Saving high quality images, doing live processing - what's the best approach? - ios

I'm still learning about AVFoundation, so I'm unsure how best I should approach the problem of needing to capture a high quality still image, but provide a low-quality preview video stream.
I've got an app that needs to take high quality images (AVCaptureSessionPresetPhoto), but process the preview video stream using OpenCV - for which a much lower resolution is acceptable. Simply using the base OpenCV Video Camera class is no good, as setting the defaultAVCaptureSessionPreset to AVCaptureSessionPresetPhoto results in the full resolution frame being passed to processImage - which is very slow indeed.
How can I have a high-quality connection to the device that I can use for capturing the still image, and a low-quality connection that can be processed and displayed? A description of how I need to set up sessions/connections would be very helpful. Is there an open-source example of such an app?

I did something similar - I grabbed the pixels in the delegate method, made a CGImageRef of them, then dispatched that to the normal priority queue, where it was modified. Since AVFoundation must be using a CADisplayLink for the callback method it has highest priority. In my particular case I was not grabbing all pixels so it worked on an iPhone 4 at 30fps. Depending on what devices you want to run you have number of pixels, fps, etc trade offs.
Another idea is to grab a power of 2 subset of pixels - for instance every 4th in each row and every 4th row. Again I did something similar in my app at 20-30fps. You can then further operate on this smaller image in dispatched blocks.
If this seems daunting offer a bounty for working code.
CODE:
// Image is oriented with bottle neck to the left and the bottle bottom on the right
- (void)captureOutput:(AVCaptureVideoDataOutput *)captureOutput didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer fromConnection:(AVCaptureConnection *)connection
{
#if 1
AVCaptureDevice *camera = [(AVCaptureDeviceInput *)[captureSession.inputs lastObject] device];
if(camera.adjustingWhiteBalance || camera.adjustingExposure) NSLog(#"GOTCHA: %d %d", camera.adjustingWhiteBalance, camera.adjustingExposure);
printf("foo\n");
#endif
if(saveState != saveOne && saveState != saveAll) return;
#autoreleasepool {
CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
//NSLog(#"PE: value=%lld timeScale=%d flags=%x", prStamp.value, prStamp.timescale, prStamp.flags);
/*Lock the image buffer*/
CVPixelBufferLockBaseAddress(imageBuffer,0);
NSRange captureRange;
if(saveState == saveOne) {
#if 0 // B G R A MODE !
NSLog(#"PIXEL_TYPE: 0x%lx", CVPixelBufferGetPixelFormatType(imageBuffer));
uint8_t *newPtr = (uint8_t *)CVPixelBufferGetBaseAddress(imageBuffer);
NSLog(#"ONE VAL %x %x %x %x", newPtr[0], newPtr[1], newPtr[2], newPtr[3]);
}
exit(0);
#endif
[edgeFinder setupImageBuffer:imageBuffer];
BOOL success = [edgeFinder delineate:1];
if(!success) {
dispatch_async(dispatch_get_main_queue(), ^{ edgeFinder = nil; [delegate error]; });
saveState = saveNone;
} else
bottleRange = edgeFinder.sides;
xRange.location = edgeFinder.shoulder;
xRange.length = edgeFinder.bottom - xRange.location;
NSLog(#"bottleRange 1: %# neck=%d bottom=%d", NSStringFromRange(bottleRange), edgeFinder.shoulder, edgeFinder.bottom );
//searchRows = [edgeFinder expandRange:bottleRange];
rowsPerSwath = lrintf((bottleRange.length*NUM_DEGREES_TO_GRAB)*(float)M_PI/360.0f);
