dlib correlation tracker 28 29

Solutions on MaxInterview for dlib correlation tracker 28 29 by the best coders in the world

showing results for - "dlib correlation tracker 28 29"
Emmy
22 May 2019
1#!/usr/bin/python
2# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
3#
4# This example shows how to use the correlation_tracker from the dlib Python
5# library.  This object lets you track the position of an object as it moves
6# from frame to frame in a video sequence.  To use it, you give the
7# correlation_tracker the bounding box of the object you want to track in the
8# current video frame.  Then it will identify the location of the object in
9# subsequent frames.
10#
11# In this particular example, we are going to run on the
12# video sequence that comes with dlib, which can be found in the
13# examples/video_frames folder.  This video shows a juice box sitting on a table
14# and someone is waving the camera around.  The task is to track the position of
15# the juice box as the camera moves around.
16#
17#
18# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
19#   You can install dlib using the command:
20#       pip install dlib
21#
22#   Alternatively, if you want to compile dlib yourself then go into the dlib
23#   root folder and run:
24#       python setup.py install
25#
26#   Compiling dlib should work on any operating system so long as you have
27#   CMake installed.  On Ubuntu, this can be done easily by running the
28#   command:
29#       sudo apt-get install cmake
30#
31#   Also note that this example requires Numpy which can be installed
32#   via the command:
33#       pip install numpy
34
35import os
36import glob
37
38import dlib
39
40# Path to the video frames
41video_folder = os.path.join("..", "examples", "video_frames")
42
43# Create the correlation tracker - the object needs to be initialized
44# before it can be used
45tracker = dlib.correlation_tracker()
46
47win = dlib.image_window()
48# We will track the frames as we load them off of disk
49for k, f in enumerate(sorted(glob.glob(os.path.join(video_folder, "*.jpg")))):
50    print("Processing Frame {}".format(k))
51    img = dlib.load_rgb_image(f)
52
53    # We need to initialize the tracker on the first frame
54    if k == 0:
55        # Start a track on the juice box. If you look at the first frame you
56        # will see that the juice box is contained within the bounding
57        # box (74, 67, 112, 153).
58        tracker.start_track(img, dlib.rectangle(74, 67, 112, 153))
59    else:
60        # Else we just attempt to track from the previous frame
61        tracker.update(img)
62
63    win.clear_overlay()
64    win.set_image(img)
65    win.add_overlay(tracker.get_position())
66    dlib.hit_enter_to_continue()
67