My goal is to find known logos in static image and videos. I want to achieve that by using feature detection with KAZE or AKAZE and RanSac.
I am aiming for a similar result to: https://www.youtube.com/watch?v=nzrqH...
While experimenting with the detection example from the docs which is great btw, i was facing several issues:
Object resolution: Differences in size between the known object and
the resolution of the scene where the object should be located
sometimes breaks the detection algorithm - the object won't be
recognized in images with a low resolution although the image quality
is still allright for a human eye.
Color contrast with the background: It seems, that the detection can
easily be distracted by different background contrasts (eg: object is
logo black on white background, logo in scene is white on black
background). How can I make the detection more robust against
different luminations and background contrasts?
Preprocessing: Should there be done any kind of preprocessing of the
object / scene? For example enlarge the scene up to a specific size?
Is there any guideline how to approach the feature detection in
several steps to get the best results?
I think your issue is more complicated than feature-descriptor-matching-homography process.
It is more likely oriented to pattern recognition or classification.
You can check this extended paper review of shape matching:
http://www.staff.science.uu.nl/~kreve101/asci/vir2001.pdf
Firstly, the resolution of images is very important,
because usually matching operation makes a pixel intensity cross-correlation
between your sample image (logo) and your process image, so you will get the best-crosscorrelated area.
In the same way, the background colour intensity
is very important because background illumination could affect severally to your final result.
Feature-based methods are widely researched:
http://docs.opencv.org/2.4/modules/features2d/doc/feature_detection_and_description.html
http://docs.opencv.org/2.4/modules/features2d/doc/common_interfaces_of_descriptor_extractors.html
So for example, you can try alternative methods such as:
Hog descritors: Histogram oriented gradients:
https://en.wikipedia.org/wiki/Histogram_of_oriented_gradients
Pattern matching or template matching
http://docs.opencv.org/2.4/doc/tutorials/imgproc/histograms/template_matching/template_matching.html
I think the lastest (Pattern matching) is the easiest to check your algorithm.
Hope these references helps.
Cheers.
Unai.
Related
I was wondering if its possible to match the exposure across a set of images.
For example, lets say you have 5 images that were taken at different angles. Images 1-3,5 are taken with the same exposure whilst the 4th image have a slightly darker exposure. When I then try to combine these into a cylindrical panorama using (seamFinder with: gc_color, surf detection, MULTI_BAND blending,Wave correction, etc.) the result turns out with a big shadow in the middle due to the darkness from image 4.
I've also tried using exposureCompensator without luck.
Since I'm taking the pictures in iOS, I maybe could increase exposure manually when needed? But this doesn't seem optimal..
Have anyone else dealt with this problem?
This method is probably overkill (and not just a little) but the current state-of-the-art method for ensuring color consistency between different images is presented in this article from HaCohen et al.
Their algorithm can correct a wide range of errors in image sets. I have implemented and tested it on datasets with large errors and it performs very well.
But, once again, I suppose this is way overkill for panorama stitching.
Sunreef has provided a very good paper, but it does seem overkill because of the complexity of a possible implementation.
What you want to do is to equalize the exposure not on the entire images, but on the overlapping zones. If the histograms of the overlapped zones match, it is a good indicator that the images have similar brightness and exposure conditions. Since you are doing more than 1 stitch, you may require a global equalization in order to make all the images look similar, and then only equalize them using either a weighted equalization on the overlapped region or a quadratic optimiser (which is again overkill if you are not a professional photographer). OpenCV has a simple implmentation of a simple equalization compensation algorithm.
The detail::ExposureCompensator class of OpenCV (sample implementation of such a stitiching is here) would be ideal for you to use.
Just create a compensator (try the 2 different types of compensation: GAIN and GAIN_BLOCKS)
Feed the images into the compensator, based on where their top-left cornes lie (in the stitched image) along with a mask (which can be either completely white or white only in the overlapped region).
Apply compensation on each individual image and iteratively check the results.
I don't know any way to do this in iOS, just OpenCV.
Given a logo image as a reference image, how to detect/recognize it in a cluttered natural image?
The logo may be quite small in the image, it can appear in clothes, hats, shoes, background wall etc. I have tried SIFT feature for matching without any other preprocessing, and the result is good for cases in which the size of the logo in images is big and the logo is clear. However, it fails for some cases where the scene is quite cluttered and the proportion of the logo size is quite small compared with the whole image. It seems that SIFT feature is sensitive to perspective distortions.
Anyone know some better features or ideas for logo detection/recognition in natural images? For example, training a classifier to locate candidate regions first, and then apply directly SIFT matching for further recognition. However, training a model needs many data, especially it needs manually annotating logo regions in images, and it needs re-training (needs to collect and annotate new image) if I want to apply it for new logos.
