There is a implementation of Mask RCNN on Github by Matterport.
I'm trying to train my data for it. I'm adding polygons on images with this tool. I'm drawing polygons on images manually, but I already have manually segmented image below (black and white one)
My questions are:
1) When adding json annotation for region data, is there a way to use that pre-segmented image below?
2) Is there a way to train my data for this algorithm, without adding json annotation and use manually segmented images? The tutorials and posts I've seen uses json annotations to train.
3) This algorithm's output is image with masks obviously, is there a way get black and white output for segmentations?
Here's the code that I'm working on google colab.
Original Repo
My Fork
Manually segmented image
I think both questions 1 and 2 refer to the same solution: you need to convert your masks to json annotations. For that, I would suggest you to read this link, posted in the repository of the cocodataset. There you can read about this repository that you could use for what you need. You could also use directly the Coco PythonAPI, calling the methods here defined.
For question 3, a mask is already binary image (therefore, you can show it as black and white pixels).
Related
Lets assume i have a little dataset. I want to implement data augmentation. First i implement image segmentation (after this, image will be binary image) and then implement data augmentation. Is this a good way?
For image augmentation in segmentation and instance segmentation, you have to either no change the positions of the objects contained in the image by manipulating colors for example, or modify these positions by applying translations and rotation.
So, yes this way works, but you have to take into consideration the type of data you have and what you are looking to achieve. Data augmentation isn't a ready to-go process with good results everywhere.
In case you have a:
Semantic segmentation : Each pixel of your image has a row i and a column j which are labeled as its enclosing object. This means having your main image I and a label image L with its same size linking every pixel to its object label. In this case, your data augmentation is applied to both I and L, giving a combination of the two transformed images.
Instance segmentation : Here we generate a mask for every instance of the original image and the augmentation is applied to all of them including the original, then from these transformed masks we get our new instances.
EDIT:
Take a look at CLoDSA (Classification, Localization, Detection and Segmentation Augmentor) it may help you implement your idea.
In case your dataset is small, you should add data-augmentation during the training. It is important to change the original image & the targets (masks) in the same way !!.
For example, If an image is rotated 90 degrees, then its mask should also be rotated 90 degrees. Since you are using Keras library, You should check if the ImageDataGenerator also changes the target images (masks), along with the inputs. If it doesn't, You can implement the augmentations by yourself. This repository shows how it is done in OpenCV here:
https://github.com/kochlisGit/random-data-augmentations
I have a large geotiff file of elevation data that I would like to use for object detection. I've labelled the objects (originally as a .shp) and converted the labels into a single geojson.
From reading object detection tutorials it seems that I need to split this large image into multiple images for training/testing. Is there a way to do this using the original labels, so that I don't need to re-label each smaller image?
If anyone has any useful tutorials/end to end examples of preparing satellite data for object detection that would also be really helpful.
The GeoJSON file you have should have the co-ordinates to get the bounding box for the named portion of the original image. (If you want to know how to do that, see here: https://gis.stackexchange.com/a/313023/120175). Once you have the bounding box, you can use any imaging library (Pillow or Pillow-SIMD) to get the sub-image that you have named (with the name in the same geojson object that contained the coordinates you took for getting bounding box). You can operate them while they're in memory or save them (they can be treated as independent images themselves) with these imaging library. These images can be used for training.
I am trying to make a yolo v4 tiny custom data set using google collab. I am using labelImg.py for image annotations which is shown in https://github.com/tzutalin/labelImg.
I have annotated one image as shown as below,
The .txt file with the annotated coordinates looks as following,
0 0.580859 0.502083 0.303906 0.404167
I only have one class which is calculator class. I want to use this one image to produce 4 more annotated images. I want to rotate the annotated image 45 degrees every time and create a new annotated image and a.txt coordinate file. I have seen something like this done in roboflow but I cant figure out how to do it manually with a python script. Is it possible to do it? If so how?
You can look into the repo and article below for python based data augmentation including rotation, shearing, resizing, translation, flipping etc.
https://github.com/Paperspace/DataAugmentationForObjectDetection
https://blog.paperspace.com/data-augmentation-for-bounding-boxes/
If you are using AlexeyAB's darknet repo for yolov4, then there are some augmentations you can use to increase training data size and variation.
https://github.com/AlexeyAB/darknet/wiki/CFG-Parameters-in-the-%5Bnet%5D-section
Look into Data augmentation section where you can use various defined augmentations for object detection by adding them to yolo cfg file.
I am working on a project where I have to find the background of a given gray-scale image.
I did several kinds of research on the internet and I've found some algorithms using OpenCV library (like the following: https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_video/py_bg_subtraction/py_bg_subtraction.html#py-background-subtraction).
This kind of approach doesn't work for me.
The image I want to elaborate is:
As you can see it is in gray-scale and we see the "gray static" background. I would love to see only the nucleus of the cell (the image will improve resolution and quality in the time, this is a pretty raw one)
I tried to subtract the 2D magnitude FFT of the background from the main image but the results is not good:
What I am asking is: What kind of process do you suggest to use to eliminate background?
Did you already try watershed algorithm ? I saw on a paper it's already used and improved for cell image segmentation.
Background subtraction won't work for your images because your background is not consistent. image's SNR is too low!
So you have 2 options:
1) Using deep learning method (like UNET) if you have enough data
2) Using bilateral filter then, some methods like active contour or GLCM Texture Feature or k-means clustering.
I am working with a stack of noisy images, trying to isolate a blob in an image section. Below you can see the starting image, loaded and plotted with python, and the same image after some editing with Gimp.
What I want to do is to isolate and recognise the blob inside the light blue circle, editing the image and then using something like ndimage.label. Do you have any suggestion on how to edit the image? Thanks.
The background looks quite even so you should be able to isolate the main object using thresholding, allowing you to use array masking to identify regions within the main object. I would have a go with some tools from scikit image to see where that gets you http://scikit-image.org/docs/dev/auto_examples/
I would try gaussian/median filtering followed by thresholding/filling gaps. Or you could try random walker segmentation, or pherhaps texture classification might be more useful. When you have a list of smaller objects within the main object you can then filter these with respect to shape, size, roundness etc
http://scikit-image.org/docs/dev/auto_examples/plot_label.html#example-plot-label-py