NSLog(#"rowsPerSwath = %d", rowsPerSwath);
saveState = saveIdling;
captureRange = NSMakeRange(0, [WLIPBase numRows]);
dispatch_async(dispatch_get_main_queue(), ^
{
[delegate focusDone];
edgeFinder = nil;
captureOutput.alwaysDiscardsLateVideoFrames = YES;
});
} else {
NSInteger rows = rowsPerSwath;
NSInteger newOffset = bottleRange.length - rows;
if(newOffset & 1) {
--newOffset;
++rows;
}
captureRange = NSMakeRange(bottleRange.location + newOffset/2, rows);
}
//NSLog(#"captureRange=%u %u", captureRange.location, captureRange.length);
/*Get information about the image*/
uint8_t *baseAddress = (uint8_t *)CVPixelBufferGetBaseAddress(imageBuffer);
size_t bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer);
size_t width = CVPixelBufferGetWidth(imageBuffer);
// Note Apple sample code cheats big time - the phone is big endian so this reverses the "apparent" order of bytes
CGContextRef newContext = CGBitmapContextCreate(NULL, width, captureRange.length, 8, bytesPerRow, colorSpace, kCGImageAlphaNoneSkipFirst | kCGBitmapByteOrder32Little); // Video in ARGB format
assert(newContext);
uint8_t *newPtr = (uint8_t *)CGBitmapContextGetData(newContext);
size_t offset = captureRange.location * bytesPerRow;
memcpy(newPtr, baseAddress + offset, captureRange.length * bytesPerRow);
CVPixelBufferUnlockBaseAddress(imageBuffer, 0);
OSAtomicIncrement32(&totalImages);
int32_t curDepth = OSAtomicIncrement32(&queueDepth);
if(curDepth > maxDepth) maxDepth = curDepth;
#define kImageContext #"kImageContext"
#define kState #"kState"
#define kPresTime #"kPresTime"
CMTime prStamp = CMSampleBufferGetPresentationTimeStamp(sampleBuffer); // when it was taken?
//CMTime deStamp = CMSampleBufferGetDecodeTimeStamp(sampleBuffer); // now?
NSDictionary *dict = [NSDictionary dictionaryWithObjectsAndKeys:
[NSValue valueWithBytes:&saveState objCType:#encode(saveImages)], kState,
[NSValue valueWithNonretainedObject:(__bridge id)newContext], kImageContext,
[NSValue valueWithBytes:&prStamp objCType:#encode(CMTime)], kPresTime,
nil ];
dispatch_async(imageQueue, ^
{
// could be on any thread now
OSAtomicDecrement32(&queueDepth);
if(!isCancelled) {
saveImages state; [(NSValue *)[dict objectForKey:kState] getValue:&state];
CGContextRef context; [(NSValue *)[dict objectForKey:kImageContext] getValue:&context];
CMTime stamp; [(NSValue *)[dict objectForKey:kPresTime] getValue:&stamp];
CGImageRef newImageRef = CGBitmapContextCreateImage(context);
CGContextRelease(context);
UIImageOrientation orient = state == saveOne ? UIImageOrientationLeft : UIImageOrientationUp;
UIImage *image = [UIImage imageWithCGImage:newImageRef scale:1.0 orientation:orient]; // imageWithCGImage: UIImageOrientationUp UIImageOrientationLeft
CGImageRelease(newImageRef);
NSData *data = UIImagePNGRepresentation(image);
// NSLog(#"STATE:[%d]: value=%lld timeScale=%d flags=%x", state, stamp.value, stamp.timescale, stamp.flags);
{
NSString *name = [NSString stringWithFormat:#"%d.png", num];
NSString *path = [[wlAppDelegate snippetsDirectory] stringByAppendingPathComponent:name];
BOOL ret = [data writeToFile:path atomically:NO];
//NSLog(#"WROTE %d err=%d w/time %f path:%#", num, ret, (double)stamp.value/(double)stamp.timescale, path);
if(!ret) {
++errors;
} else {
dispatch_async(dispatch_get_main_queue(), ^
{
if(num) [delegate progress:(CGFloat)num/(CGFloat)(MORE_THAN_ONE_REV * SNAPS_PER_SEC) file:path];
} );
}
++num;
}
} else NSLog(#"CANCELLED");
} );
}
}

