我還在偷書掃描腳本,現在,我需要的是能夠自動檢測翻頁。這本書填滿了屏幕的90%(我使用的是運動檢測的惡劣攝像頭),所以當我翻頁時,運動的方向基本上是一致的。Python OpenCV:檢測運動的一般方向?
我修改了運動跟蹤腳本,但衍生物無處讓我:
#!/usr/bin/env python
import cv, numpy
class Target:
def __init__(self):
self.capture = cv.CaptureFromCAM(0)
cv.NamedWindow("Target", 1)
def run(self):
# Capture first frame to get size
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
moving_average = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
difference = None
movement = []
while True:
# Capture frame from webcam
color_image = cv.QueryFrame(self.capture)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if not difference:
# Initialize
difference = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, moving_average, 1.0, 0.0)
else:
cv.RunningAvg(color_image, moving_average, 0.020, None)
# Convert the scale of the moving average.
cv.ConvertScale(moving_average, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, difference)
# Convert the image to grayscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, 70, 255, cv.CV_THRESH_BINARY)
# Dilate and erode to get object blobs
cv.Dilate(grey_image, grey_image, None, 18)
cv.Erode(grey_image, grey_image, None, 10)
# Calculate movements
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, storage, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
# Draw rectangles
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255,0,0), 1)
num_points = len(points)
if num_points:
x = 0
for point in points:
x += point[0]
x /= num_points
movement.append(x)
if len(movement) > 0 and numpy.average(numpy.diff(movement[-30:-1])) > 0:
print 'Left'
else:
print 'Right'
# Display frame to user
cv.ShowImage("Target", color_image)
# Listen for ESC or ENTER key
c = cv.WaitKey(7) % 0x100
if c == 27 or c == 10:
break
if __name__=="__main__":
t = Target()
t.run()
它能檢測出所有的箱子的平均中心,這是非常低效的平均運動。我該如何快速準確地檢測這種運動(即在一個閾值內)?
我正在使用Python,我打算堅持下去,因爲我的整個框架都是基於Python的。
幫助表示感謝,所以提前謝謝大家。乾杯。
你真的需要運動跟蹤嗎?爲什麼不只是檢測一些閾值的變化? (即沿着'sum(abs(img2 - img1))> threshold'線)的東西) – 2010-12-21 03:49:56
嗯,我會搗鼓的。但是,我將如何判斷頁面是向前還是向後,還是更糟,轉向一半,然後又轉回。我會玩圖表,因爲這就是我的工作方式。謝謝! – Blender 2010-12-21 03:51:20
啊,真的,我只是假設你需要知道一個頁面已經被轉換了......如果你需要知道方向,我上面的評論顯然不是一個好的選擇! – 2010-12-21 04:26:33