Искал похожую вещь и решил "накатить свой". Я понимаю, что это старый пост, но на случай, если кто-то еще его ищет, вот мое решение. это относительно быстро и грязно и нормализует изображение до «полного масштаба». изображения, которые он создает, являются «широкими», т.е. вам нужно поместить их в UIScrollView или иным образом управлять отображением.
это основано на некоторых ответах на этот вопрос
Образец выходных данных
РЕДАКТИРОВАТЬ: Я добавил логарифмическую версию методов усреднения и рендеринга, альтернативную версию и результаты сравнения см. в конце этого сообщения. Я лично предпочитаю исходную линейную версию, но решил опубликовать ее, на случай, если кто-то сможет улучшить используемый алгоритм.
Вам понадобятся следующие импортированные данные:
#import <MediaPlayer/MediaPlayer.h>
#import <AVFoundation/AVFoundation.h>
Во-первых, общий метод рендеринга, который принимает указатель на усредненные образцы данных
и возвращает UIImage. Обратите внимание, что эти образцы не являются воспроизводимыми аудиосэмплами.
-(UIImage *) audioImageGraph:(SInt16 *) samples
normalizeMax:(SInt16) normalizeMax
sampleCount:(NSInteger) sampleCount
channelCount:(NSInteger) channelCount
imageHeight:(float) imageHeight {
CGSize imageSize = CGSizeMake(sampleCount, imageHeight);
UIGraphicsBeginImageContext(imageSize);
CGContextRef context = UIGraphicsGetCurrentContext();
CGContextSetFillColorWithColor(context, [UIColor blackColor].CGColor);
CGContextSetAlpha(context,1.0);
CGRect rect;
rect.size = imageSize;
rect.origin.x = 0;
rect.origin.y = 0;
CGColorRef leftcolor = [[UIColor whiteColor] CGColor];
CGColorRef rightcolor = [[UIColor redColor] CGColor];
CGContextFillRect(context, rect);
CGContextSetLineWidth(context, 1.0);
float halfGraphHeight = (imageHeight / 2) / (float) channelCount ;
float centerLeft = halfGraphHeight;
float centerRight = (halfGraphHeight*3) ;
float sampleAdjustmentFactor = (imageHeight/ (float) channelCount) / (float) normalizeMax;
for (NSInteger intSample = 0 ; intSample < sampleCount ; intSample ++ ) {
SInt16 left = *samples++;
float pixels = (float) left;
pixels *= sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerLeft-pixels);
CGContextAddLineToPoint(context, intSample, centerLeft+pixels);
CGContextSetStrokeColorWithColor(context, leftcolor);
CGContextStrokePath(context);
if (channelCount==2) {
SInt16 right = *samples++;
float pixels = (float) right;
pixels *= sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerRight - pixels);
CGContextAddLineToPoint(context, intSample, centerRight + pixels);
CGContextSetStrokeColorWithColor(context, rightcolor);
CGContextStrokePath(context);
}
}
// Create new image
UIImage *newImage = UIGraphicsGetImageFromCurrentImageContext();
// Tidy up
UIGraphicsEndImageContext();
return newImage;
}
Затем метод, который принимает AVURLAsset и возвращает данные изображения PNG
- (NSData *) renderPNGAudioPictogramForAsset:(AVURLAsset *)songAsset {
NSError * error = nil;
AVAssetReader * reader = [[AVAssetReader alloc] initWithAsset:songAsset error:&error];
AVAssetTrack * songTrack = [songAsset.tracks objectAtIndex:0];
NSDictionary* outputSettingsDict = [[NSDictionary alloc] initWithObjectsAndKeys:
[NSNumber numberWithInt:kAudioFormatLinearPCM],AVFormatIDKey,
// [NSNumber numberWithInt:44100.0],AVSampleRateKey, /*Not Supported*/
// [NSNumber numberWithInt: 2],AVNumberOfChannelsKey, /*Not Supported*/
[NSNumber numberWithInt:16],AVLinearPCMBitDepthKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsBigEndianKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsFloatKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsNonInterleaved,