In AVCaptureSessionPresetPhoto it use small video preview(about 1000x700 for iPhone6) and high resolution photo(about 3000x2000).
So I use modified 'CvPhotoCamera' class to process small preview and take photo of full-size picture. I post this code here: https://stackoverflow.com/a/31478505/1994445

Related

Why is Yp Cb Cr image buffer all shuffled in iOS 13?

I have a computer vision app that takes grayscale images from sensor and processes them. The image acquisition for iOS is written in Obj-C and the image processing is performed in C++ using OpenCV. As I only need the luminance data, I acquire the image in YUV (or Yp Cb Cr) 420 bi-planar full range format and just assign the buffer's data to an OpenCV Mat object (see aquisition code below). This worked great so far, until the brand new iOS 13 came out... For some reason, on iOS 13 the image I obtain is misaligned, resulting in diagonal stripes. By looking at the image I obtain, I suspect this is the consequence of a change in ordering of the buffer's Y Cb an Cr components or a change in the buffer's stride. Does anyone know if iOS 13 introduces this kind of changes and how I could update my code to avoid this, preferably in a backward-compatible manner?
Here is my image acquisition code:
//capture config
- (void)initialize {
AVCaptureDevice *frontCameraDevice;
NSArray *devices = [AVCaptureDevice devicesWithMediaType:AVMediaTypeVideo];
for (AVCaptureDevice *device in devices) {
if (device.position == AVCaptureDevicePositionFront) {
frontCameraDevice = device;
}
}
if (frontCameraDevice == nil) {
NSLog(#"Front camera device not found");
return;
}
_session = [[AVCaptureSession alloc] init];
_session.sessionPreset = AVCaptureSessionPreset640x480;
NSError *error = nil;
AVCaptureDeviceInput *input = [AVCaptureDeviceInput deviceInputWithDevice:frontCameraDevice error: &error];
if (error != nil) {
NSLog(#"Error getting front camera device input: %#", error);
}
if ([_session canAddInput:input]) {
[_session addInput:input];
} else {
NSLog(#"Could not add front camera device input to session");
}
AVCaptureVideoDataOutput *videoOutput = [[AVCaptureVideoDataOutput alloc] init];
// This is the default, but making it explicit
videoOutput.alwaysDiscardsLateVideoFrames = YES;
if ([videoOutput.availableVideoCVPixelFormatTypes containsObject:
[NSNumber numberWithInt:kCVPixelFormatType_420YpCbCr8BiPlanarFullRange]]) {
OSType format = kCVPixelFormatType_420YpCbCr8BiPlanarFullRange;
videoOutput.videoSettings = [NSDictionary dictionaryWithObject:[NSNumber numberWithUnsignedInt:format]
forKey:(id)kCVPixelBufferPixelFormatTypeKey];
} else {
NSLog(#"YUV format not available");
}
[videoOutput setSampleBufferDelegate:self queue:dispatch_queue_create("extrapage.camera.capture.sample.buffer.delegate", DISPATCH_QUEUE_SERIAL)];
if ([_session canAddOutput:videoOutput]) {
[_session addOutput:videoOutput];
} else {
NSLog(#"Could not add video output to session");
}
AVCaptureConnection *captureConnection = [videoOutput connectionWithMediaType:AVMediaTypeVideo];
captureConnection.videoOrientation = AVCaptureVideoOrientationPortrait;
}
//acquisition code
- (void)captureOutput:(AVCaptureOutput *)output didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer fromConnection:(AVCaptureConnection *)connection {
if (_listener != nil) {
CVPixelBufferRef pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
OSType format = CVPixelBufferGetPixelFormatType(pixelBuffer);
NSAssert(format == kCVPixelFormatType_420YpCbCr8BiPlanarFullRange, #"Only YUV is supported");
// The first plane / channel (at index 0) is the grayscale plane
// See more infomation about the YUV format
// http://en.wikipedia.org/wiki/YUV
CVPixelBufferLockBaseAddress(pixelBuffer, 0);
void *baseaddress = CVPixelBufferGetBaseAddressOfPlane(pixelBuffer, 0);
CGFloat width = CVPixelBufferGetWidth(pixelBuffer);
CGFloat height = CVPixelBufferGetHeight(pixelBuffer);
cv::Mat frame(height, width, CV_8UC1, baseaddress, 0);
[_listener onNewFrame:frame];
CVPixelBufferUnlockBaseAddress(pixelBuffer, 0);
}
}
I found the solution to this problem. It was a row stride issue: appearently, in iOS 13, the row stride of the Yp Cb Cr 4:2:0 8 bit bi-planar buffer was changed. Maybe for it to always be a power of 2. Therefore in some cases, the row stride is no longer the same as the width. It was the case for me. The fix is easy, just get the row stride from the buffer's info and pass it to the OpenCV Mat's constructor as shown below.
void *baseaddress = CVPixelBufferGetBaseAddressOfPlane(pixelBuffer, 0);
size_t width = CVPixelBufferGetWidthOfPlane(pixelBuffer, 0);
size_t height = CVPixelBufferGetHeightOfPlane(pixelBuffer, 0);
size_t bytesPerRow = CVPixelBufferGetBytesPerRowOfPlane(pixelBuffer, 0);
cv::Mat frame(height, width, CV_8UC1, baseaddress, bytesPerRow);
Note that I also changed how I get the width and height by using the dimensions of the plane instead of the ones of the buffer. For the Y plane, it should always be the same. I am not sure that this makes a difference.
Also be careful: after the Xcode update to support the iOS 13 SDK, I had to uninstall my app from the test device because otherwise, Xcode kept running the old version instead of the newly compiled one.
this is not an answer, but we have a similar problem. I tried with different resolution used in photo capture, only one resolution (2592 x 1936) does not work, other resolutions does work. I think change the resolution to 1440x1920 for example may be a workaround to your problem.

