前言
dlib提供了dlib.correlation_tracker()类用于跟踪目标。
官方文档入口：http://dlib.net/python/index.html#dlib.correlation_tracker
不复杂，就不介绍了，后面会直接给出两个程序，有注释。
程序1
# -*- coding: utf-8 -*-
import sys
import dlib
import cv2
tracker = dlib.correlation_tracker() # 导入correlation_tracker()类
cap = cv2.VideoCapture(0) # OpenCV打开摄像头
start_flag = True # 标记，是否是第一帧，若在第一帧需要先初始化
selection = None # 实时跟踪鼠标的跟踪区域
track_window = None # 要检测的物体所在区域
drag_start = None # 标记，是否开始拖动鼠标
# 鼠标点击事件回调函数
def onMouseClicked(event, x, y, flags, param):
global selection, track_window, drag_start # 定义全局变量
if event == cv2.EVENT_LBUTTONDOWN: # 鼠标左键按下
drag_start = (x, y)
track_window = None
if drag_start: # 是否开始拖动鼠标，记录鼠标位置
xMin = min(x, drag_start[0])
yMin = min(y, drag_start[1])
xMax = max(x, drag_start[0])
yMax = max(y, drag_start[1])
selection = (xMin, yMin, xMax, yMax)
if event == cv2.EVENT_LBUTTONUP: # 鼠标左键松开
drag_start = None
track_window = selection
selection = None
if __name__ == '__main__':
cv2.namedWindow("image", cv2.WINDOW_AUTOSIZE)
cv2.setMouseCallback("image", onMouseClicked)
# opencv的bgr格式图片转换成rgb格式
# b, g, r = cv2.split(frame)
# frame2 = cv2.merge([r, g, b])
while(1):
ret, frame = cap.read() # 从摄像头读入1帧
if start_flag == True: # 如果是第一帧，需要先初始化
# 这里是初始化，窗口中会停在当前帧，用鼠标拖拽一个框来指定区域，随后会跟踪这个目标；我们需要先找到目标才能跟踪不是吗？
while True:
img_first = frame.copy() # 不改变原来的帧，拷贝一个新的出来
if track_window: # 跟踪目标的窗口画出来了，就实时标出来
cv2.rectangle(img_first, (track_window[0], track_window[1]), (track_window[2], track_window[3]), (0,0,255), 1)
elif selection: # 跟踪目标的窗口随鼠标拖动实时显示
cv2.rectangle(img_first, (selection[0], selection[1]), (selection[2], selection[3]), (0,0,255), 1)
cv2.imshow("image", img_first)
# 按下回车，退出循环
if cv2.waitKey(5) == 13:
break
start_flag = False # 初始化完毕，不再是第一帧了
tracker.start_track(frame, dlib.rectangle(track_window[0], track_window[1], track_window[2], track_window[3])) # 跟踪目标，目标就是选定目标窗口中的
else:
tracker.update(frame) # 更新，实时跟踪
box_predict = tracker.get_position() # 得到目标的位置
cv2.rectangle(frame,(int(box_predict.left()),int(box_predict.top())),(int(box_predict.right()),int(box_predict.bottom())),(0,255,255),1) # 用矩形框标注出来
cv2.imshow("image", frame)
# 如果按下ESC键，就退出
if cv2.waitKey(10) == 27:
break
cap.release()
cv2.destroyAllWindows()注：如果程序卡了，就调一下cv2.waitKey()中的参数，也就是延时时间，调小即可。
运行结果
初始时，窗口中只会显示第一帧的图像；
使用鼠标拖拽一个框，红框中目标后，按回车，设置框内为识别目标；
实时识别，以橙框标出；
按ESC键退出。
（csdn只能上传2M的图片，真心难受）
程序2
由于前面那个程序，只是熟悉下函数写的，我觉得用起来蛋疼，所以又重新封装了一下。看起来舒服多了。
# -*- coding: utf-8 -*-
import sys
import dlib
import cv2
class myCorrelationTracker(object):
def __init__(self, windowName='default window', cameraNum=0):
# 自定义几个状态标志
self.STATUS_RUN_WITHOUT_TRACKER = 0 # 不跟踪目标，但是实时显示
self.STATUS_RUN_WITH_TRACKER = 1 # 跟踪目标，实时显示
self.STATUS_PAUSE = 2 # 暂停，卡在当前帧
self.STATUS_BREAK = 3 # 退出
self.status = self.STATUS_RUN_WITHOUT_TRACKER # 指示状态的变量
# 这几个跟前面程序1定义的变量一样
self.track_window = None # 实时跟踪鼠标的跟踪区域
self.drag_start = None # 要检测的物体所在区域
self.start_flag = True # 标记，是否开始拖动鼠标
# 创建好显示窗口
cv2.namedWindow(windowName, cv2.WINDOW_AUTOSIZE)
