I'm doing an opencv project which needs to detect a image on the screen, which will disappear after some time it shows up. It needs to save the most amount of frames possible while the image is showing, and stop when it disappears. I plan to use the data collected to do a ConvNet, so the more frames I can capture, the better.
I was using template matching full-screen to search for the image and to identify when it disappears, but I was only capturing about 30% of the total frames, with the screen at 30FPS.
Wanting to increase frame capture rate, I changed to searching full-screen with template matching until the image was found, and then the area for searching was reduced to the coordinates found of the image with a little margin, so the program could identify when the image disapeared using a lot less resources (because of a very smaller área to check if the image was still there). This allowed me to capture 60% of the frames.
However I want to know, can I do something else to allow me to optimize my program? I feel like doing template matching for every frame is overkill. Is object tracking better in this case, or it won't even work because the image disapears?
PS: the image stays for about 7~10 seconds on the screen and takes about the same time to pop up again.
I ended using numpy to save the captured frames and reached 99% efficiency with the reduced area, no resizing of the images or multiprocessing.
Related
So the current methods for capturing a downscaled image is to capture the full thing then downscale it, but I'm trying to go fast and thus don't want to capture the full image only every 10th pixel giving me an image 144 along and 108 down. which would result in a 10X speed increase because I don't have to get all the pixels from a full resolution just the few I want.
Thanks in advance
I don't think this is possible due to driver/library limitations, I'm thinking they'd be sending you the entire frame, try looking into the library you're using
I want to play a video using python-vlc. I have gotten everything to work, and the video plays without any technical issues. There is this one aesthetic issue, though. I only want to play part of the video. As in, I want to crop out a fair bit on the bottom and a good bit on the right. I know I can do this with a call to MediaPlayer.video_set_crop_geometry(), and I've done so semi-successfully. However, the actual window that opens is the one that is adjusted for the entire video, with the part that I want centered in the middle with black bars around it. (If I call MediaPlayer.video_set_scale(), then the cropped-out bit the same size as it would be if I didn't crop. If I don't call video_set_scale(), the cropped-out bit is stretched, maintaining aspect ratio, until it reaches the edge of the window. Regardless, there are black bars).
Can I get the window to adjust to this new, smaller video? Preferably automatically, but if I have to pass in the size I want, that's fine too.
I have tried shuffling around the order between the different calls to no avail. Clearly python-vlc has the capacity somewhere to adjust the window it's playing in, as it can open a window the correct size for the regular video to play, and it adjusts automaticallty after calling video_set_scale(), but only to fit the original video, not the cropped one.
You should probably share more details, such as your full code and platform used.
That being said, libvlc doesn't offer an API to resize the native Window it draws on, but you can easily do it yourself (with win32 APIs for HWND, on Windows, for example).
I'm trying to implement a video overlay solution such as this one: https://www.videologixinc.com/, where there is no delay in the original source video.
My problem is that, with OpenCV, all the necessary drawings (circle, text, etc) requires the entire frame to be processed and then returned to be exhibited. Is there any solution where I could just overlay the information in the original source without implying in delay/frame drop? (the additional information can be displayed with delay - drawings, text - but not the original video pipeline).
Multiprocessing could make things faster, but I would still have delay or frame drops.
I was also thinking if would be better to have two simultaneous applications and maybe two different computers - one to read the frame and make the processing - and another one to just receive, somehow, the information to overlay it on the original video pipeline.
Any thoughts? Thank you all!
An example of data pipeline in this case, without interfering in the original video flow
I have a video file of evening time ( 6pm-9pm). And I want to detect movement of people on the road.
While trying to find the difference between a handful of images from "10 minute" time frame videos (10 equally time spaced images within any 10 minutes video frame clip) I'm facing these challenges:
All the images are coming as different (coming as Alert) because there is some plant moving due to wind all the time.
All the 10 images are coming different also because the sun is setting down and hence due to "natural light variation" the 10
images from 10 minute frames after coming different even though
there is no public/human movement.
How do I restrict my algorithm to focus only on movements ion certain area of the video rather than all of it ? (Couldn't find
anything on google or dont know if there's any algo in opencv for this)
This one is rather difficult to deal with. I recommend you try to blur the frames a little bit to reduce the noises from moving plants. Also, if the range of the movement is not so large, try changing the difference threshold and area threshold (if your algorithm contains contour detection as the following step). Hope this can help a little bit.
For detecting "movement" of people, a (10 frame/10 min) fps is a little too low. People in the frames can be totally different. This means you cannot detect the movement of a single person, but to find the differences between two frames. In the case where you are using low fps videos, I recommend you try Background Subtraction, to find people in the frames instead of people movements between the frames. For Background Subtraction, to solve
All the 10 images are coming different also because the sun is setting down and hence due to "natural light variation" the 10 images from 10 minute frames after coming different even though there is no public/human movement.
you can try using the average image of all frames as the background_img in
difference = current_img - background_img
If the time span is longer, you can use the average of images more recent to current_img as background_img. And keep updating background_img when running the video.
If your ROI is a rectangle in the frame, use
my_ROI = cv::Rect(x, y, width, height)
cv::Mat ROI_img= frame(my_ROI)
If not, try using a mask.
I think what you are looking for is a Pedestrian Detection. You can do this easily in Python with OpenCV package.
# Initialize a HOG descriptor
hog = cv2.HOGDescriptor()
# Set it for Pedestrian Detection
hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
# Then use the detector
hog.detectMultiScale()
Exemple : Pedestrian Detection OpenCV
I have a django based website in which I have created profiles of people working in the organisation. Since this is a redesign effort, I used the already existing profile pictures. The size of current profile image style is 170x190px. Since the images already exist and are of different sizes, I want to crop them to the size specified above. But how do I decide from which side I have to crop?
Currently, I have applied style of 170by190 to all the images while displaying in profiles, but most of them look distorted as the aspect ratios do not match.
I have tried PIL thumbnail function but it does not fit the need.
Please suggest a solution.
Well, you have to resize pictures, but images ratio create huge impact on final result. As images have some ratio, and you cannot simply resize them to 170px190px without prior adjusting of their ratio, so you have to update( not crop them!) images before resizing them to get best possible output, it can be done in next ways:
Crop them manually to desired ratio (17:19). (take a while if you have plenty of images)
Create script which add padding to that images if image ratio is close to required, all images which ratio is far away from desired mark as 'human cropping required' and work with their ratio later by own (semi-manual, so still may be really time consuming)
Spend some time and write face recognation function, then process images with that function and find faces, then crop them from origin image, but before: add padding to achieve desired radio (17:19) at top and bottom of face. (recommended)
Some links which may be use full for you:
Face Recognition With Python, in Under 25 Lines of Code
facereclib module, they probably are able to help you.
Image Manipulation, The Hitchhiker’s Guide
Good luck !
Use sorl-thumbnail, you don't need to crop every image manually.