Capturing a still image from camera in OpenCV Mat format

I am developing an iOS application and trying to get a still image snapshot from the camera using capture session but I'm unable to convert it successfully to an OpenCV Mat.
The still image output is created using this code:
- (void)createStillImageOutput;
{
// setup still image output with jpeg codec
self.stillImageOutput = [[AVCaptureStillImageOutput alloc] init];
NSDictionary *outputSettings = [NSDictionary dictionaryWithObjectsAndKeys:AVVideoCodecJPEG, AVVideoCodecKey, nil];
[self.stillImageOutput setOutputSettings:outputSettings];
[self.captureSession addOutput:self.stillImageOutput];
for (AVCaptureConnection *connection in self.stillImageOutput.connections) {
for (AVCaptureInputPort *port in [connection inputPorts]) {
if ([port.mediaType isEqual:AVMediaTypeVideo]) {
self.videoCaptureConnection = connection;
break;
}
}
if (self.videoCaptureConnection) {
break;
}
}
NSLog(#"[Camera] still image output created");
}
And then attempting to capture a still image using this code:
[self.stillImageOutput captureStillImageAsynchronouslyFromConnection:self.videoCaptureConnection
completionHandler:
^(CMSampleBufferRef imageSampleBuffer, NSError *error)
{
if (error == nil && imageSampleBuffer != NULL)
{
NSData *jpegData = [AVCaptureStillImageOutput jpegStillImageNSDataRepresentation:imageSampleBuffer];
}
I need a way to create an OpenCV Mat based on the pixel data in the buffer.
I have tried creating a Mat using this code which I have taken from OpenCV video camera class camera here:
CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
CVPixelBufferLockBaseAddress(imageBuffer, 0);
void* bufferAddress;
size_t width;
size_t height;
size_t bytesPerRow;
CGColorSpaceRef colorSpace;
CGContextRef context;
int format_opencv;
OSType format = CVPixelBufferGetPixelFormatType(imageBuffer);
if (format == kCVPixelFormatType_420YpCbCr8BiPlanarFullRange) {
format_opencv = CV_8UC1;
bufferAddress = CVPixelBufferGetBaseAddressOfPlane(imageBuffer, 0);
width = CVPixelBufferGetWidthOfPlane(imageBuffer, 0);
height = CVPixelBufferGetHeightOfPlane(imageBuffer, 0);
bytesPerRow = CVPixelBufferGetBytesPerRowOfPlane(imageBuffer, 0);
} else { // expect kCVPixelFormatType_32BGRA
format_opencv = CV_8UC4;
bufferAddress = CVPixelBufferGetBaseAddress(imageBuffer);
width = CVPixelBufferGetWidth(imageBuffer);
height = CVPixelBufferGetHeight(imageBuffer);
bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer);
}
cv::Mat image(height, width, format_opencv, bufferAddress, bytesPerRow);
but it fails to get the actual height and width of the image on the CVPixelBufferGetWidth or CVPixelBufferGetHeight call and so the creation of Mat fails.
I'm aware that I can create a UIImage based on the pixel data using this code:
UIImage* newImage = [UIImage imageWithData:jpegData];
But I prefer to construct a CvMat directly as it is the case in the OpenCV CvVideoCamera class because I'm interested in handling the image in OpenCV only and I don't want to consume time converting again and not risk losing quality or having issues with orientation (anyway the UIImagetoCV conversion function provided by OpenCV is causing me memory leaks and not freeing the memory).
Please advise how can I get the image as an OpenCV Mat.
Thanks in advance.
I have found the solution for my problem.
the Solution is :
by overriding this method in the OpenCv Camera Class : "createVideoPreviewLayer"
it should look like this :
- (void)createVideoPreviewLayer;
{
self.parentView.layer.sublayers = nil;
if (captureVideoPreviewLayer == nil) {
captureVideoPreviewLayer = [[AVCaptureVideoPreviewLayer alloc]
initWithSession:self.captureSession];
}
if (self.parentView != nil) {
captureVideoPreviewLayer.frame = self.parentView.bounds;
captureVideoPreviewLayer.videoGravity =
AVLayerVideoGravityResizeAspectFill;
[self.parentView.layer addSublayer:captureVideoPreviewLayer];
}
NSLog(#"[Camera] created AVCaptureVideoPreviewLayer");
}
you should add this line to the "createVideoPreviewLayer" method will solve
the problem :
self.parentView.layer.sublayers = nil;
and you need to use the pause method instead of the stop method

