pablofdezalc / kaze Goto Github PK

Kaze throws an error when executing with AOS:

OpenCV Error: Sizes of input arguments do not match (The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array') in arithm_op, file /tmp/opencv3-20170308-12431-1olfhjn/opencv-3.2.0/modules/core/src/arithm.cpp, line 659
libc++abi.dylib: terminating with uncaught exception of type cv::Exception: /tmp/opencv3-20170308-12431-1olfhjn/opencv-3.2.0/modules/core/src/arithm.cpp:659: error: (-209) The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array' in function arithm_op

[1]    40925 abort      ./kaze_features real.jpg --use_fed 0z

Please tell me what needs to be changed to make it work with AOS

considering the memory and speed, i don't need so much keypoints, so how i can sort the keypoints to get the top N ?

I am having a hard time trying to understand the Octaves and Sub-levels in the Non-Linear Scale space. For the SIFT- Octaves is a collection of same sized images and sub-level is number of blurred images to be generated in the octave. How can this be explained in KAZE and AKAZE?
I want to tune the parameters and so need to understand this properly.

Is "fe780181937c55d1e38050d4343a351e14537f8c" latest commit compatible with OpenCV 2? Can you please assign a tag or a branch to it?

Hi

I am trying to interface KAZE with matlab. But while compilation, I get the following error:

kaze.cpp: In function ‘void mexFunction(int, mxArray**, int, const mxArray**)’:
kaze.cpp:198:3: error: ‘KAZE’ was not declared in this scope
KAZE evolution(options);
kaze.cpp:198:3: note: suggested alternatives:
In file included from /usr/local/include/opencv2/opencv.hpp:50:0,
from ../src/lib/utils.h:12,
from ../src/lib/KAZE.h:15,
from kaze.cpp:22:
/usr/local/include/opencv2/features2d.hpp:514:20: note: ‘cv::KAZE’
class CV_EXPORTS_W KAZE : public Feature2D
^
In file included from kaze.cpp:22:0:
../src/lib/KAZE.h:43:9: note: ‘libKAZE::KAZE’
class KAZE {

kaze.cpp:199:3: error: ‘evolution’ was not declared in this scope
evolution.Create_Nonlinear_Scale_Space(img_32);

mex: compile of ' "kaze.cpp"' failed.

Hi, I am trying to compile and get the following error:

[ 66%] Linking CXX executable ../bin/kaze_match
Undefined symbols for architecture x86_64:
"cv::imwrite(cv::String const&, cv::_InputArray const&, std::__1::vector<int, std::__1::allocator > const&)", referenced from:
libKAZE::KAZE::Save_Scale_Space() in libKAZE.a(KAZE.cpp.o)
libKAZE::KAZE::Save_Detector_Responses() in libKAZE.a(KAZE.cpp.o)
"cv::DescriptorMatcher::knnMatch(cv::_InputArray const&, cv::_InputArray const&, std::__1::vector<std::__1::vector<cv::DMatch, std::__1::allocatorcv::DMatch >, std::__1::allocator<std::__1::vector<cv::DMatch, std::__1::allocatorcv::DMatch > > >&, int, cv::_InputArray const&, bool) const", referenced from:
_main in kaze_match.cpp.o
ld: symbol(s) not found for architecture x86_64
clang: error: linker command failed with exit code 1 (use -v to see invocation)
make[2]: *** [bin/kaze_match] Error 1
make[1]: *** [src/CMakeFiles/kaze_match.dir/all] Error 2
make: *** [all] Error 2

I am not sure what has happened, googled it, but its so broad this issue - Undefined symbols for architecture x86_64.

System:

Mac OS 10.14.6

After I succeed compiling the KAZE project as the reference on your github, and run ./kaze_features img.jpg. There comes the following instruction:

Illegal instruction (core dumped)

And then the program exit.

I'm looking forward to implement your detector on my human detection project in Python