So, any suggestions for this? Detailed workflow/code/reference will be highly appreciated, thanks!
There are many algorithms from shape matching to haar classifiers. The best algorithm very depend on kind of logo.
If you want to continue with feature registration, i recommend:
For detection of small logos, use tiles. Split whole image to smaller (overlapping) tiles and perform usual detection. It will use "locality" of searched features.
Try ASIFT for affine invariant detection.
Use many template images for reference feature extraction, with different lightning , different background images (black, white, gray)
I don't think I'm going to get any replies but here goes: I'm developing an iOS app that performs image segmentation functions. I'm trying to implement the easiest way to crop out a subject from an image without the need of a greenscreen/keying. Most automated solutions like using OpenCV just aren't cutting it.
I've found the rotoscope brush tool in After Effects to be effective at giving hints on where the app should be cutting out. Anyone know what kind of algorithms the rotoscope brush tool is using?
Check out this page, which contains a couple of video presentations from SIGGRAPH (a computer graphics conference) about the Roto Brush tool. Also take a look at Jue Wang's paper on Video SnapCut. As Damien guessed, object extraction relies on some pretty intense image processing algorithms. You might be able to implement something similar in OpenCV depending on how clever/masochistic you're feeling.
The algorithm is a graph-cut based segmentation algorithm where Gaussian Mixture Models (GMM) are trained using color pixels in "local" regions as well as "globally", together with some sort of shape prior.
OpenCV has a "cheap hack" implementation of the "GrabCut" paper where the user specifies a bounding box around the object he wish to segment. Typically, using just the bounding box will not give good results. You will need the user to specify the "foreground" and "background" pixels (as is done in Adobe's Rotoscoping tool) to help the algorithm build foreground and background color models (in this case GMMs) so that it will know what are the typical colors in the foreground object you wish to segment, and those for the background that you want to leave out.
A basic graph-cut implementation can be found on this blog. You can probably start from there and experiment with different ways to compute the cost terms to get better results.
Lastly, the "soften" the edges, a cheap hack is to blur the binary mask to obtain a mask with values between 0 and 1. Then recomposite your image using the mask i.e. c[i][j] = mask[i][j] * fgd[i][j] + (1 - mask[i][j]) * bgd[i][j], where you are blending the foreground you segmented (fgd), with a new background image (bgd) using the mask values as blending weights.
I had asked this on photo stackexchange but thought it might be relevant here as well, since I want to implement this programatically in my implementation.
I am trying to implement a blur detection algorithm for my imaging pipeline. The blur that I want to detect is both -
1) Camera Shake: Pictures captured using hand which moves/shakes when shutter speed is less.
2) Lens focussing errors - (Depth of Field) issues, like focussing on a incorrect object causing some blur.
3) Motion blur: Fast moving objects in the scene, captured using a not high enough shutter speed. E.g. A moving car a night might show a trail of its headlight/tail light in the image as a blur.
How can one detect this blur and quantify it in some way to make some decision based on that computed 'blur metric'?
What is the theory behind blur detection?
I am looking of good reading material using which I can implement some algorithm for this in C/Matlab.
thank you.
-AD.
Motion blur and camera shake are kind of the same thing when you think about the cause: relative motion of the camera and the object. You mention slow shutter speed -- it is a culprit in both cases.
Focus misses are subjective as they depend on the intent on the photographer. Without knowing what the photographer wanted to focus on, it's impossible to achieve this. And even if you do know what you wanted to focus on, it still wouldn't be trivial.
With that dose of realism aside, let me reassure you that blur detection is actually a very active research field, and there are already a few metrics that you can try out on your images. Here are some that I've used recently:
Edge width. Basically, perform edge detection on your image (using Canny or otherwise) and then measure the width of the edges. Blurry images will have wider edges that are more spread out. Sharper images will have thinner edges. Google for "A no-reference perceptual blur metric" by Marziliano -- it's a famous paper that describes this approach well enough for a full implementation. If you're dealing with motion blur, then the edges will be blurred (wide) in the direction of the motion.
Presence of fine detail. Have a look at my answer to this question (the edited part).
Frequency domain approaches. Taking the histogram of the DCT coefficients of the image (assuming you're working with JPEG) would give you an idea of how much fine detail the image has. This is how you grab the DCT coefficients from a JPEG file directly. If the count for the non-DC terms is low, it is likely that the image is blurry. This is the simplest way -- there are more sophisticated approaches in the frequency domain.
There are more, but I feel that that should be enough to get you started. If you require further info on either of those points, fire up Google Scholar and look around. In particular, check out the references of Marziliano's paper to get an idea about what has been tried in the past.
There is a great paper called : "analysis of focus measure operators for shape-from-focus" (https://www.researchgate.net/publication/234073157_Analysis_of_focus_measure_operators_in_shape-from-focus) , which does a comparison about 30 different techniques.