cv::Mat doesn't match UIImageView width?

I am using AVFoundation to capture video frames, process with opencv and display the result in an UIImageView on the new iPad. The opencv process does the followings ("inImg" is the video frame) :
cv::Mat testROI = inImg.rowRange(0,100);
testROI = testROI.colRange(0,10);
testROI.setTo(255); // this is a BGRA frame.
However, instead of getting a vertical white bar (100 row x 10 col) on the top left corner of the frame, I got 100 stair-like horizontal lines from top right corner to the bottom left, each with 10 pixel long.
After some investigation, I realized that the width of the displayed frame seems to be 8 pixel wider than the cv::Mat. (i.e. the 9th pixel of the 2nd row is right below the 1st pixel of the 1st row.).
The video frame itself is shown correctly (no displacement between rows).
The problem appears when the AVCaptureSession.sessionPreset is AVCaptureSessionPresetMedium (frame rows=480, cols=360) but does not appear when it is AVCaptureSessionPresetHigh (frame rows=640, cols=480).
There are 360 cols shown in full screen. (I tried traverse and modify the cv::Mat pixel-by-pixel. Pixel 1-360 were shown correctly. 361-368 disappeared and 369 was shown right under pixel 1).
I tried combinations of imageview.contentMode (UIViewContentModeScaleAspectFill and UIViewContentModeScaleAspectFit) and imageview.clipsToBound (YES/NO) but no luck.
What could be the problem?
Thank you very much.
I use the following code to create the AVCaptureSession:
NSArray* devices = [AVCaptureDevice devicesWithMediaType:AVMediaTypeVideo];
if ([devices count] == 0) {
NSLog(#"No video capture devices found");
return NO;
}
for (AVCaptureDevice *device in devices) {
if ([device position] == AVCaptureDevicePositionFront) {
_captureDevice = device;
}
}
NSError* error_exp = nil;
if ([_captureDevice lockForConfiguration:&error_exp]) {
[_captureDevice setWhiteBalanceMode:AVCaptureWhiteBalanceModeContinuousAutoWhiteBalance];
[_captureDevice unlockForConfiguration];
}
// Create the capture session
_captureSession = [[AVCaptureSession alloc] init];
_captureSession.sessionPreset = AVCaptureSessionPresetMedium;
// Create device input
NSError *error = nil;
AVCaptureDeviceInput *input = [[AVCaptureDeviceInput alloc] initWithDevice:_captureDevice error:&error];
// Create and configure device output
_videoOutput = [[AVCaptureVideoDataOutput alloc] init];
dispatch_queue_t queue = dispatch_queue_create("cameraQueue", NULL);
[_videoOutput setSampleBufferDelegate:self queue:queue];
dispatch_release(queue);
_videoOutput.alwaysDiscardsLateVideoFrames = YES;
OSType format = kCVPixelFormatType_32BGRA;
_videoOutput.videoSettings = [NSDictionary dictionaryWithObject:[NSNumber numberWithUnsignedInt:format]forKey:(id)kCVPixelBufferPixelFormatTypeKey];
// Connect up inputs and outputs
if ([_captureSession canAddInput:input]) {
[_captureSession addInput:input];
}
if ([_captureSession canAddOutput:_videoOutput]) {
[_captureSession addOutput:_videoOutput];
}
AVCaptureConnection * captureConnection = [_videoOutput connectionWithMediaType:AVMediaTypeVideo];
if (captureConnection.isVideoMinFrameDurationSupported)
captureConnection.videoMinFrameDuration = CMTimeMake(1, 60);
if (captureConnection.isVideoMaxFrameDurationSupported)
captureConnection.videoMaxFrameDuration = CMTimeMake(1, 60);
if (captureConnection.supportsVideoMirroring)
[captureConnection setVideoMirrored:NO];
[captureConnection setVideoOrientation:AVCaptureVideoOrientationPortraitUpsideDown];
When a frame is received, the followings is called:
- (void)captureOutput:(AVCaptureOutput *)captureOutput didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer fromConnection:(AVCaptureConnection *)connection
{
#autoreleasepool {
CVPixelBufferRef pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
OSType format = CVPixelBufferGetPixelFormatType(pixelBuffer);
CGRect videoRect = CGRectMake(0.0f, 0.0f, CVPixelBufferGetWidth(pixelBuffer), CVPixelBufferGetHeight(pixelBuffer));
AVCaptureConnection *currentConnection = [[_videoOutput connections] objectAtIndex:0];
AVCaptureVideoOrientation videoOrientation = [currentConnection videoOrientation];
CGImageRef quartzImage;
// For color mode a 4-channel cv::Mat is created from the BGRA data
CVPixelBufferLockBaseAddress(pixelBuffer, 0);
void *baseaddress = CVPixelBufferGetBaseAddress(pixelBuffer);
cv::Mat mat(videoRect.size.height, videoRect.size.width, CV_8UC4, baseaddress, 0);
if ([self doFrame]) { // a flag to switch processing ON/OFF
[self processFrame:mat videoRect:videoRect videoOrientation:videoOrientation]; // "processFrame" is the opencv function shown above
}
CIImage *ciImage = [CIImage imageWithCVPixelBuffer:pixelBuffer];
quartzImage = [self.context createCGImage:ciImage fromRect:ciImage.extent];
CVPixelBufferUnlockBaseAddress(pixelBuffer, 0);
UIImage *image = [UIImage imageWithCGImage:quartzImage scale:1.0 orientation:UIImageOrientationUp];
CGImageRelease(quartzImage);
[self.imageView performSelectorOnMainThread:#selector(setImage:) withObject:image waitUntilDone:YES];
I assume you're using the constructor Mat(int _rows, int _cols, int _type, void* _data, size_t _step=AUTO_STEP) and that AUTO_STEP is 0 and assumes that the row stride is width*bytesPerPixel.
This is generally wrong — it's very common to align rows to some larger boundary. In this case, 360 is not a multiple of 16 but 368 is; which strongly suggests that it's aligning to 16-pixel boundaries (perhaps to assist algorithms that process in 16×16 blocks?).
Try
cv::Mat mat(videoRect.size.height, videoRect.size.width, CV_8UC4, baseaddress, CVPixelBufferGetBytesPerRow(pixelBuffer));