nil];
AVAssetReaderTrackOutput* output = [[AVAssetReaderTrackOutput alloc] initWithTrack:songTrack outputSettings:outputSettingsDict];
[reader addOutput:output];
[output release];
UInt32 sampleRate,channelCount;
NSArray* formatDesc = songTrack.formatDescriptions;
for(unsigned int i = 0; i < [formatDesc count]; ++i) {
CMAudioFormatDescriptionRef item = (CMAudioFormatDescriptionRef)[formatDesc objectAtIndex:i];
const AudioStreamBasicDescription* fmtDesc = CMAudioFormatDescriptionGetStreamBasicDescription (item);
if(fmtDesc ) {
sampleRate = fmtDesc->mSampleRate;
channelCount = fmtDesc->mChannelsPerFrame;
// NSLog(@"channels:%u, bytes/packet: %u, sampleRate %f",fmtDesc->mChannelsPerFrame, fmtDesc->mBytesPerPacket,fmtDesc->mSampleRate);
}
}
UInt32 bytesPerSample = 2 * channelCount;
SInt16 normalizeMax = 0;
NSMutableData * fullSongData = [[NSMutableData alloc] init];
[reader startReading];
UInt64 totalBytes = 0;
SInt64 totalLeft = 0;
SInt64 totalRight = 0;
NSInteger sampleTally = 0;
NSInteger samplesPerPixel = sampleRate / 50;
while (reader.status == AVAssetReaderStatusReading){
AVAssetReaderTrackOutput * trackOutput = (AVAssetReaderTrackOutput *)[reader.outputs objectAtIndex:0];
CMSampleBufferRef sampleBufferRef = [trackOutput copyNextSampleBuffer];
if (sampleBufferRef){
CMBlockBufferRef blockBufferRef = CMSampleBufferGetDataBuffer(sampleBufferRef);
size_t length = CMBlockBufferGetDataLength(blockBufferRef);
totalBytes += length;
NSAutoreleasePool *wader = [[NSAutoreleasePool alloc] init];
NSMutableData * data = [NSMutableData dataWithLength:length];
CMBlockBufferCopyDataBytes(blockBufferRef, 0, length, data.mutableBytes);
SInt16 * samples = (SInt16 *) data.mutableBytes;
int sampleCount = length / bytesPerSample;
for (int i = 0; i < sampleCount ; i ++) {
SInt16 left = *samples++;
totalLeft += left;
SInt16 right;
if (channelCount==2) {
right = *samples++;
totalRight += right;
}
sampleTally++;
if (sampleTally > samplesPerPixel) {
left = totalLeft / sampleTally;
SInt16 fix = abs(left);
if (fix > normalizeMax) {
normalizeMax = fix;
}
[fullSongData appendBytes:&left length:sizeof(left)];
if (channelCount==2) {
right = totalRight / sampleTally;
SInt16 fix = abs(right);
if (fix > normalizeMax) {
normalizeMax = fix;
}
[fullSongData appendBytes:&right length:sizeof(right)];
}
totalLeft = 0;
totalRight = 0;
sampleTally = 0;
}
}
[wader drain];
CMSampleBufferInvalidate(sampleBufferRef);
CFRelease(sampleBufferRef);
}
}
NSData * finalData = nil;
if (reader.status == AVAssetReaderStatusFailed || reader.status == AVAssetReaderStatusUnknown){
// Something went wrong. return nil
return nil;
}
if (reader.status == AVAssetReaderStatusCompleted){
NSLog(@"rendering output graphics using normalizeMax %d",normalizeMax);
UIImage *test = [self audioImageGraph:(SInt16 *)
fullSongData.bytes
normalizeMax:normalizeMax
sampleCount:fullSongData.length / 4
channelCount:2
imageHeight:100];
finalData = imageToData(test);
}
[fullSongData release];
[reader release];
return finalData;
}
Расширенный вариант:, наконец, если вы хотите иметь возможность воспроизводить звук с помощью AVAudioPlayer, вам необходимо кэшировать его в папку кэша пакета ваших приложений. Поскольку я делал это, я решил также кэшировать данные изображения и обернул все это в категорию UIImage. вам необходимо включить это предложение с открытым исходным кодом для извлечения аудио и некоторый код из здесь для обработки фоновой потоковой передачи Особенности.
сначала несколько определений и несколько общих методов класса для обработки имен путей и т. д.
