static INLINE int libyuv_scale(aom_image_t *src, aom_image_t *dst,
FilterModeEnum mode) {
#if CONFIG_AOM_HIGHBITDEPTH
if (src->fmt == AOM_IMG_FMT_I42016) {
assert(dst->fmt == AOM_IMG_FMT_I42016);
return I420Scale_16(
(uint16_t *)src->planes[AOM_PLANE_Y], src->stride[AOM_PLANE_Y] / 2,
(uint16_t *)src->planes[AOM_PLANE_U], src->stride[AOM_PLANE_U] / 2,
(uint16_t *)src->planes[AOM_PLANE_V], src->stride[AOM_PLANE_V] / 2,
src->d_w, src->d_h, (uint16_t *)dst->planes[AOM_PLANE_Y],
dst->stride[AOM_PLANE_Y] / 2, (uint16_t *)dst->planes[AOM_PLANE_U],
dst->stride[AOM_PLANE_U] / 2, (uint16_t *)dst->planes[AOM_PLANE_V],
dst->stride[AOM_PLANE_V] / 2, dst->d_w, dst->d_h, mode);
}
#endif
assert(src->fmt == AOM_IMG_FMT_I420);
assert(dst->fmt == AOM_IMG_FMT_I420);
return I420Scale(src->planes[AOM_PLANE_Y], src->stride[AOM_PLANE_Y],
src->planes[AOM_PLANE_U], src->stride[AOM_PLANE_U],
src->planes[AOM_PLANE_V], src->stride[AOM_PLANE_V], src->d_w,
src->d_h, dst->planes[AOM_PLANE_Y], dst->stride[AOM_PLANE_Y],
dst->planes[AOM_PLANE_U], dst->stride[AOM_PLANE_U],
dst->planes[AOM_PLANE_V], dst->stride[AOM_PLANE_V], dst->d_w,
dst->d_h, mode);
}
static INLINE int vpx_image_scale(vpx_image_t *src, vpx_image_t *dst,
FilterModeEnum mode) {
#if CONFIG_VP9 && CONFIG_VP9_HIGHBITDEPTH
if (src->fmt == VPX_IMG_FMT_I42016) {
assert(dst->fmt == VPX_IMG_FMT_I42016);
return I420Scale_16((uint16_t*)src->planes[VPX_PLANE_Y],
src->stride[VPX_PLANE_Y]/2,
(uint16_t*)src->planes[VPX_PLANE_U],
src->stride[VPX_PLANE_U]/2,
(uint16_t*)src->planes[VPX_PLANE_V],
src->stride[VPX_PLANE_V]/2,
src->d_w, src->d_h,
(uint16_t*)dst->planes[VPX_PLANE_Y],
dst->stride[VPX_PLANE_Y]/2,
(uint16_t*)dst->planes[VPX_PLANE_U],
dst->stride[VPX_PLANE_U]/2,
(uint16_t*)dst->planes[VPX_PLANE_V],
dst->stride[VPX_PLANE_V]/2,
dst->d_w, dst->d_h,
mode);
}
#endif
assert(src->fmt == VPX_IMG_FMT_I420);
assert(dst->fmt == VPX_IMG_FMT_I420);
return I420Scale(src->planes[VPX_PLANE_Y], src->stride[VPX_PLANE_Y],
src->planes[VPX_PLANE_U], src->stride[VPX_PLANE_U],
src->planes[VPX_PLANE_V], src->stride[VPX_PLANE_V],
src->d_w, src->d_h,
dst->planes[VPX_PLANE_Y], dst->stride[VPX_PLANE_Y],
dst->planes[VPX_PLANE_U], dst->stride[VPX_PLANE_U],
dst->planes[VPX_PLANE_V], dst->stride[VPX_PLANE_V],
dst->d_w, dst->d_h,
mode);
}
static int vpx_image_scale(vpx_image_t *src, vpx_image_t *dst,
FilterMode mode) {
assert(src->fmt == VPX_IMG_FMT_I420);
assert(dst->fmt == VPX_IMG_FMT_I420);
return I420Scale(src->planes[VPX_PLANE_Y], src->stride[VPX_PLANE_Y],
src->planes[VPX_PLANE_U], src->stride[VPX_PLANE_U],
