Tag: video

I have a video showing a football match. video file match.mp4 consist of several opening ads, the actual game and the half-time / break. As a result, the video file is always longer than the match itself. The properties of match.mp4 looks like this:

According to my Windows computer, the file has a length of 00:48:36, I want to check this with OpenCV:

import cv2   # version 3.4.2

video = cv2.VideoCapture('match.mp4')
while (True):
   fps = video.get(cv2.CAP_PROP_FPS)                      # 30
   video.set(cv2.CAP_PROP_POS_AVI_RATIO, 1)               # set video to the end
   duration = video.get(cv2.CAP_PROP_POS_MSEC)            # 2,916,633 ms
   total_frames = video.get(cv2.CAP_PROP_FRAME_COUNT)     # 87,499 frames

2,916,633 / (1,000 * 60) = 48 minutes and ~ 37 seconds. I like to work on it and calculate it secondsPerFrame:

secondsPerFrame =  87,499 / 2,916,633 = 0,030000003428611

So, now I know for each frame how many seconds have passed videoTime passes. Within the video, I also watch the gameTime:

I try to find that gameTime With TesseractOCR and contour acquisition. Sometimes I get the right result, sometimes I get no result and sometimes I get wrong results.

Right:

Frame: 211, gameTime: 00:17
Frame: 212, gameTime: 00:18
Frame: 213, gameTime: 00:18
Frame: 214, gameTime: 00:18  
Frame: 215, gameTime: 00:18
Frame: 216, gameTime: 00:18
....

none:

Frame: 228, gameTime: N/A
Frame: 229, gameTime: N/A
Frame: 230, gameTime: N/A
Frame: 231, gameTime: N/A
Frame: 232, gameTime: N/A
Frame: 233, gameTime: N/A
...

Wrong / Outliers:

Frame: 1742, gameTime: N/A
Frame: 1743, gameTime: 61:09
Frame: 1744, gameTime: N/A
Frame: 1745, gameTime: 61:09
Frame: 1746, gameTime: 61:09
Frame: 1747, gameTime: 01:09     # should be 61:09
...

Important to note is the relationship between videoTime and gameTime, Obviously, the two differ as videoTime starts with advertising while gameTime Starts only when the game starts and the time is observed on the scorebox for the first time. However, both variables are closely related because there is a simple linear relationship (with slope 1) between the video and the playing time. 1 sec. In videoTime is also 1 sec. in gameTime,

We can write the linear relationship between the two as follows:

y = mx + b where y is gameTime, m = 1, x = videoTime, b = (-)delay between gameTime and videoTime

So my question is How can we determine b as fast and accurately as possible? My thoughts below:

• I want to use a limited number of frames. In the first few seconds of the game, events take place that need to be timestamped as quickly as possible
• It has to be able to handle outliers. So my idea was to use RANCSAC to handle any misinterpretations of time and filter those outliers.
• My overall script runs in real time, so the method has to be fast. Performing regressions (normal / RANCSAC) takes a long time. As the match progresses, more and more frames are added to the dataset.

My screenplay:

import cv2  
from skimage.measure import LineModelND, ransac


video = cv2.VideoCapture('match.mp4')
previous_frames = ()
frame_count = ()
match_time = ()
counter = 0


def ransac_regression(data, counter):
  model = ransac(data, LineModelND, min_samples=5, residual_threshold=1, max_trials=5)(0)
   matchTime = model.predict_y(counter)
   print(matchTime)


while True:
   ret, frame = video.read()
   if ret:
      if len(previous_frames) == 200:
         time = get_matchtime()
         boolean = checktime()
         if boolean:
            print("Frame: {0}, time: {1}".format(counter, time))
            frame_count.append(counter)
            match_time.append(timestamp)
         else:
            print("Frame: {0}, time: N/A".format(counter))
         previous_frames = previous_frames(1:)
         previous_frames.append(frame)        
      else:
         previous_frames.append(frame)
   if len(match_time) >= 25:
      data = np.column_stack((frame_count, match_time))
      ransac = ransac_regression(data, counter) 
   counter += 1
   key = cv2.waitKey(5)
   if key == ord('q'):
      break

video.release()
cv2.destroyAllWindows() 

My script works, but I feel like I'm complicating things and there are easier / faster ways to determine the delay between videoTime and gameTime, Thanks in advance for your help!