//#define imgExt @"jpg"
//#define imageToData(x) UIImageJPEGRepresentation(x,4)
#define imgExt @"png"
#define imageToData(x) UIImagePNGRepresentation(x)
+ (NSString *) assetCacheFolder {
NSArray *assetFolderRoot = NSSearchPathForDirectoriesInDomains(NSCachesDirectory, NSUserDomainMask, YES);
return [NSString stringWithFormat:@"%@/audio", [assetFolderRoot objectAtIndex:0]];
}
+ (NSString *) cachedAudioPictogramPathForMPMediaItem:(MPMediaItem*) item {
NSString *assetFolder = [[self class] assetCacheFolder];
NSNumber * libraryId = [item valueForProperty:MPMediaItemPropertyPersistentID];
NSString *assetPictogramFilename = [NSString stringWithFormat:@"asset_%@.%@",libraryId,imgExt];
return [NSString stringWithFormat:@"%@/%@", assetFolder, assetPictogramFilename];
}
+ (NSString *) cachedAudioFilepathForMPMediaItem:(MPMediaItem*) item {
NSString *assetFolder = [[self class] assetCacheFolder];
NSURL * assetURL = [item valueForProperty:MPMediaItemPropertyAssetURL];
NSNumber * libraryId = [item valueForProperty:MPMediaItemPropertyPersistentID];
NSString *assetFileExt = [[[assetURL path] lastPathComponent] pathExtension];
NSString *assetFilename = [NSString stringWithFormat:@"asset_%@.%@",libraryId,assetFileExt];
return [NSString stringWithFormat:@"%@/%@", assetFolder, assetFilename];
}
+ (NSURL *) cachedAudioURLForMPMediaItem:(MPMediaItem*) item {
NSString *assetFilepath = [[self class] cachedAudioFilepathForMPMediaItem:item];
return [NSURL fileURLWithPath:assetFilepath];
}
Теперь о методе инициализации, который делает "свое дело"
- (id) initWithMPMediaItem:(MPMediaItem*) item
completionBlock:(void (^)(UIImage* delayedImagePreparation))completionBlock {
NSFileManager *fman = [NSFileManager defaultManager];
NSString *assetPictogramFilepath = [[self class] cachedAudioPictogramPathForMPMediaItem:item];
if ([fman fileExistsAtPath:assetPictogramFilepath]) {
NSLog(@"Returning cached waveform pictogram: %@",[assetPictogramFilepath lastPathComponent]);
self = [self initWithContentsOfFile:assetPictogramFilepath];
return self;
}
NSString *assetFilepath = [[self class] cachedAudioFilepathForMPMediaItem:item];
NSURL *assetFileURL = [NSURL fileURLWithPath:assetFilepath];
if ([fman fileExistsAtPath:assetFilepath]) {
NSLog(@"scanning cached audio data to create UIImage file: %@",[assetFilepath lastPathComponent]);
[assetFileURL retain];
[assetPictogramFilepath retain];
[NSThread MCSM_performBlockInBackground: ^{
AVURLAsset *asset = [[AVURLAsset alloc] initWithURL:assetFileURL options:nil];
NSData *waveFormData = [self renderPNGAudioPictogramForAsset:asset];
[waveFormData writeToFile:assetPictogramFilepath atomically:YES];
[assetFileURL release];
[assetPictogramFilepath release];
if (completionBlock) {
[waveFormData retain];
[NSThread MCSM_performBlockOnMainThread:^{
UIImage *result = [UIImage imageWithData:waveFormData];
NSLog(@"returning rendered pictogram on main thread (%d bytes %@ data in UIImage %0.0f x %0.0f pixels)",waveFormData.length,[imgExt uppercaseString],result.size.width,result.size.height);
completionBlock(result);
[waveFormData release];
}];
}
}];
return nil;
} else {
NSString *assetFolder = [[self class] assetCacheFolder];
[fman createDirectoryAtPath:assetFolder withIntermediateDirectories:YES attributes:nil error:nil];
NSLog(@"Preparing to import audio asset data %@",[assetFilepath lastPathComponent]);
[assetPictogramFilepath retain];
[assetFileURL retain];
TSLibraryImport* import = [[TSLibraryImport alloc] init];
NSURL * assetURL = [item valueForProperty:MPMediaItemPropertyAssetURL];
[import importAsset:assetURL toURL:assetFileURL completionBlock:^(TSLibraryImport* import) {
//check the status and error properties of
//TSLibraryImport
if (import.error) {
NSLog (@"audio data import failed:%@",import.error);
} else{
NSLog (@"Creating waveform pictogram file: %@", [assetPictogramFilepath lastPathComponent]);
AVURLAsset *asset = [[AVURLAsset alloc] initWithURL:assetFileURL options:nil];
NSData *waveFormData = [self renderPNGAudioPictogramForAsset:asset];
[waveFormData writeToFile:assetPictogramFilepath atomically:YES];
if (completionBlock) {
[waveFormData retain];
[NSThread MCSM_performBlockOnMainThread:^{
UIImage *result = [UIImage imageWithData:waveFormData];
NSLog(@"returning rendered pictogram on main thread (%d bytes %@ data in UIImage %0.0f x %0.0f pixels)",waveFormData.length,[imgExt uppercaseString],result.size.width,result.size.height);
completionBlock(result);
[waveFormData release];
}];
}
}
[assetPictogramFilepath release];
[assetFileURL release];
} ];
return nil;
}
}
Пример вызова этого:
-(void) importMediaItem {
MPMediaItem* item = [self mediaItem];
// since we will be needing this for playback, save the url to the cached audio.
