I have a problem, not so easy to solve i guess. In general, I have a database of frames from different videos and I want to find for a given picture (which is not necessarily one of the frames but from some same source video) the matching source video.
So lets say I have some videos and extracted frames each x seconds. The frames are stored in the db.
My guess would now be to loop over all video frames in the db and try to find matching features. So I would somehow have to find features in the source image and then try to find these in the frames stored in the db.
My question is how can I achieve this? The problem is that camera angle and vieweing distance can be quite different when the picture in question was not taken quite close to the time the frame was extracted previously.
Is this even feasible?
I'm working with Python and OpenCV.
Thanks and best regards
Related
What am I trying to do?
Listen to camera video
Detect faces
Save only faces to folder
The problem:
I have done all of those things above EXCEPT it gives me bunch of same person faces because it checks it on every frame it captures and gives as new face when it's the same person.
I want the script to understand that it's the same person and skip it. (of course it depends on accuracy overall, but that's okay, as long as it's not giving me 60 files of same face a second)
So I was thinking to somehow use face_verify within the same library, but couldn't make it working quickly and decided to ask first instead of wasting time on something what most likely not gonna work.
Any suggestions? Hopefully described it well, also didn't find any duplicates of this question.
Thanks in advance
It depends on what you are using, face-detection or face-recognition.
Face-detection will just detect faces and return bounding box for each frame. In this case you can use any simple tracking algorithm (like SORT) which will give tracking ID for each bounding boxes in each frame. This way you can ensure to save only 1 face for each tracking ID
In case of Face-recognition, it's all the more easier as each detected face has an associated label (similar to a tracking ID in the above approach). So you can simply save face-images based on labels (1 image per label)
Can I modify the pixel value of frames(to hide some information) after extracting it from a video file and then generating the new video with the help of modified (in terms of pixel value) frames so that I can retrieve my information on again extracting the frames from new video?
I've used OpenCV to try this but it seems there's some compression being done on frames while extracting them or maybe while putting them together because I was not able to retrieve my hidden information in the pixels.
Do you know is this achievable? And if yes, then please suggest me a way to do this in python.
I have tried this code but it results in loss of my information on pixel level because I think some compression is being done somewhere.
I have continuous videos taken from two cameras placed on up right and up left corners of my car's windshield (please note that they are not fixed to each other, and I aligned them approximately straight). Now I am trying to make a 3D point cloud out of that and have no idea how to do that. I surfed the internet a lot and still couldn't find any useful info. Can you send me some links or hints on how can I make that work in Python.
You can try the stereo matching and point cloud generation implementation in the OpenCV library. Start with this short Python sample.
I suppose that you have two independent video streams that are not exactly synchronized. You will have to synchronize them first, because the linked sample expects two images, not videos. Extract images from videos using OpenCV or ffmpeg and find an image pair that shares exactly the same timepoint (e.g. green appearing on a traffic light). Alternatively you can use the audio tracks for synchronization, see https://github.com/benkno/audio-offset-finder. Beware: synchronization based on a single frame pair or a short audio excerpt will probably work only for few minutes before and after the synchronized timepoint.
I have a fixed camera and I need to check if its position or orientation has been changed. I am trying to use OpenCV (calculating diiferencies between a reference image and a new one) for this, but I am pretty new to OpenCV (and image processing in general) but I am not really sure what specific algorithm would be the best to use for this, or how to interpret the results to find if the camera has been moved/rotated. Any ideas?
Please help,
One way to do it would be to register the two frames to each other using affine image registration from openCV. From this you can extract the rotation and displacement difference between the two frames. Unfortunately this will only work well for in-plane rotations but I still think it is your best bet.
If you post some sample code and data I would be happy to take a look.
You can use Canny or HoughLinesP to find lines,From this you can get two lines,compare it.Maybe this will be effective in some simple background.if some object in your picture,try sift or other feature extractor,you can take features to find the relationship from two frames.
I am getting video input from 2 separate cameras with some area of overlap between the output videos. I have tried out a code which combines the video output horizontally. Here is the link for that code:
https://github.com/rajatsaxena/NeuroscienceLab/blob/master/positiontracking/combinevid.py
To explain the problem visually:
The red part shows the overlap region between two image frame. I need the output to look like the second image, with first frame in blue and second frame in green (as shown in third illustration)
A solutions I can think of but unable to implement is, Using SIFT/SURF find out the maximum distance keypoints from both frames and then take the first video frame completely and just pick the non overlapping region from second video frame and horizontally combine them to get the stitched output.
Let me know of any other solutions possible as well. Thanks!
I read this post one hour ago. I tried some really easy approach. Not perfect but in some cases should work well. For example, if you have both cameras on one frame placed side by side.
I took 2 images from the phone like on a picture (color images). Program select Rectangles region from both source images and resize end extract this roi rectangles. The idea is to find the "best" overlapping Rect regions by normalized correlation.
M1 and M2 is mat roi to compare,
matchTemplate(M1, M2, res, TM_CCOEFF_NORMED);
After, I find this overlapping Rect use this to crop source images and combine by hconcat() function together.
My code is in C++ but is really simple to replicate this in python. It is not the best solution but one of the most simple solution. If your cameras are fixed in stable position between themselves. This is a good solution I think.
I hold my phone in hand :)
You can also use this simple approach on video. The speed depends only on the number of rectangle candidate you compare.
You can improve this by smart region to compare selection.
Also, I am thinking about another idea to use optical flow by putting your images from a camera at the same time to sequence behind each other. From the possible overlapping regions in one image extract good features to track and find them in the region of second images.
Surf and sift are great for this but this is the most simple idea on my mind.
Code is Here Code