cv2.setMouseCallback(windowName, self.onMouseClicked)
self.windowName = windowName
# 打开摄像头
self.cap = cv2.VideoCapture(cameraNum)
# correlation_tracker()类，跟踪器，跟程序1中一样
self.tracker = dlib.correlation_tracker()
# 当前帧
self.frame = None
# 按键处理函数
def keyEventHandler(self):
keyValue = cv2.waitKey(5) # 每隔5ms读取一次按键的键值
if keyValue == 27: # ESC
self.status = self.STATUS_BREAK
if keyValue == 32: # 空格
if self.status != self.STATUS_PAUSE: # 按下空格，暂停播放，可以选定跟踪的区域
#print self.status
self.status = self.STATUS_PAUSE
#print self.status
else: # 再按次空格，重新播放，但是不进行目标识别
if self.track_window:
self.status = self.STATUS_RUN_WITH_TRACKER
self.start_flag = True
else:
self.status = self.STATUS_RUN_WITHOUT_TRACKER
if keyValue == 13: # 回车
#print '**'
if self.status == self.STATUS_PAUSE: # 按下空格之后
if self.track_window: # 如果选定了区域，再按回车，表示确定选定区域为跟踪目标
self.status = self.STATUS_RUN_WITH_TRACKER
self.start_flag = True
# 任务处理函数
def processHandler(self):
# 不跟踪目标，但是实时显示
if self.status == self.STATUS_RUN_WITHOUT_TRACKER:
ret, self.frame = self.cap.read()
cv2.imshow(self.windowName, self.frame)
# 暂停，暂停时使用鼠标拖动红框，选择目标区域，与程序1类似
elif self.status == self.STATUS_PAUSE:
img_first = self.frame.copy() # 不改变原来的帧，拷贝一个新的变量出来
if self.track_window: # 跟踪目标的窗口画出来了，就实时标出来
cv2.rectangle(img_first, (self.track_window[0], self.track_window[1]), (self.track_window[2], self.track_window[3]), (0,0,255), 1)
elif self.selection: # 跟踪目标的窗口随鼠标拖动实时显示
cv2.rectangle(img_first, (self.selection[0], self.selection[1]), (self.selection[2], self.selection[3]), (0,0,255), 1)
cv2.imshow(self.windowName, img_first)
# 退出
elif self.status == self.STATUS_BREAK:
self.cap.release() # 释放摄像头
cv2.destroyAllWindows() # 释放窗口
sys.exit() # 退出程序
# 跟踪目标，实时显示
elif self.status == self.STATUS_RUN_WITH_TRACKER:
ret, self.frame = self.cap.read() # 从摄像头读取一帧
if self.start_flag: # 如果是第一帧，需要先初始化
self.tracker.start_track(self.frame, dlib.rectangle(self.track_window[0], self.track_window[1], self.track_window[2], self.track_window[3])) # 开始跟踪目标
self.start_flag = False # 不再是第一帧
else:
self.tracker.update(self.frame) # 更新
# 得到目标的位置，并显示
box_predict = self.tracker.get_position()
cv2.rectangle(self.frame,(int(box_predict.left()),int(box_predict.top())),(int(box_predict.right()),int(box_predict.bottom())),(0,255,255),1)
cv2.imshow(self.windowName, self.frame)
# 鼠标点击事件回调函数
def onMouseClicked(self, event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN: # 鼠标左键按下
self.drag_start = (x, y)
self.track_window = None
if self.drag_start: # 是否开始拖动鼠标，记录鼠标位置
xMin = min(x, self.drag_start[0])
yMin = min(y, self.drag_start[1])
xMax = max(x, self.drag_start[0])
yMax = max(y, self.drag_start[1])
self.selection = (xMin, yMin, xMax, yMax)
if event == cv2.EVENT_LBUTTONUP: # 鼠标左键松开
self.drag_start = None
self.track_window = self.selection
self.selection = None
def run(self):
while(1):
self.keyEventHandler()
self.processHandler()
if __name__ == '__main__':
testTracker = myCorrelationTracker(windowName='image', cameraNum=1)
testTracker.run()
注：如果程序卡了，就调一下cv2.waitKey()中的参数，也就是延时时间，调小即可。
