archer71's profile - activity

A few issues I would like to point out regarding the use of the FLANN index.

The use case if trying to match one image to a list of images ( LIST OF IMAGES, NOT SEVERAL CATEGORIES OF IMAGES), I am trying to find a specific image in a database.

1. It is strange that I have to concat all the descriptors using vconcat. You might say I could use the descriptor->compute function and actually pass it a vector<mat> however I can't do that becuase:

2. There is no way of mapping matched images back to the original image. Lowe's implemented Flann has a way. There should be a constructor which accepts a vector<mat> during the creation of the index. Or the result indices should contain imgIdx, so I can map it back to the original image.

3.Storing index to disk works, however when I try to load it back, it expects the size of the supermatrix I previously created. This defeats the purpose of actually saving the file, the constructor is used identically to when it was first created. How should I know the size? The loading part should not expect any size of Mat as input, it should be saved when the index is stored on disk.

Solved this, was using the wrong path.

Trying to follow the steps here:

http://docs.opencv.org/3.0-last-rst/d...

But after running the python script I get:

<working_dict>/ios/build/iPhoneOS-armv7/attempt/opencv" does not exist. Specify --help for usage, or press the help button on the CMake GUI. ('Child returned:', 1)

From what I have understood from reading the documentation, I should choose the same algorithms for both feature extraction, creating the descriptiors and then detecting the object. So first questions I have is what algorithm is the most optimal for this use-case? I will only be using iPhone 5S and newer phones, so I am expecting very good FPS, but I would want the same algorithm to be used because I understood it gives the best results. So what do you recommend? SURF/SIFT/FAST/ORB/ some deep learning?

Please suggest what algorithms/tutorials/ how can I achieve the following steps:

1. Extract features from a (one) high-quality image on the web.
2. Transform into a .xml or .dat file.
3. Port file to an ARM, ios or android.
4. Obtain video frames
5. Apply image recognition, feature extraction etc. to detected object
6. Get coordinates of objects on every frame scanned Out of scope of openCV but maybe someone can help:
7. Render a video on top of the coordinates

Being completely new to computer vision (but having worked in c++/java/python) I will directly show you what I am trying to accomplish and any help would be appreciated. Specifically, I would like to know if someone can outline the process that needs to be done, and provide some materials/tutorials, I will search and implement everything myself.

The first use case from this video. How would this be accomplished?

Thank you.