The iPhone 3GS and kCVPixelFormatType_420YpCbCr8BiPlanarFullRange format?

I'm developing an iOS application with latest SDK and testing it on an iPhone 3GS.
I'm doing this on init method:
CFDictionaryRef formatDictionary = CVPixelFormatDescriptionCreateWithPixelFormatType(kCFAllocatorDefault, kCVPixelFormatType_420YpCbCr8BiPlanarFullRange);
CFNumberRef val = (CFNumberRef) CFDictionaryGetValue(formatDictionary, kCVPixelFormatBitsPerBlock);
if (val != nil)
{
CFNumberGetValue(val,kCFNumberSInt8Type, &_bytesPerPixel);
_bytesPerPixel /= 8;
}
else
_bytesPerPixel = 4;
But val is always nil.
And here:
- (void)captureOutput:(AVCaptureOutput *)captureOutput
didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer
fromConnection:(AVCaptureConnection *)connection
{
CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
//Lock the image buffer//
CVPixelBufferLockBaseAddress(imageBuffer,0);
//Get information about the image//
uint8_t *baseAddress = (uint8_t *)CVPixelBufferGetBaseAddress(imageBuffer);
size_t width = CVPixelBufferGetWidth(imageBuffer);
size_t height = CVPixelBufferGetHeight(imageBuffer);
//size_t stride = CVPixelBufferGetBytesPerRow(imageBuffer);
//put buffer in open cv, no memory copied
cv::Mat image = cv::Mat(height, width, CV_8UC4, baseAddress);
// copy the image
//cv::Mat copied_image = image.clone();
[_previewBufferLock lock];
memcpy(baseAddress, _lastFrame, _previewSurfaceHeight * _previewSurfaceWidth * _bytesPerPixel);
[_previewBufferLock unlock];
//We unlock the image buffer//
CVPixelBufferUnlockBaseAddress(imageBuffer,0);
}
I have add a breakpoint on memcpy line and I these are my vars values:
But I'm getting an EXEC_BAD_ACCESS here: memcpy(baseAddress, _lastFrame, _previewSurfaceHeight * _previewSurfaceWidth * _bytesPerPixel);
Does the iPhone 3GS support kCVPixelFormatType_420YpCbCr8BiPlanarFullRange?
No, the iPhone 3GS does not have support for kCVPixelFormatType_420YpCbCr8BiPlanarFullRange as an output buffer type from the camera, only kCVPixelFormatType_420YpCbCr8BiPlanarVideoRange. The iPhone 4S and iPhone 5 have support for the full-range YUV output, but older devices do not.
You can test this availability using the following code:
videoOutput = [[AVCaptureVideoDataOutput alloc] init];
BOOL supportsFullYUVRange = NO;
NSArray *supportedPixelFormats = videoOutput.availableVideoCVPixelFormatTypes;
for (NSNumber *currentPixelFormat in supportedPixelFormats)
{
if ([currentPixelFormat intValue] == kCVPixelFormatType_420YpCbCr8BiPlanarFullRange)
{
supportsFullYUVRange = YES;
}
}