运行结果
操作有一些改变：
初始时，会自动从摄像头采集图像显示；
按下空格，暂停；此时若再按空格，恢复实时显示，但不进行目标跟踪；
暂停时，拖动鼠标会显示红框，按下回车，将红框内物体视为目标进行识别；
随后实时识别，以橙框标出；
按ESC键退出。
官方例程
#!/usr/bin/python
# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
#
# This example shows how to use the correlation_tracker from the dlib Python
# library. This object lets you track the position of an object as it moves
# from frame to frame in a video sequence. To use it, you give the
# correlation_tracker the bounding box of the object you want to track in the
# current video frame. Then it will identify the location of the object in
# subsequent frames.
#
# In this particular example, we are going to run on the
# video sequence that comes with dlib, which can be found in the
# examples/video_frames folder. This video shows a juice box sitting on a table
# and someone is waving the camera around. The task is to track the position of
# the juice box as the camera moves around.
#
#
# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
# You can install dlib using the command:
# pip install dlib
#
# Alternatively, if you want to compile dlib yourself then go into the dlib
# root folder and run:
# python setup.py install
# or
# python setup.py install --yes USE_AVX_INSTRUCTIONS
# if you have a CPU that supports AVX instructions, since this makes some
# things run faster.
#
# Compiling dlib should work on any operating system so long as you have
# CMake and boost-python installed. On Ubuntu, this can be done easily by
# running the command:
# sudo apt-get install libboost-python-dev cmake
#
# Also note that this example requires scikit-image which can be installed
# via the command:
# pip install scikit-image
# Or downloaded from http://scikit-image.org/download.html.
import os
import glob
import dlib
from skimage import io
# Path to the video frames
video_folder = os.path.join("..", "examples", "video_frames")
# Create the correlation tracker - the object needs to be initialized
# before it can be used
tracker = dlib.correlation_tracker()
win = dlib.image_window()
# We will track the frames as we load them off of disk
for k, f in enumerate(sorted(glob.glob(os.path.join(video_folder, "*.jpg")))):
print("Processing Frame {}".format(k))
img = io.imread(f)
# We need to initialize the tracker on the first frame
if k == 0:
# Start a track on the juice box. If you look at the first frame you
# will see that the juice box is contained within the bounding
# box (74, 67, 112, 153).
tracker.start_track(img, dlib.rectangle(74, 67, 112, 153))
else:
# Else we just attempt to track from the previous frame
tracker.update(img)
win.clear_overlay()
win.set_image(img)
win.add_overlay(tracker.get_position())
dlib.hit_enter_to_continue()
吐槽：
已经写了四篇有关dlib的学习笔记了。dlib这个库的确很方便，能够很轻松地让我们实现一些基础的识别任务，比如人脸识别。但是如果想要在各种识别任务中有更好的效果，肯定是不能只用他给的模型的。那也就是说需要自己训练了，看到官方文档中也提供了一些训练以及自己构建神经网络等的api接口，下次有时间再来整理一下程序。最近学校又是校运会，又要看数学（矩阵论、凸优化），不过这样抽时间出来写写程序心情也舒畅了不少。
ヽ(･ω･｡)ﾉ
扫一扫
2779
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
