域直方图
- Python OpenCV学习笔记之:分水岭算法分割图像
- Python OpenCV学习笔记之:图像数学形态操作
- Python OpenCV学习笔记之:使用Grabcut算法进行图像背景和前景分割
- opencv python学习笔记(五)图像的算术与
- 【基于C++和Python的Opencv3学习笔记之图像载入、显示和保存】
- Opencv Python版学习笔记(一)图像直方图
- Python3+OpenCV学习笔记(一):图像加载、显示和保存
- Python OpenCV学习笔记之:图像阈值操作
- Python OpenCV学习笔记之:图像计算
- python3.6.3+opencv3.3.0学习笔记六--存储视频和图像
- Python OpenCV学习笔记之:图像轮廓处理
- Python OpenCV学习笔记之:图像直方图反向投影(backprojection)原理简单实现
- Python OpenCV学习笔记之:图像直方图反向投影
- Python OpenCV学习笔记之:灰度图像的直方图计算
- OpenCV之Python学习笔记(1)(2): 图像的载入、显示和保存 图像元素的访问、通道分离与合并
- Python3+OpenCV学习笔记(二):图像几何变换及补边、裁剪
- python3.6.3+opencv3.3.0学习笔记三--本地图像显示
- Python OpenCV学习笔记之:图像模板匹配