src->planes[VPX_PLANE_V], src->stride[VPX_PLANE_V],
src->d_w, src->d_h,
dst->planes[VPX_PLANE_Y], dst->stride[VPX_PLANE_Y],
dst->planes[VPX_PLANE_U], dst->stride[VPX_PLANE_U],
dst->planes[VPX_PLANE_V], dst->stride[VPX_PLANE_V],
dst->d_w, dst->d_h,
mode);
}
int main(int argc, char **argv)
{
FILE *infile, *outfile[NUM_ENCODERS];
vpx_codec_ctx_t codec[NUM_ENCODERS];
vpx_codec_enc_cfg_t cfg[NUM_ENCODERS];
vpx_codec_pts_t frame_cnt = 0;
vpx_image_t raw[NUM_ENCODERS];
vpx_codec_err_t res[NUM_ENCODERS];
int i;
long width;
long height;
int frame_avail;
int got_data;
int flags = 0;
/*Currently, only realtime mode is supported in multi-resolution encoding.*/
int arg_deadline = VPX_DL_REALTIME;
/* Set show_psnr to 1/0 to show/not show PSNR. Choose show_psnr=0 if you
don't need to know PSNR, which will skip PSNR calculation and save
encoding time. */
int show_psnr = 0;
uint64_t psnr_sse_total[NUM_ENCODERS] = {0};
uint64_t psnr_samples_total[NUM_ENCODERS] = {0};
double psnr_totals[NUM_ENCODERS][4] = {{0,0}};
int psnr_count[NUM_ENCODERS] = {0};
/* Set the required target bitrates for each resolution level. */
unsigned int target_bitrate[NUM_ENCODERS]={1400, 500, 100};
/* Enter the frame rate of the input video */
int framerate = 30;
/* Set down-sampling factor for each resolution level.
dsf[0] controls down sampling from level 0 to level 1;
dsf[1] controls down sampling from level 1 to level 2;
dsf[2] is not used. */
vpx_rational_t dsf[NUM_ENCODERS] = {{2, 1}, {2, 1}, {1, 1}};
if(argc!= (5+NUM_ENCODERS))
die("Usage: %s <width> <height> <infile> <outfile(s)> <output psnr?>\n",
argv[0]);
printf("Using %s\n",vpx_codec_iface_name(interface));
width = strtol(argv[1], NULL, 0);
height = strtol(argv[2], NULL, 0);
if(width < 16 || width%2 || height <16 || height%2)
die("Invalid resolution: %ldx%ld", width, height);
/* Open input video file for encoding */
if(!(infile = fopen(argv[3], "rb")))
die("Failed to open %s for reading", argv[3]);
/* Open output file for each encoder to output bitstreams */
for (i=0; i< NUM_ENCODERS; i++)
{
if(!(outfile[i] = fopen(argv[i+4], "wb")))
die("Failed to open %s for writing", argv[i+4]);
}
show_psnr = strtol(argv[NUM_ENCODERS + 4], NULL, 0);
/* Populate default encoder configuration */
for (i=0; i< NUM_ENCODERS; i++)
{
res[i] = vpx_codec_enc_config_default(interface, &cfg[i], 0);
if(res[i]) {
printf("Failed to get config: %s\n", vpx_codec_err_to_string(res[i]));
return EXIT_FAILURE;
}
}
/*
* Update the default configuration according to needs of the application.
