Question

我正在尝试向量化滑动窗口搜索对象检测。到目前为止，我已经能够使用numpy广播将我的主图像切割成窗口大小的切片，这些切片存储在下面看到的变量“all_windows”中。我已经确认实际值匹配，所以我很满意它。

下一部分是我遇到麻烦的地方。当我调用patchCleanNPredict（）函数时，我想索引到'all_windows'数组，以便我可以以类似的矢量化格式将每个窗口传递给函数。

我试图创建一个名为new_indx的数组，它包含一个二维数组中的切片索引，例如（[0,0]，[1,0]，[2,0] ...）但是一直在运行陷入困境。

我希望最终得到每个窗口的置信值数组。下面的代码适用于python 3.5。提前感谢您的任何帮助/建议。

import numpy as np

def patchCleanNPredict(patch):
    # patch = cv2.resize()# shrink patches with opencv resize function
    patch = np.resize(patch.flatten(),(1,np.shape(patch.flatten())[0])) # flatten the patch
    print('patch: ',patch.shape) 
    # confidence = predict(patch) # fake function showing prediction intent
    return # confidence


window = (30,46)# window dimensions
strideY = 10
strideX = 10

img = np.random.randint(0,245,(640,480)) # image that is being sliced by the windows

indx = np.arange(0,img.shape[0]-window[1],strideY)[:,None]+np.arange(window[1])
vertical_windows = img[indx]
print(vertical_windows.shape) # returns (60,46,480)


vertical_windows = np.transpose(vertical_windows,(0,2,1))
indx = np.arange(0,vertical_windows.shape[1]-window[0],strideX)[:,None]+np.arange(window[0])
all_windows = vertical_windows[0:vertical_windows.shape[0],indx]
all_windows = np.transpose(all_windows,(1,0,3,2))

print(all_windows.shape) # returns (45,60,46,30)


data_patch_size = (int(window[0]/2),int(window[1]/2)) # size the windows will be shrunk to

single_patch = all_windows[0,0,:,:]
patchCleanNPredict(single_patch) # prints the flattened patch size (1,1380)

new_indx = (1,1) # should this be an array of indices? 
patchCleanNPredict(all_windows[new_indx,:,:]) ## this is where I'm having trouble

Answer 1

为了以矢量化的方式评估所有窗口上的函数，我最终需要进行大量的调整大小并使用np.transpose重新排列以使其全部正确播放。下面的代码工作，并有循环显示和确认图像窗口没有乱码/混淆。它们将被删除/评论以进行全速运行。

一个小小的免责声明：我认为在2D矩阵中必须有更清晰的滑动窗口实现，但由于我无法找到下面的任何示例，可能会对其他人有所帮助。此外，一些频繁的重新排列和调整大小可能会通过更广泛地理解广播语法来清理。

import numpy as np
import cv2


def Predict(flattened_patches):
    # taking the mean of the flattened windows and then returning the
    # index of the row (window) with the highest mean, a predicter would have the same syntax
    results = flattened_patches.mean(1) 
    max_index = results.argmax() 
    return results, max_index

## -------- image and sliding window setup -------------------------
AR = 1.45 # choose an aspect ratio to maintain throughout scaling steps
win_h = 200 # window height
win_w = int(win_h/AR) # window width
window = (win_w,win_h)# window dimensions
strideY = 100
strideX = 100

data_patch_size = (30,46) # size the windows will be shrunk to for object detection

img = cv2.imread('picture6.png') # load an image to slide over

cv2.namedWindow('image',cv2.WINDOW_NORMAL) 
cv2.resizeWindow("image",int(img.shape[1]/2),int(img.shape[0]/2)) # shrink the image viewing window if you have large images

img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
## -------- end of, image and sliding window setup --------------------

## -------- sliding window vectorization steps --------------------------
num_vert_windows = len(np.arange(0,img.shape[0]-window[1],strideY)) # number of vertical windows that will be created
indx = np.arange(0,img.shape[0]-window[1],strideY)[:,None]+np.arange(window[1]) # index that will be broadcasted across image
vertical_windows = img[indx] # array of windows win_h tall and the full width of the image

vertical_windows = np.transpose(vertical_windows,(0,2,1)) # transpose to prep for broadcasting
num_horz_windows = len(np.arange(0,vertical_windows.shape[1]-window[0],strideX)) # number of horizontal windows that will be created
indx = np.arange(0,vertical_windows.shape[1]-window[0],strideX)[:,None]+np.arange(window[0]) # index for broadcasting across vertical windows
all_windows = vertical_windows[0:vertical_windows.shape[0],indx] # array of all the windows
## -------- end of, sliding window vectorization ------------------------

## ------- The below code rearranges and flattens the windows into a single matrix of pixels in columns and each window
## ------- in a row which makes evaluating a function over every window in a vectorized manner easier

total_windows = num_vert_windows*num_horz_windows

all_windows = np.transpose(all_windows,(3,2,1,0)) # rearrange for resizing and intuitive indexing

print('all_windows shape as stored in 2d matrix:', all_windows.shape)
for i in range(all_windows.shape[2]): # display windows for visual confirmation
    for j in range(all_windows.shape[3]):
        cv2.imshow('image',all_windows[:,:,i,j])
        cv2.waitKey(100)

all_windows = np.resize(all_windows,(win_h,win_w,total_windows))
print('all_windows shape after folding into 1d vector:', all_windows.shape)
for i in range(all_windows.shape[2]): # display windows for visual confirmation
    cv2.imshow('image',all_windows[:,:,i])
    cv2.waitKey(100)

# shrinking all the windows down to the size needed for object detect predictions
small_windows = cv2.resize(all_windows[:,:,0:all_windows.shape[2]],data_patch_size,0,0,cv2.INTER_AREA)
print('all_windows shape after shrinking to evaluation size:',small_windows.shape)
for i in range(small_windows.shape[2]): # display windows for vis. conf.
    cv2.imshow('image',small_windows[:,:,i])
    cv2.waitKey(100)

# flattening and rearranging the window data so that the pixels are in columns and each window is a row
flat_windows = np.resize(small_windows,(data_patch_size[0]*data_patch_size[1],total_windows))
flat_windows = np.transpose(flat_windows)
print('shape of the window data to send to the predicter:',np.shape(flat_windows))

results, max_index = Predict(flat_windows) # get predictions on all the windows

如何在矢量化滑动窗口的切片上调用函数？

1 个答案: