我正在尝试为使用C / C ++编写的应用程序创建一个python包装器,它广泛使用OpenCV C API。我想使用ctypes来做这件事,因为我已经在以前的程序中成功使用过它。但是当我尝试将IplImage从Python作为参数传递给c库中的函数时,我遇到了问题。
我已经创建了一个示例测试库来演示该问题。以下是我想要使用的库中的函数:
// ImageDll.h
#include "opencv2/opencv.hpp"
extern "C" //Tells the compile to use C-linkage for the next scope.
{
// Returns image loaded from location
__declspec(dllexport) IplImage* Load(char* dir);
// Show image
__declspec(dllexport) void Show(IplImage* img);
}
和一个cpp文件:
// ImageDll.cpp
// compile with: /EHsc /LD
#include "ImageDll.h"
using namespace std;
extern "C" //Tells the compile to use C-linkage for the next scope.
{
IplImage* Load(char* dir)
{
return cvLoadImage(dir, CV_LOAD_IMAGE_COLOR);
}
void Show(IplImage* img)
{
cvShowImage("image", img);
cvWaitKey(0);
}
}
这是python中的初始尝试:
from time import sleep
from ctypes import *
from modules.acquisition import InitCamera, GetImage
from modules.utils import struct
import cv2.cv as cv
# load DLL containing image functions
print "Loading shared library with genetic algorithm...",
image_lib = cdll.LoadLibrary("OpenCV_test_DLL.dll")
print "Done."
# get function handles
print "Loading functions of library...",
image_load = image_lib.Load
image_show = image_lib.Show
# set return type for functions (because ctypes default is int)
image_load.restype = c_void_p
image_show.restype = None
print "Done."
# initialize source
print "Initializing camera",
source = struct()
InitCamera(source)
print "Done."
# show video
while (1):
# get image as PIL image
img = GetImage(source)
# transform image to OpenCV IplImage
cv_img = cv.CreateImageHeader(img.size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_img, img.tostring())
# show image using OpenCV highgui lib
image_show(pointer(cv_img))
正如您所看到的,我从相机获取图像作为PIL图像,然后我将其转换为python IplImage。这适用于100%,因为当我用cv2.cv模块中的python绑定替换最后一行 image_show(pointer(cv_img))时:
cv.ShowImage("image", cv_img)
cv.WaitKey(20)
然后我得到正确的输出。
问题出在 image_show(指针(cv_img)),但 TypeError: type 必须有存储信息。这是因为cv_img需要是有效的ctypes IplImage结构。我试图用ctypes模仿它,但收效甚微:
from ctypes import *
from cv2 import cv
# ctypes IplImage
class cIplImage(Structure):
_fields_ = [("nSize", c_int),
("ID", c_int),
("nChannels", c_int),
("alphaChannel", c_int),
("depth", c_int),
("colorModel", c_char * 4),
("channelSeq", c_char * 4),
("dataOrder", c_int),
("origin", c_int),
("align", c_int),
("width", c_int),
("height", c_int),
("roi", c_void_p),
("maskROI", c_void_p),
("imageID", c_void_p),
("tileInfo", c_void_p),
("imageSize", c_int),
("imageData", c_char_p),
("widthStep", c_int),
("BorderMode", c_int * 4),
("BorderConst", c_int * 4),
("imageDataOrigin", c_char_p)]
以下是执行转换的功能:
# convert Python PIL to ctypes Ipl
def PIL2Ipl(input_img):
# mode dictionary:
# (pil_mode : (ipl_depth, ipl_channels)
mode_list = {
"RGB" : (cv.IPL_DEPTH_8U, 3),
"L" : (cv.IPL_DEPTH_8U, 1),
"F" : (cv.IPL_DEPTH_32F, 1)
}
if not mode_list.has_key(input_img.mode):
raise ValueError, 'unknown or unsupported input mode'
result = cIplImage()
result.imageData = c_char_p(input_img.tostring())
result.depth = c_int(mode_list[input_img.mode][0])
result.channels = c_int(mode_list[input_img.mode][1])
result.height = c_int(input_img.size[0])
result.width = c_int(input_img.size[1])
return result
("imageData", c_char_p),
("widthStep", c_int),
("BorderMode", c_int * 4),
("BorderConst", c_int * 4),
("imageDataOrigin", c_char_p)]
视频循环然后更改为
# show video
while (1):
# get image as PIL image
img = GetImage(source)
# transform image to OpenCV IplImage
cv_img = cIplImage()
cv_img = PIL2Ipl(img)
# show image using OpenCV highgui lib
image_show(pointer(cv_img))
这样数据就会传递给库,但是它会在未知函数中呼叫 OpenCV错误:错误标志(参数或结构字段)(无法识别或不支持的数组类型)。因此创建的ctypes结构无效。有谁知道如何正确实现它?当我能够将 python IplImage传递给c库时,我会接受其他不使用ctypes的解决方案。感谢。
注意:我过去2天试图找到这个问题的答案但没有成功。有OpenCV 1.0的解决方案,但最近使用numpy数组的Python的OpenCV绑定几乎不可能使Python和C应用程序之间的接口工作。 :(
答案 0 :(得分:3)
最后,我找到了解决问题的方法。而不是使用默认的python函数
cv.CreateImageHeader()
cv.SetData()
我使用从OpenCV C库导出的C函数。 :)我甚至设法将颜色从PILs RGB翻转为IplImage BGR格式。以下是完整的资料来源:
<强> ImageDll.h 强>
#include "opencv2/opencv.hpp"
extern "C" //Tells the compile to use C-linkage for the next scope.
