python - 如何将 OpenCV 代码集成到 tkinter GUI 中并解决“单个位置索引器越界”错误？

Question

我已经编译了一个代码来使用 openCV 计算汽车。我尝试使用 tkinter 将其集成到 GUI 中，但失败了。我该怎么做？

我曾尝试在 tkinter 中创建一个框架，并尝试在该框架中实现汽车跟踪代码，但失败了。

以下是运行良好的汽车跟踪代码（除非使用实时网络摄像头作为视频源，导致单个位置索引器越界错误，也需要帮助）：

当前使用的视频文件：https ://drive.google.com/file/d/1yU5m7SoDQgsqi2UPOzwNE5H_7SyDGKcs/

import numpy as np
import cv2
import pandas as pd

cap = cv2.VideoCapture('traffic.mp4')
# cap = cv2.VideoCapture(0) 

frames_count = cap.get(cv2.CAP_PROP_FRAME_COUNT)
fps = cap.get(cv2.CAP_PROP_FPS)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))

# creates a pandas data frame with the number of rows the same length as frame count
df = pd.DataFrame(index=range(int(frames_count)))
df.index.name = "Frames"

framenumber = 0  # keeps track of current frame
carscrossedup = 0  # keeps track of cars that crossed up
carscrosseddown = 0  # keeps track of cars that crossed down
carids = []  # blank list to add car ids
caridscrossed = []  # blank list to add car ids that have crossed
totalcars = 0  # keeps track of total cars

fgbg = cv2.createBackgroundSubtractorMOG2()  # create background subtractor

ret, frame = cap.read()  # import image
ratio = 1  # resize ratio
image = cv2.resize(frame, (0, 0), None, ratio, ratio)  # resize image

while True:

    ret, frame = cap.read()  # import image

    if ret:  # if there is a frame continue with code

        image = cv2.resize(frame, (0, 0), None, ratio, ratio)  # resize image

        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # converts image to gray

        fgmask = fgbg.apply(gray)  # uses the background subtraction

        # applies different thresholds to fgmask to try and isolate cars
        # just have to keep playing around with settings until cars are easily identifiable
        kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))  # kernel to apply to the morphology
        closing = cv2.morphologyEx(fgmask, cv2.MORPH_CLOSE, kernel)
        opening = cv2.morphologyEx(closing, cv2.MORPH_OPEN, kernel)
        dilation = cv2.dilate(opening, kernel)
        retvalbin, bins = cv2.threshold(dilation, 220, 255, cv2.THRESH_BINARY)  # removes the shadows

        # creates contours
        contours, hierarchy = cv2.findContours(bins, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

        # use convex hull to create polygon around contours
        hull = [cv2.convexHull(c) for c in contours]

        # draw contours
        cv2.drawContours(image, hull, -1, (0, 255, 0), 1)

        # line created to stop counting contours, needed as cars in distance become one big contour
        lineypos = 225
        cv2.line(image, (0, lineypos), (width, lineypos), (255, 0, 0), 2)

        # line y position created to count contours
        lineypos2 = 250
        cv2.line(image, (0, lineypos2), (width, lineypos2), (0, 255, 0), 2)

        # min area for contours in case a bunch of small noise contours are created
        minarea = 300

        # max area for contours, can be quite large for buses
        maxarea = 50000

        # vectors for the x and y locations of contour centroids in current frame
        cxx = np.zeros(len(contours))
        cyy = np.zeros(len(contours))

        for i in range(len(contours)):  # cycles through all contours in current frame

            if hierarchy[0, i, 3] == -1:  # using hierarchy to only count parent contours (contours not within others)

                area = cv2.contourArea(contours[i])  # area of contour

                if minarea < area < maxarea:  # area threshold for contour

                    # calculating centroids of contours
                    cnt = contours[i]
                    M = cv2.moments(cnt)
                    cx = int(M['m10'] / M['m00'])
                    cy = int(M['m01'] / M['m00'])

                    if cy > lineypos:  # filters out contours that are above line (y starts at top)

                        # gets bounding points of contour to create rectangle
                        # x,y is top left corner and w,h is width and height
                        x, y, w, h = cv2.boundingRect(cnt)

                        # creates a rectangle around contour
                        cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 2)

                        # adds centroids that passed previous criteria to centroid list
                        cxx[i] = cx
                        cyy[i] = cy

        # eliminates zero entries (centroids that were not added)
        cxx = cxx[cxx != 0]
        cyy = cyy[cyy != 0]

        # empty list to later check which centroid indices were added to dataframe
        minx_index2 = []
        miny_index2 = []

        # maximum allowable radius for current frame centroid to be considered the same centroid from previous frame
        maxrad = 25