*/
/* Highest-resolution encoder settings */
cfg[0].g_w = width;
cfg[0].g_h = height;
cfg[0].g_threads = 1; /* number of threads used */
cfg[0].rc_dropframe_thresh = 0;
cfg[0].rc_end_usage = VPX_CBR;
cfg[0].rc_resize_allowed = 0;
cfg[0].rc_min_quantizer = 4;
cfg[0].rc_max_quantizer = 56;
cfg[0].rc_undershoot_pct = 98;
cfg[0].rc_overshoot_pct = 100;
cfg[0].rc_buf_initial_sz = 500;
cfg[0].rc_buf_optimal_sz = 600;
cfg[0].rc_buf_sz = 1000;
//cfg[0].rc_dropframe_thresh = 10;
cfg[0].g_error_resilient = 1; /* Enable error resilient mode */
cfg[0].g_lag_in_frames = 0;
/* Disable automatic keyframe placement */
//cfg[0].kf_mode = VPX_KF_DISABLED;
cfg[0].kf_min_dist = cfg[0].kf_max_dist = 1000;
cfg[0].rc_target_bitrate = target_bitrate[0]; /* Set target bitrate */
cfg[0].g_timebase.num = 1; /* Set fps */
cfg[0].g_timebase.den = framerate;
/* Other-resolution encoder settings */
for (i=1; i< NUM_ENCODERS; i++)
{
memcpy(&cfg[i], &cfg[0], sizeof(vpx_codec_enc_cfg_t));
cfg[i].g_threads = 1; /* number of threads used */
cfg[i].rc_target_bitrate = target_bitrate[i];
/* Note: Width & height of other-resolution encoders are calculated
* from the highest-resolution encoder's size and the corresponding
* down_sampling_factor.
*/
{
unsigned int iw = cfg[i-1].g_w*dsf[i-1].den + dsf[i-1].num - 1;
unsigned int ih = cfg[i-1].g_h*dsf[i-1].den + dsf[i-1].num - 1;
cfg[i].g_w = iw/dsf[i-1].num;
cfg[i].g_h = ih/dsf[i-1].num;
}
/* Make width & height to be multiplier of 2. */
// Should support odd size ???
if((cfg[i].g_w)%2)cfg[i].g_w++;
if((cfg[i].g_h)%2)cfg[i].g_h++;
}
/* Allocate image for each encoder */
for (i=0; i< NUM_ENCODERS; i++)
if(!vpx_img_alloc(&raw[i], VPX_IMG_FMT_I420, cfg[i].g_w, cfg[i].g_h, 32))
die("Failed to allocate image", cfg[i].g_w, cfg[i].g_h);
if (raw[0].stride[VPX_PLANE_Y] == raw[0].d_w)
read_frame_p = read_frame;
else
read_frame_p = read_frame_by_row;
for (i=0; i< NUM_ENCODERS; i++)
write_ivf_file_header(outfile[i], &cfg[i], 0);
/* Initialize multi-encoder */
if(vpx_codec_enc_init_multi(&codec[0], interface, &cfg[0], NUM_ENCODERS,
(show_psnr ? VPX_CODEC_USE_PSNR : 0), &dsf[0]))
die_codec(&codec[0], "Failed to initialize encoder");
/* The extra encoding configuration parameters can be set as follows. */
/* Set encoding speed */
for ( i=0; i<NUM_ENCODERS; i++)
{
int speed = -6;
if(vpx_codec_control(&codec[i], VP8E_SET_CPUUSED, speed))
die_codec(&codec[i], "Failed to set cpu_used");
}
/* Set static thresh for highest-resolution encoder. Set it to 1000 for
* better performance. */
{
unsigned int static_thresh = 1000;
if(vpx_codec_control(&codec[0], VP8E_SET_STATIC_THRESHOLD, static_thresh))
die_codec(&codec[0], "Failed to set static threshold");
}
/* Set static thresh = 0 for other encoders for better quality */
for ( i=1; i<NUM_ENCODERS; i++)
{
