Notes for challenging basketball video analysis

http://qiita.com/northriver/items/d6b73da79a13bf3526e2 Now that you know about opencv, let's challenge towards the title

First of all, understand by using something that seems to be helpful

I found a code that is tracking the green ball, so I'll give it a try. This seems to be detected by color http://www.pyimagesearch.com/2015/09/14/ball-tracking-with-opencv/

#Import required packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2
#Make an argument to execute. "Python xxx.py -v test.mov "-About v
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=64,help="max buffer size")
args = vars(ap.parse_args())

Click here for an explanation of argparse http://python.civic-apps.com/argparse/

#Define the color of the chasing ball"green" (HSV)
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)
pts = deque(maxlen=args["buffer"])

HSV color space http://www.peko-step.com/html/hsv.html

#If there is an argument, the path of the file, if not, the webcam
if not args.get("video", False):
	camera = cv2.VideoCapture(0)
else:
	camera = cv2.VideoCapture(args["video"])
while True:
	#Camera, take video
	(grabbed, frame) = camera.read()
 
	#If you can't, break
	if args.get("video") and not grabbed:
		break
 
	# resize
	frame = imutils.resize(frame, width=600)
	#Convert to hsv
	hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
	#Extract only the green part and perform morphology conversion
	mask = cv2.inRange(hsv, greenLower, greenUpper)
	mask = cv2.erode(mask, None, iterations=2)
	mask = cv2.dilate(mask, None, iterations=2)

I am doing morphology conversion. The morphology transformation extracts the characteristic part of the object and removes the rest. I am trying to reduce it. cv2.erode is eroded to leave characteristic parts, and cv2.dilate is eroded to restore only the important parts. http://labs.eecs.tottori-u.ac.jp/sd/Member/oyamada/OpenCV/html/py_tutorials/py_imgproc/py_morphological_ops/py_morphological_ops.html

	#Extract contours from binary black and white data
	# (x, y) center of the ball
	cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[-2]
	center = None

Extract contours from binary black and white data with cv2.findContours. RETR_EXTERNAL is a mode that extracts only the outermost part, and CHAIN_APPROX_SIMPLE is a method of contour approximation method. http://opencv.jp/opencv-2.1/cpp/structural_analysis_and_shape_descriptors.html

    if len(cnts) > 0:
        #Calculate the area occupied by the area and find the one with the largest area
        c = max(cnts, key=cv2.contourArea)
        #Find the smallest circle
        ((x, y), radius) = cv2.minEnclosingCircle(c)
    #Moment(Basic values such as area and center of gravity)And get the coordinates of the center of the circle
        M = cv2.moments(c)
        center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))

        #Draw a circle
        if radius > 10:
            cv2.circle(frame, (int(x), int(y)), int(radius),
(0, 255, 255), 2)
            cv2.circle(frame, center, 5, (0, 0, 255), -1)

http://labs.eecs.tottori-u.ac.jp/sd/Member/oyamada/OpenCV/html/py_tutorials/py_imgproc/py_contours/py_contour_features/py_contour_features.html

The following is to follow the trajectory, so you don't have to

	# update the points queue
	pts.appendleft(center)
	# loop over the set of tracked points
	for i in xrange(1, len(pts)):
		# if either of the tracked points are None, ignore
		# them
		if pts[i - 1] is None or pts[i] is None:
			continue
 
		# otherwise, compute the thickness of the line and
		# draw the connecting lines
		thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
		cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)

The rest is just output, this is the same as the tutorial

	# show the frame to our screen
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF
 
	# if the 'q' key is pressed, stop the loop
	if key == ord("q"):
		break
 
# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()

Connect from start to finish

# import the necessary packages
from collections import deque
import numpy as np
import argparse
import imutils
import cv2
 
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
	help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=64,
	help="max buffer size")
args = vars(ap.parse_args())