{
// Returns image loaded from location
__declspec(dllexport) IplImage* Load(char* dir);
// Show image
__declspec(dllexport) void Show(IplImage* img);
// Auxiliary functions
__declspec(dllexport) void aux_cvSetData(CvArr* arr, void* data, int step);
__declspec(dllexport) IplImage* aux_cvCreateImageHeader(int width, int height, int depth, int channels);
__declspec(dllexport) IplImage* aux_cvCvtColor(const IplImage* src, int code);
__declspec(dllexport) void aux_cvCopy(const CvArr* src, CvArr* dst);
__declspec(dllexport) void aux_cvReleaseImage(IplImage** image);
__declspec(dllexport) void aux_cvReleaseImageHeader(IplImage** image);
}
<强> ImageDll.cpp 强>
#include "ImageDll.h"
using namespace std;
extern "C" //Tells the compile to use C-linkage for the next scope.
{
IplImage* Load(char* dir)
{
return cvLoadImage(dir, CV_LOAD_IMAGE_COLOR);
}
void Show(IplImage* img)
{
cvShowImage("image", img);
cvWaitKey(5);
}
void aux_cvSetData(CvArr* arr, void* data, int step)
{
cvSetData(arr,data,step);
}
IplImage* aux_cvCreateImageHeader(int width, int height, int depth, int channels)
{
return cvCreateImageHeader(cvSize(width,height), depth, channels);
}
IplImage* aux_cvCvtColor(const IplImage* src, int code)
{
IplImage* dst = cvCreateImage(cvSize(src->width,src->height),src->depth,src->nChannels);
cvCvtColor(src, dst, code);
return dst;
}
void aux_cvCopy(const CvArr* src, CvArr* dst)
{
cvCopy(src, dst, NULL);
}
void aux_cvReleaseImage(IplImage** image)
{
cvReleaseImage(image);
}
void aux_cvReleaseImageHeader(IplImage** image)
{
cvReleaseImageHeader(image);
}
}
<强> run.py 强>
# This Python file uses the following encoding: utf-8
from time import sleep
from ctypes import *
from modules.acquisition import InitCamera, GetImage
from modules.utils import struct
import cv2.cv as cv
from modules.ipl import *
# load DLL containing image functions
print "Loading shared library with C functions...",
image_lib = cdll.LoadLibrary("OpenCV_test_DLL.dll")
print "Done."
# get function handles
print "Loading functions of library...",
image_load = image_lib.Load
image_show = image_lib.Show
cvReleaseImage = image_lib.aux_cvReleaseImage
# set return type for functions (because ctypes default is int)
image_load.restype = c_void_p
image_show.restype = None
cvReleaseImage.restype = None
print "Done."
# initialize source
print "Initializing camera",
source = struct()
InitCamera(source)
print "Done."
# show video
while (1):
# get image as PIL image
img = GetImage(source)
# transform image to OpenCV IplImage
cv_img = PIL2Ipl(img)
# show image using OpenCV highgui lib
image_show(cv_img)
# release memory
cvReleaseImage(byref(cv_img))
<强> ipl.py 强>
from ctypes import *
from cv2 import cv
# ctypes IplImage
class cIplImage(Structure):
_fields_ = [("nSize", c_int),
("ID", c_int),
("nChannels", c_int),
("alphaChannel", c_int),
("depth", c_int),
("colorModel", c_char * 4),
("channelSeq", c_char * 4),
("dataOrder", c_int),
("origin", c_int),
("align", c_int),
("width", c_int),
("height", c_int),
("roi", c_void_p),
("maskROI", c_void_p),
("imageID", c_void_p),
("tileInfo", c_void_p),
("imageSize", c_int),
("imageData", POINTER(c_char)),
("widthStep", c_int),
("BorderMode", c_int * 4),
("BorderConst", c_int * 4),
("imageDataOrigin", c_char_p)]
# load DLL containing needed OpenCV functions
libr = cdll.LoadLibrary("OpenCV_test_DLL.dll")
cvSetData = libr.aux_cvSetData
cvCreateImageHeader = libr.aux_cvCreateImageHeader
cvCvtColor = libr.aux_cvCvtColor
cvCopy = libr.aux_cvCopy
cvReleaseImage = libr.aux_cvReleaseImage
cvReleaseImageHeader = libr.aux_cvReleaseImageHeader
# set return types for library functions
cvSetData.restype = None
cvCreateImageHeader.restype = POINTER(cIplImage)
cvCvtColor.restype = POINTER(cIplImage)
cvCopy.restype = None
cvReleaseImage.restype = None
cvReleaseImageHeader.restype = None
#print "auxlib loaded"
# convert Python PIL to ctypes Ipl
def PIL2Ipl(pil_img):
"""Converts a PIL image to the OpenCV/IplImage data format.
Supported input image formats are:
RGB
L
F
"""
# mode dictionary:
# (pil_mode : (ipl_depth, ipl_channels)
mode_list = {
"RGB" : (cv.IPL_DEPTH_8U, 3),
"L" : (cv.IPL_DEPTH_8U, 1),
"F" : (cv.IPL_DEPTH_32F, 1)
}
if not mode_list.has_key(pil_img.mode):
raise ValueError, 'unknown or unsupported input mode'
depth = c_int(mode_list[pil_img.mode][0])
channels = c_int(mode_list[pil_img.mode][1])
height = c_int(pil_img.size[1])
width = c_int(pil_img.size[0])
data = pil_img.tostring()
ipl_img = cvCreateImageHeader(width, height, depth, channels);
cvSetData(ipl_img, create_string_buffer(data,len(data)), c_int(width.value * channels.value))
brg_img = cvCvtColor(ipl_img,cv.CV_RGB2BGR)
cvReleaseImageHeader(byref(ipl_img))
return brg_img
希望它会帮助某人:)