[url release];
url = [[UIImage cachedAudioURLForMPMediaItem:item] retain];
[waveFormImage release];
waveFormImage = [[UIImage alloc ] initWithMPMediaItem:item completionBlock:^(UIImage* delayedImagePreparation){
waveFormImage = [delayedImagePreparation retain];
[self displayWaveFormImage];
}];
if (waveFormImage) {
[waveFormImage retain];
[self displayWaveFormImage];
}
}
Логарифмическая версия методов усреднения и рендеринга
#define absX(x) (x<0?0-x:x)
#define minMaxX(x,mn,mx) (x<=mn?mn:(x>=mx?mx:x))
#define noiseFloor (-90.0)
#define decibel(amplitude) (20.0 * log10(absX(amplitude)/32767.0))
-(UIImage *) audioImageLogGraph:(Float32 *) samples
normalizeMax:(Float32) normalizeMax
sampleCount:(NSInteger) sampleCount
channelCount:(NSInteger) channelCount
imageHeight:(float) imageHeight {
CGSize imageSize = CGSizeMake(sampleCount, imageHeight);
UIGraphicsBeginImageContext(imageSize);
CGContextRef context = UIGraphicsGetCurrentContext();
CGContextSetFillColorWithColor(context, [UIColor blackColor].CGColor);
CGContextSetAlpha(context,1.0);
CGRect rect;
rect.size = imageSize;
rect.origin.x = 0;
rect.origin.y = 0;
CGColorRef leftcolor = [[UIColor whiteColor] CGColor];
CGColorRef rightcolor = [[UIColor redColor] CGColor];
CGContextFillRect(context, rect);
CGContextSetLineWidth(context, 1.0);
float halfGraphHeight = (imageHeight / 2) / (float) channelCount ;
float centerLeft = halfGraphHeight;
float centerRight = (halfGraphHeight*3) ;
float sampleAdjustmentFactor = (imageHeight/ (float) channelCount) / (normalizeMax - noiseFloor) / 2;
for (NSInteger intSample = 0 ; intSample < sampleCount ; intSample ++ ) {
Float32 left = *samples++;
float pixels = (left - noiseFloor) * sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerLeft-pixels);
CGContextAddLineToPoint(context, intSample, centerLeft+pixels);
CGContextSetStrokeColorWithColor(context, leftcolor);
CGContextStrokePath(context);
if (channelCount==2) {
Float32 right = *samples++;
float pixels = (right - noiseFloor) * sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerRight - pixels);
CGContextAddLineToPoint(context, intSample, centerRight + pixels);
CGContextSetStrokeColorWithColor(context, rightcolor);
CGContextStrokePath(context);
}
}
// Create new image
UIImage *newImage = UIGraphicsGetImageFromCurrentImageContext();
// Tidy up
UIGraphicsEndImageContext();
return newImage;
}
- (NSData *) renderPNGAudioPictogramLogForAsset:(AVURLAsset *)songAsset {
NSError * error = nil;
AVAssetReader * reader = [[AVAssetReader alloc] initWithAsset:songAsset error:&error];
AVAssetTrack * songTrack = [songAsset.tracks objectAtIndex:0];
NSDictionary* outputSettingsDict = [[NSDictionary alloc] initWithObjectsAndKeys:
[NSNumber numberWithInt:kAudioFormatLinearPCM],AVFormatIDKey,
// [NSNumber numberWithInt:44100.0],AVSampleRateKey, /*Not Supported*/
// [NSNumber numberWithInt: 2],AVNumberOfChannelsKey, /*Not Supported*/
[NSNumber numberWithInt:16],AVLinearPCMBitDepthKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsBigEndianKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsFloatKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsNonInterleaved,
nil];
AVAssetReaderTrackOutput* output = [[AVAssetReaderTrackOutput alloc] initWithTrack:songTrack outputSettings:outputSettingsDict];
[reader addOutput:output];
[output release];
UInt32 sampleRate,channelCount;
NSArray* formatDesc = songTrack.formatDescriptions;
for(unsigned int i = 0; i < [formatDesc count]; ++i) {
CMAudioFormatDescriptionRef item = (CMAudioFormatDescriptionRef)[formatDesc objectAtIndex:i];
const AudioStreamBasicDescription* fmtDesc = CMAudioFormatDescriptionGetStreamBasicDescription (item);
if(fmtDesc ) {
sampleRate = fmtDesc->mSampleRate;
channelCount = fmtDesc->mChannelsPerFrame;
// NSLog(@"channels:%u, bytes/packet: %u, sampleRate %f",fmtDesc->mChannelsPerFrame, fmtDesc->mBytesPerPacket,fmtDesc->mSampleRate);
}
}
UInt32 bytesPerSample = 2 * channelCount;
Float32 normalizeMax = noiseFloor;
NSLog(@"normalizeMax = %f",normalizeMax);
NSMutableData * fullSongData = [[NSMutableData alloc] init];
[reader startReading];
UInt64 totalBytes = 0;
Float64 totalLeft = 0;
Float64 totalRight = 0;
Float32 sampleTally = 0;
NSInteger samplesPerPixel = sampleRate / 50;
while (reader.status == AVAssetReaderStatusReading){
AVAssetReaderTrackOutput * trackOutput = (AVAssetReaderTrackOutput *)[reader.outputs objectAtIndex:0];
CMSampleBufferRef sampleBufferRef = [trackOutput copyNextSampleBuffer];
if (sampleBufferRef){
CMBlockBufferRef blockBufferRef = CMSampleBufferGetDataBuffer(sampleBufferRef);
size_t length = CMBlockBufferGetDataLength(blockBufferRef);
totalBytes += length;
NSAutoreleasePool *wader = [[NSAutoreleasePool alloc] init];
NSMutableData * data = [NSMutableData dataWithLength:length];
CMBlockBufferCopyDataBytes(blockBufferRef, 0, length, data.mutableBytes);
SInt16 * samples = (SInt16 *) data.mutableBytes;
int sampleCount = length / bytesPerSample;
for (int i = 0; i < sampleCount ; i ++) {
Float32 left = (Float32) *samples++;
left = decibel(left);
left = minMaxX(left,noiseFloor,0);
totalLeft += left;
Float32 right;
if (channelCount==2) {
right = (Float32) *samples++;
right = decibel(right);
right = minMaxX(right,noiseFloor,0);
totalRight += right;
}
sampleTally++;
if (sampleTally > samplesPerPixel) {
left = totalLeft / sampleTally;
if (left > normalizeMax) {
normalizeMax = left;
}
// NSLog(@"left average = %f, normalizeMax = %f",left,normalizeMax);
[fullSongData appendBytes:&left length:sizeof(left)];
if (channelCount==2) {
right = totalRight / sampleTally;
if (right > normalizeMax) {
normalizeMax = right;
}
[fullSongData appendBytes:&right length:sizeof(right)];
}
totalLeft = 0;
totalRight = 0;
sampleTally = 0;
}
}
[wader drain];
CMSampleBufferInvalidate(sampleBufferRef);
CFRelease(sampleBufferRef);
}
}
NSData * finalData = nil;
if (reader.status == AVAssetReaderStatusFailed || reader.status == AVAssetReaderStatusUnknown){
// Something went wrong. Handle it.
}
if (reader.status == AVAssetReaderStatusCompleted){
// You're done. It worked.
NSLog(@"rendering output graphics using normalizeMax %f",normalizeMax);
UIImage *test = [self audioImageLogGraph:(Float32 *) fullSongData.bytes
normalizeMax:normalizeMax
sampleCount:fullSongData.length / (sizeof(Float32) * 2)
channelCount:2
imageHeight:100];
finalData = imageToData(test);
}
[fullSongData release];
[reader release];
return finalData;
}
результаты сравнения
Линейный график для начала "Warm It Up" от Acme Swing Company
Логарифмический график для начала "Warm It Up" от Acme Swing Company
person
unsynchronized
schedule
12.09.2011