        # The section below keeps track of the centroids and assigns them to old carids or new carids

        if len(cxx):  # if there are centroids in the specified area

            if not carids:  # if carids is empty

                for i in range(len(cxx)):  # loops through all centroids

                    carids.append(i)  # adds a car id to the empty list carids
                    df[str(carids[i])] = ""  # adds a column to the dataframe corresponding to a carid

                    # assigns the centroid values to the current frame (row) and carid (column)
                    df.at[int(framenumber), str(carids[i])] = [cxx[i], cyy[i]]

                    totalcars = carids[i] + 1  # adds one count to total cars

            else:  # if there are already car ids

                dx = np.zeros((len(cxx), len(carids)))  # new arrays to calculate deltas
                dy = np.zeros((len(cyy), len(carids)))  # new arrays to calculate deltas

                for i in range(len(cxx)):  # loops through all centroids

                    for j in range(len(carids)):  # loops through all recorded car ids

                        # acquires centroid from previous frame for specific carid
                        oldcxcy = df.iloc[int(framenumber - 1)][str(carids[j])]

                        # acquires current frame centroid that doesn't necessarily line up with previous frame centroid
                        curcxcy = np.array([cxx[i], cyy[i]])

                        if not oldcxcy:  # checks if old centroid is empty in case car leaves screen and new car shows

                            continue  # continue to next carid

                        else:  # calculate centroid deltas to compare to current frame position later

                            dx[i, j] = oldcxcy[0] - curcxcy[0]
                            dy[i, j] = oldcxcy[1] - curcxcy[1]

                for j in range(len(carids)):  # loops through all current car ids

                    sumsum = np.abs(dx[:, j]) + np.abs(dy[:, j])  # sums the deltas wrt to car ids

                    # finds which index carid had the min difference and this is true index
                    correctindextrue = np.argmin(np.abs(sumsum))
                    minx_index = correctindextrue
                    miny_index = correctindextrue

                    # acquires delta values of the minimum deltas in order to check if it is within radius later on
                    mindx = dx[minx_index, j]
                    mindy = dy[miny_index, j]

                    if mindx == 0 and mindy == 0 and np.all(dx[:, j] == 0) and np.all(dy[:, j] == 0):
                        # checks if minimum value is 0 and checks if all deltas are zero since this is empty set
                        # delta could be zero if centroid didn't move

                        continue  # continue to next carid

                    else:

                        # if delta values are less than maximum radius then add that centroid to that specific carid
                        if np.abs(mindx) < maxrad and np.abs(mindy) < maxrad:

                            # adds centroid to corresponding previously existing carid
                            df.at[int(framenumber), str(carids[j])] = [cxx[minx_index], cyy[miny_index]]
                            minx_index2.append(minx_index)  # appends all the indices that were added to previous carids
                            miny_index2.append(miny_index)

                for i in range(len(cxx)):  # loops through all centroids

                    # if centroid is not in the minindex list then another car needs to be added
                    if i not in minx_index2 and miny_index2:

                        df[str(totalcars)] = ""  # create another column with total cars
                        totalcars = totalcars + 1  # adds another total car the count
                        t = totalcars - 1  # t is a placeholder to total cars
                        carids.append(t)  # append to list of car ids
                        df.at[int(framenumber), str(t)] = [cxx[i], cyy[i]]  # add centroid to the new car id

                    elif curcxcy[0] and not oldcxcy and not minx_index2 and not miny_index2:
                        # checks if current centroid exists but previous centroid does not
                        # new car to be added in case minx_index2 is empty

                        df[str(totalcars)] = ""  # create another column with total cars
                        totalcars = totalcars + 1  # adds another total car the count
                        t = totalcars - 1  # t is a placeholder to total cars
                        carids.append(t)  # append to list of car ids
                        df.at[int(framenumber), str(t)] = [cxx[i], cyy[i]]  # add centroid to the new car id

        # The section below labels the centroids on screen

        currentcars = 0  # current cars on screen
        currentcarsindex = []  # current cars on screen carid index

        for i in range(len(carids)):  # loops through all carids

            if df.at[int(framenumber), str(carids[i])] != '':
                # checks the current frame to see which car ids are active
                # by checking in centroid exists on current frame for certain car id

                currentcars = currentcars + 1  # adds another to current cars on screen
                currentcarsindex.append(i)  # adds car ids to current cars on screen

        for i in range(currentcars):  # loops through all current car ids on screen

            # grabs centroid of certain carid for current frame
            curcent = df.iloc[int(framenumber)][str(carids[currentcarsindex[i]])]

            # grabs centroid of certain carid for previous frame
            oldcent = df.iloc[int(framenumber - 1)][str(carids[currentcarsindex[i]])]

            if curcent:  # if there is a current centroid
                if oldcent:  # checks if old centroid exists
                    # adds radius box from previous centroid to current centroid for visualization
                    xstart = oldcent[0] - maxrad
                    ystart = oldcent[1] - maxrad
                    xwidth = oldcent[0] + maxrad
                    yheight = oldcent[1] + maxrad
                    cv2.rectangle(image, (int(xstart), int(ystart)), (int(xwidth), int(yheight)), (0, 125, 0), 1)

