Estaba buscando algo similar y decidí "rodar el mío". Me doy cuenta de que esta es una publicación antigua, pero en caso de que alguien más esté buscando esto, aquí está mi solución. es relativamente rápido y sucio y normaliza la imagen a "escala completa". las imágenes que crea son "amplias", es decir, debe colocarlas en un UIScrollView o administrar la visualización de otro modo.
esto se basa en algunas respuestas dadas a esta pregunta
Salida de muestra
EDITAR: He agregado una versión logarítmica de los métodos de promediado y renderizado, vea el final de este mensaje para ver la versión alternativa y las salidas de comparación. Yo personalmente prefiero la versión lineal original, pero he decidido publicarla, en caso de que alguien pueda mejorar el algoritmo utilizado.
Necesitará estas importaciones:
#import <MediaPlayer/MediaPlayer.h>
#import <AVFoundation/AVFoundation.h>
Primero, un método de representación genérico que toma un puntero a datos de muestra promediados
y devuelve un UIImage. Tenga en cuenta que estas muestras no son muestras de audio reproducibles.
-(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);
}
}
UIImage *newImage = UIGraphicsGetImageFromCurrentImageContext();
UIGraphicsEndImageContext();
return newImage;
}
A continuación, un método que toma un AVURLAsset y devuelve datos de imagen 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: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;
}
}
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){
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;
}
Opción avanzada:
finalmente, si desea poder reproducir el audio usando AVAudioPlayer, deberá almacenarlo en la caché de la carpeta de caché del paquete de sus aplicaciones. Ya que estaba haciendo eso, decidí almacenar en caché los datos de la imagen también, y envolví todo en una categoría UIImage. debe incluir esta oferta de código abierto para extraer el audio y algún código de aquí para manejar algunas funciones de subprocesamiento en segundo plano.
primero, algunas definiciones y algunos métodos de clase genéricos para manejar nombres de ruta, etc.
#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];
}
Ahora el método init que hace "el negocio"
- (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) {
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;
}
}
Un ejemplo de cómo invocar esto:
-(void) importMediaItem {
MPMediaItem* item = [self mediaItem];
[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];
}
}
Versión logarítmica de los métodos de promediado y renderizado
#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);
}
}
UIImage *newImage = UIGraphicsGetImageFromCurrentImageContext();
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: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;
}
}
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;
}
[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){
}
if (reader.status == AVAssetReaderStatusCompleted){
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;
}
salidas de comparación
Gráfico lineal para el inicio de "Warm It Up" de Acme Swing Company
Gráfico logarítmico para el inicio de "Warm It Up" de Acme Swing Company