Encoding raw YUV420P to h264 with AVCodec on iOS

I am trying to encode a single YUV420P image gathered from a CMSampleBuffer to an AVPacket so that I can send h264 video over the network with RTMP.
The posted code example seems to work as avcodec_encode_video2 returns 0 (Success) however got_output is also 0 (AVPacket is empty).
Does anyone have any experience with encoding video on iOS devices that might know what I am doing wrong?
- (void) captureOutput:(AVCaptureOutput *)captureOutput
didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer
fromConnection:(AVCaptureConnection *)connection {
// sampleBuffer now contains an individual frame of raw video frames
CVPixelBufferRef pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
CVPixelBufferLockBaseAddress(pixelBuffer, 0);
// access the data
int width = CVPixelBufferGetWidth(pixelBuffer);
int height = CVPixelBufferGetHeight(pixelBuffer);
int bytesPerRow = CVPixelBufferGetBytesPerRowOfPlane(pixelBuffer, 0);
unsigned char *rawPixelBase = (unsigned char *)CVPixelBufferGetBaseAddressOfPlane(pixelBuffer, 0);
// Convert the raw pixel base to h.264 format
AVCodec *codec = 0;
AVCodecContext *context = 0;
AVFrame *frame = 0;
AVPacket packet;
//avcodec_init();
avcodec_register_all();
codec = avcodec_find_encoder(AV_CODEC_ID_H264);
if (codec == 0) {
NSLog(#"Codec not found!!");
return;
}
context = avcodec_alloc_context3(codec);
if (!context) {
NSLog(#"Context no bueno.");
return;
}
// Bit rate
context->bit_rate = 400000; // HARD CODE
context->bit_rate_tolerance = 10;
// Resolution
context->width = width;
context->height = height;
// Frames Per Second
context->time_base = (AVRational) {1,25};
context->gop_size = 1;
//context->max_b_frames = 1;
context->pix_fmt = PIX_FMT_YUV420P;
// Open the codec
if (avcodec_open2(context, codec, 0) < 0) {
NSLog(#"Unable to open codec");
return;
}
// Create the frame
frame = avcodec_alloc_frame();
if (!frame) {
NSLog(#"Unable to alloc frame");
return;
}
frame->format = context->pix_fmt;
frame->width = context->width;
frame->height = context->height;
avpicture_fill((AVPicture *) frame, rawPixelBase, context->pix_fmt, frame->width, frame->height);
int got_output = 0;
av_init_packet(&packet);
avcodec_encode_video2(context, &packet, frame, &got_output)
// Unlock the pixel data
CVPixelBufferUnlockBaseAddress(pixelBuffer, 0);
// Send the data over the network
[self uploadData:[NSData dataWithBytes:packet.data length:packet.size] toRTMP:self.rtmp_OutVideoStream];
}
Note: It is known that this code has memory leaks because I am not freeing the memory that is dynamically allocated.
UPDATE
I updated my code to use #pogorskiy method. I only try to upload the frame if got output returns 1 and clear the buffer once I am done encoding video frames.

Resources