unsigned int static_thresh = 0;
if(vpx_codec_control(&codec[i], VP8E_SET_STATIC_THRESHOLD, static_thresh))
die_codec(&codec[i], "Failed to set static threshold");
}
frame_avail = 1;
got_data = 0;
while(frame_avail || got_data)
{
vpx_codec_iter_t iter[NUM_ENCODERS]={NULL};
const vpx_codec_cx_pkt_t *pkt[NUM_ENCODERS];
flags = 0;
frame_avail = read_frame_p(infile, &raw[0]);
if(frame_avail)
{
for ( i=1; i<NUM_ENCODERS; i++)
{
/*Scale the image down a number of times by downsampling factor*/
/* FilterMode 1 or 2 give better psnr than FilterMode 0. */
I420Scale(raw[i-1].planes[VPX_PLANE_Y], raw[i-1].stride[VPX_PLANE_Y],
raw[i-1].planes[VPX_PLANE_U], raw[i-1].stride[VPX_PLANE_U],
raw[i-1].planes[VPX_PLANE_V], raw[i-1].stride[VPX_PLANE_V],
raw[i-1].d_w, raw[i-1].d_h,
raw[i].planes[VPX_PLANE_Y], raw[i].stride[VPX_PLANE_Y],
raw[i].planes[VPX_PLANE_U], raw[i].stride[VPX_PLANE_U],
raw[i].planes[VPX_PLANE_V], raw[i].stride[VPX_PLANE_V],
raw[i].d_w, raw[i].d_h, 1);
}
}
/* Encode each frame at multi-levels */
if(vpx_codec_encode(&codec[0], frame_avail? &raw[0] : NULL,
frame_cnt, 1, flags, arg_deadline))
die_codec(&codec[0], "Failed to encode frame");
for (i=NUM_ENCODERS-1; i>=0 ; i--)
{
got_data = 0;
while( (pkt[i] = vpx_codec_get_cx_data(&codec[i], &iter[i])) )
{
got_data = 1;
switch(pkt[i]->kind) {
case VPX_CODEC_CX_FRAME_PKT:
write_ivf_frame_header(outfile[i], pkt[i]);
if(fwrite(pkt[i]->data.frame.buf, 1, pkt[i]->data.frame.sz,
outfile[i]));
break;
case VPX_CODEC_PSNR_PKT:
if (show_psnr)
{
int j;
psnr_sse_total[i] += pkt[i]->data.psnr.sse[0];
psnr_samples_total[i] += pkt[i]->data.psnr.samples[0];
for (j = 0; j < 4; j++)
{
//fprintf(stderr, "%.3lf ", pkt[i]->data.psnr.psnr[j]);
psnr_totals[i][j] += pkt[i]->data.psnr.psnr[j];
}
psnr_count[i]++;
}
break;
default:
break;
}
printf(pkt[i]->kind == VPX_CODEC_CX_FRAME_PKT
&& (pkt[i]->data.frame.flags & VPX_FRAME_IS_KEY)? "K":".");
fflush(stdout);
}
}
frame_cnt++;
}
printf("\n");
fclose(infile);
for (i=0; i< NUM_ENCODERS; i++)
{
printf("Processed %ld frames.\n",(long int)frame_cnt-1);
/* Calculate PSNR and print it out */
if ( (show_psnr) && (psnr_count[i]>0) )
{
int j;
double ovpsnr = vp8_mse2psnr(psnr_samples_total[i], 255.0,
psnr_sse_total[i]);
fprintf(stderr, "\n ENC%d PSNR (Overall/Avg/Y/U/V)", i);
fprintf(stderr, " %.3lf", ovpsnr);
for (j = 0; j < 4; j++)
{
fprintf(stderr, " %.3lf", psnr_totals[i][j]/psnr_count[i]);
}
}
if(vpx_codec_destroy(&codec[i]))
die_codec(&codec[i], "Failed to destroy codec");
/* Try to rewrite the file header with the actual frame count */
if(!fseek(outfile[i], 0, SEEK_SET))
write_ivf_file_header(outfile[i], &cfg[i], frame_cnt-1);
fclose(outfile[i]);
vpx_img_free(&raw[i]);
}
return EXIT_SUCCESS;
}
JNIEXPORT jboolean JNICALL Java_co_splots_recorder_H264Encoder_encode(
JNIEnv* env, jobject thiz, jbyteArray data, jobject cameraInfo,