Out of all the different techniques, the "Laplacian" based methods seem to have the best performance. Most image processing programs like : MATLAB or OPENCV have already implemented this method . Below is an example using OpenCV : http://www.pyimagesearch.com/2015/09/07/blur-detection-with-opencv/
One important point to note here is that an image can have some blurry areas and some sharp areas. For example, if an image contains portrait photography, the image in the foreground is sharp whereas the background is blurry. In sports photography, the object in focus is sharp and the background usually has motion blur. One way to detect such a spatially varying blur in an image is to run a frequency domain analysis at every location in the image. One of the papers which addresses this topic is "Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes" (cvpr2017).
the authors look at multi resolution DCT coefficients at every pixel. These DCT coefficients are divided into low, medium, and high frequency bands, out of which only the high frequency coefficients are selected.
The DCT coefficients are then fused together and sorted to form the multiscale-fused and sorted high-frequency transform coefficients
A subset of these coefficients are selected. the number of selected coefficients is a tunable parameter which is application specific.
The selected subset of coefficients are then sent through a max pooling block to retain the highest activation within all the scales. This gives the blur map as the output, which is then sent through a post processing step to refine the map.
This blur map can be used to quantify the sharpness in various regions of the image. In order to get a single global metric to quantify the bluriness of the entire image, the mean of this blur map or the histogram of this blur map can be used
Here are some examples results on how the algorithm performs:
The sharp regions in the image have a high intensity in the blur_map, whereas blurry regions have a low intensity.
The github link to the project is: https://github.com/Utkarsh-Deshmukh/Spatially-Varying-Blur-Detection-python
The python implementation of this algorithm can be found on pypi which can easily be installed as shown below:
pip install blur_detector
A sample code snippet to generate the blur map is as follows:
import blur_detector
import cv2
if __name__ == '__main__':
img = cv2.imread('image_name', 0)
blur_map = blur_detector.detectBlur(img, downsampling_factor=4, num_scales=4, scale_start=2, num_iterations_RF_filter=3)
cv2.imshow('ori_img', img)
cv2.imshow('blur_map', blur_map)
cv2.waitKey(0)
For detecting blurry images, you can tweak the approach and add "Region of Interest estimation".
In this github link: https://github.com/Utkarsh-Deshmukh/Blurry-Image-Detector , I have used local entropy filters to estimate a region of interest. In this ROI, I then use DCT coefficients as feature extractors and train a simple multi-layer perceptron. On testing this approach on 20000 images in the "BSD-B" dataset (http://cg.postech.ac.kr/research/realblur/) I got an average accuracy of 94%
Just to add on the focussing errors, these may be detected by comparing the psf of the captured blurry images (wider) with reference ones (sharper). Deconvolution techniques may help correcting them but leaving artificial errors (shadows, rippling, ...). A light field camera can help refocusing to any depth planes since it captures the angular information besides the traditional spatial ones of the scene.
For a project of mine, I'm required to process images differences with OpenCV. The goal is to detect an intrusion in a zone.
To be a little more clear, here are the inputs and outputs:
Inputs:
An image of reference
A second image from approximately the same point of view (can be an error margin)
Outputs:
Detection of new objects in the scene.
Bonus:
Recognition of those objects.
For me, the most difficult part of it is to take off small differences (luminosity, camera position margin error, movement of trees...)
I already read a lot about OpenCV image processing (subtraction, erosion, threshold, SIFT, SURF...) and have some good results.
What I would like is a list of steps you think is the best to have a good detection (humans, cars...), and the algorithms to do each step.
Many thanks for your help.
Track-by-Detect, human tracker:
You apply the Hog detector to detect humans.
You draw a respective rectangle as foreground area on the foreground mask.
You pass this mask to "The OpenCV Video Surveillance / Blob Tracker Facility"
You can, now, group the passing humans based on their blob.{x,y} values into public/restricted areas.
I had to deal with this problem the last year.
I suggest an adaptive background-foreground estimation algorithm which produced a foreground mask.
On top of that, you add a blob detector and tracker, and then calculate if an intersection takes place between the blobs and your intrusion area.
Opencv comes has samples of all of these within the legacy code. Ofcourse, if you want you can also use your own or other versions of these.
Links:
http://opencv.willowgarage.com/wiki/VideoSurveillance
http://experienceopencv.blogspot.gr/2011/03/blob-tracking-video-surveillance-demo.html
I would definitely start with a running average background subtraction if the camera is static. Then you can use findContours() to find the intruding object's location and size. If you want to detect humans that are walking around in a scene, I would recommend looking at using the built-in haar classifier:
http://docs.opencv.org/doc/tutorials/objdetect/cascade_classifier/cascade_classifier.html#cascade-classifier
where you would just replace the xml with the upperbody classifier.