                    # checks if old centroid is on or below line and curcent is on or above line
                    # to count cars and that car hasn't been counted yet
                    if oldcent[1] >= lineypos2 and curcent[1] <= lineypos2 and carids[
                        currentcarsindex[i]] not in caridscrossed:

                        carscrossedup = carscrossedup + 1
                        cv2.line(image, (0, lineypos2), (width, lineypos2), (0, 0, 255), 5)
                        caridscrossed.append(
                            currentcarsindex[i])  # adds car id to list of count cars to prevent double counting

                    # checks if old centroid is on or above line and curcent is on or below line
                    # to count cars and that car hasn't been counted yet
                    elif oldcent[1] <= lineypos2 and curcent[1] >= lineypos2 and carids[
                        currentcarsindex[i]] not in caridscrossed:

                        carscrosseddown = carscrosseddown + 1
                        cv2.line(image, (0, lineypos2), (width, lineypos2), (0, 0, 125), 5)
                        caridscrossed.append(currentcarsindex[i])



        cv2.putText(image, "Cars out: " + str(carscrossedup), (0, 30), cv2.FONT_HERSHEY_DUPLEX, 0.5, (0, 170, 0), 1)
        cv2.putText(image, "Cars in: " + str(carscrosseddown), (0, 45), cv2.FONT_HERSHEY_DUPLEX, 0.5,(0, 170, 0), 1)


        # displays images and transformations
        cv2.imshow("Car Count", image)
#         cv2.moveWindow("countours", 0, 0)

        # adds to framecount
        framenumber = framenumber + 1

        k = cv2.waitKey(int(1000/fps)) & 0xff
        if k == 27:
            break

    else:  # if video is finished then break loop

        break

cap.release()
cv2.destroyAllWindows()

此外，将输入源设置为网络摄像头时，出现“单个位置索引器越界”错误。有什么解决办法吗？

    IndexError                                Traceback (most recent call last)
<ipython-input-2-6702d1950482> in <module>
    220 
    221             # grabs centroid of certain carid for current frame
--> 222             curcent = df.iloc[int(framenumber)][str(carids[currentcarsindex[i]])]
    223 
    224             # grabs centroid of certain carid for previous frame

c:\users\....\appdata\local\programs\python\python36\lib\site-packages\pandas\core\indexing.py in __getitem__(self, key)
   1476 
   1477             maybe_callable = com._apply_if_callable(key, self.obj)
-> 1478             return self._getitem_axis(maybe_callable, axis=axis)
   1479 
   1480     def _is_scalar_access(self, key):

c:\users\....\appdata\local\programs\python\python36\lib\site-packages\pandas\core\indexing.py in _getitem_axis(self, key, axis)
   2100 
   2101             # validate the location
-> 2102             self._validate_integer(key, axis)
   2103 
   2104             return self._get_loc(key, axis=axis)

c:\users\....\appdata\local\programs\python\python36\lib\site-packages\pandas\core\indexing.py in _validate_integer(self, key, axis)
   2007         l = len(ax)
   2008         if key >= l or key < -l:
-> 2009             raise IndexError("single positional indexer is out-of-bounds")
   2010 
   2011     def _getitem_tuple(self, tup):

IndexError: single positional indexer is out-of-bounds

以下是我一直在处理的 UI 代码：

from tkinter import*
import tkinter.messagebox
from tkinter import ttk
import cv2

def main():
    root = Tk()
    app = PMMain(root)

class WindowPMMain:
    def __init__(self, master):
        self.master = master
        self.master.title("Car Tracking")
        #self.master.geometry("1366x715+0+0")
        #self.master.state("zoomed")
        self.frame = Frame(self.master)
        self.frame.pack()

        self.LabelTitleMain = Label(self.frame, text = 'Click to start tracking', font = ('arial', 20, 'bold'), bd = 5)
        self.LabelTitleMain.grid(row=0, column=0, columnspan =1, pady =10)


        ###### need help here #####

if __name__ == '__main__':
    root = Tk()
    b = WindowPMMain(root)
    root.mainloop()

我知道输出如下图所示： https ://i.imgur.com/CR6TBej.jpg

汽车计数

其中，当我按下按钮时，跟踪显示在窗口的右半部分，因此我可以将其他一些 UI 组件与左侧的按钮一起放置。

我是这个界面的新手，很难理解它。实际的方法是使用网络摄像头而不是录制的视频，这也会有错误。请帮忙。

标签： pythonpandasopencvuser-interfacetkinter