Question

How can I visualize the segmented image output of the Selective Search algorithm applied on an image?

import cv2

image = cv2.imread("x.jpg")

ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()
ss.setBaseImage(image)

ss.switchToSelectiveSearchQuality()
rects = ss.process()

That is, to get the image on the right

Answer 1

I am not sure but I think the image you require can possibly not be obtained. Reason being: Open this file first containing the source code

第726-734条变数的“工资”是私人的,在828行的“ToSelectiveSearchality()”转换方法中,用于计算的不同图像被储存在私人变量“images”中(见下面的添加功能)。

此外,“images”变量中储存的图像需要处理第901行的分部分。这里所说的方法是我无法追溯到的“分类”类过程。

因此,你所需要的图像不可能存放在任何地方,也不可能储存在无法进入的私人变量中。

EDIT: Found "GraphSegmentation" class and method "processImage" declaration in this file at lines 46 and 52.

Answer 2

I think you can use the following. I tried it - it s working

import cv2, random

image = cv2.imread("x.jpg")

ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()
ss.setBaseImage(image)

ss.switchToSelectiveSearchQuality()
rects = ss.process()

for i in range(0, len(rects), 100):
    # clone the original image so we can draw on it

    output = image.copy()
    # loop over the current subset of region proposals
    for (x, y, w, h) in rects[i:i + 100]:
        # draw the region proposal bounding box on the image
        color = [random.randint(0, 255) for j in range(0, 3)]
        cv2.rectangle(output, (x, y), (x + w, y + h), color, 2)

    cv2.imshow("Output", output)
    key = cv2.waitKey(0) & 0xFF
    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break

Why 100? I chose a chunk size of 100.

Original Image:

After processing:

Answer 3

You have a bit a confusion.

The image you are trying to create is generated by graph segmentation:

  gs = cv2.ximgproc.segmentation.createGraphSegmentation()

  # Set the sigma, k, and min_size parameters
  gs.setSigma(sigma)
  gs.setK(k)
  gs.setMinSize(min_size)

  # Process the image
  segments = gs.processImage(img)

  # Get the minimum and maximum values in the segments image
  # min, max,_, _ = cv2.minMaxLoc(segments)

  # # Get the number of segments
  # nb_segs = int(max + 1)

  # Create an output image
  output = np.zeros_like(img)
  for segment_id in np.unique(segments):
      output[segments == segment_id] = color_mapping(segment_id)

  # Save the output image
  cv2.imwrite(output_image, output)

  print("Image written to " + output_image)

graph segmentation works as described here: https://www.youtube.com/watch?v=2IVAznQwdS4&ab_channel=FirstPrinciplesofComputerVision

while selective search described here https://learnopencv.com/selective-search-for-object-detection-cpp-python/ is used for bounding box suggestion - i.e. it will produce many suggestion, so that some of the suggestion contains objects

NOTE:

Selective search uses graph segmentation as it s first step
Selective search is used as suggesting mechanizm for RCNN to avoid scanning the entire img, as explained here https://towardsdatascience.com/understanding-regions-with-cnn-features-r-cnn-ec69c15f8ea7
The RCNN uses the suggestion to predict objects class, if there is no object in the suggestion, the suggestion is discarded, therefore Selective search require an extra step to discard bad suggestion in order to be usefull

友情链接