# define the lower and upper boundaries of the "green"
# ball in the HSV color space, then initialize the
# list of tracked points
greenLower = (29, 86, 6)
greenUpper = (64, 255, 255)
pts = deque(maxlen=args["buffer"])
 
# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
	camera = cv2.VideoCapture(0)
 
# otherwise, grab a reference to the video file
else:
	camera = cv2.VideoCapture(args["video"])

# keep looping
while True:
	# grab the current frame
	(grabbed, frame) = camera.read()
 
	# if we are viewing a video and we did not grab a frame,
	# then we have reached the end of the video
	if args.get("video") and not grabbed:
		break
 
	# resize the frame, blur it, and convert it to the HSV
	# color space
	frame = imutils.resize(frame, width=600)
	# blurred = cv2.GaussianBlur(frame, (11, 11), 0)
	hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
 
	# construct a mask for the color "green", then perform
	# a series of dilations and erosions to remove any small
	# blobs left in the mask
	mask = cv2.inRange(hsv, greenLower, greenUpper)
	mask = cv2.erode(mask, None, iterations=2)
	mask = cv2.dilate(mask, None, iterations=2)
	# find contours in the mask and initialize the current
	# (x, y) center of the ball
	cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
		cv2.CHAIN_APPROX_SIMPLE)[-2]
	center = None
 
	# only proceed if at least one contour was found
	if len(cnts) > 0:
		# find the largest contour in the mask, then use
		# it to compute the minimum enclosing circle and
		# centroid
		c = max(cnts, key=cv2.contourArea)
		((x, y), radius) = cv2.minEnclosingCircle(c)
		M = cv2.moments(c)
		center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
 
		# only proceed if the radius meets a minimum size
		if radius > 10:
			# draw the circle and centroid on the frame,
			# then update the list of tracked points
			cv2.circle(frame, (int(x), int(y)), int(radius),
				(0, 255, 255), 2)
			cv2.circle(frame, center, 5, (0, 0, 255), -1)
 
	# update the points queue
	pts.appendleft(center)
	# loop over the set of tracked points
	for i in xrange(1, len(pts)):
		# if either of the tracked points are None, ignore
		# them
		if pts[i - 1] is None or pts[i] is None:
			continue
 
		# otherwise, compute the thickness of the line and
		# draw the connecting lines
		thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
		cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)
 
	# show the frame to our screen
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF
 
	# if the 'q' key is pressed, stop the loop
	if key == ord("q"):
		break
 
# cleanup the camera and close any open windows
camera.release()
cv2.destroyAllWindows()

Well, I tried so far, but when I put in a basketball video, I could not detect it ... There is a color problem

greenLower = (7,100,100)
greenUpper = (11,255,255)

In the case of basketball, the balls are similar in color to the gymnasium, and the old balls are black. Therefore, it is necessary to use a recognition method other than color detection.

http://labs.eecs.tottori-u.ac.jp/sd/Member/oyamada/OpenCV/html/py_tutorials/py_video/py_table_of_contents_video/py_table_of_contents_video.html#py-table-of-content-video I also found an improved version http://answers.opencv.org/question/17637/backgroundsubtractormog-with-python/ For the time being, there is also a method of detecting motion by background subtraction, so I tried it, but in the case of basketball, the camera moves, so there is no background ... Subtle ...

I can't come up with a good idea ... Please let me know if you would like to do this.

this? http://qiita.com/olympic2020/items/3d8973f855e963c9d999

I tried it, but it didn't work ...

Recommended Posts

Notes for challenging basketball video analysis
Tips for data analysis ・ Notes
Folder structure for analysis
Source analysis for Django--INSTALLED_APPS
Installation notes for TensorFlow for Windows
Python for Data Analysis Chapter 4
Python Tkinter notes (for myself)
[Python] Notes on data analysis
Python data analysis learning notes
Python for Data Analysis Chapter 2
Notes for HHKB Programming Contest 2020
Python for Data Analysis Chapter 3