jlong timeStamp) {
jclass camera_info_class = (*env)->GetObjectClass(env, cameraInfo);
jfieldID field_id = (*env)->GetFieldID(env, camera_info_class,
"orientation", "I");
jint rotation = (*env)->GetIntField(env, cameraInfo, field_id);
field_id = (*env)->GetFieldID(env, camera_info_class, "facing", "I");
jint facing = (*env)->GetIntField(env, cameraInfo, field_id);
int nv21_length = (*env)->GetArrayLength(env, data);
uint8_t *nv21_input = (uint8_t *) (*env)->GetByteArrayElements(env, data,
(jboolean) 0);
int width = crop_width;
int height = crop_height;
int rotate = rotation;
int converted_half_size = (width + 1) / 2;
uint8_t convert_i420[width * height + (width * height + 1) / 2];
uint8_t *convert_i420_y = convert_i420;
uint8_t *convert_i420_u = convert_i420 + (width * height);
uint8_t *convert_i420_v = convert_i420_u
+ (converted_half_size * converted_half_size);
if (facing == 1) {
height = 0 - height;
rotate = (rotate + 180) % 360;
}
if (ConvertToI420(nv21_input, nv21_length, convert_i420_y, width,
convert_i420_v, converted_half_size, convert_i420_u,
converted_half_size, crop_x, crop_y, src_width, src_height, width,
height, rotate, FOURCC_NV21) != 0)
return JNI_FALSE;
int scaled_half_size = (dest_width + 1) / 2;
int scaled_data_length = dest_width * dest_height
+ (dest_width * dest_height + 1) / 2;
uint8_t scaled_i420[scaled_data_length];
uint8_t* scaled_i420_y = scaled_i420;
uint8_t* scaled_i420_u = scaled_i420 + (dest_width * dest_height);
uint8_t* scaled_i420_v = scaled_i420_u
+ (scaled_half_size * scaled_half_size);
if (width != dest_width || height != dest_height) {
if (I420Scale(convert_i420_y, width, convert_i420_u,
converted_half_size, convert_i420_v, converted_half_size, width,
height, scaled_i420_y, dest_width, scaled_i420_u,
scaled_half_size, scaled_i420_v, scaled_half_size, dest_width,
dest_height, kFilterNone) != 0)
return JNI_FALSE;
} else {
scaled_i420_y = convert_i420_y;
scaled_i420_u = convert_i420_u;
scaled_i420_v = convert_i420_v;
}
uint8_t *frame = (uint8_t *) malloc(sizeof(uint8_t) * scaled_data_length);
uint8_t *frame_y = frame;
uint8_t *frame_u = frame_y + (dest_width * dest_height);
uint8_t *frame_v = frame_u + (scaled_half_size * scaled_half_size);
memcpy(frame_y, scaled_i420_y, dest_width * dest_height);
memcpy(frame_u, scaled_i420_v, scaled_half_size * scaled_half_size);
memcpy(frame_v, scaled_i420_u, scaled_half_size * scaled_half_size);
if (thumbnail == NULL) {
thumbnail_size = scaled_data_length;
thumbnail_width = dest_width;
thumbnail_height = dest_height;
thumbnail = (uint8_t *) malloc(sizeof(uint8_t) * thumbnail_size);
uint8_t* thumbnail_y = thumbnail;
uint8_t* thumbnail_vu = thumbnail + (dest_width * dest_height);
I420ToNV12(scaled_i420_y, dest_width, scaled_i420_u, scaled_half_size,
scaled_i420_v, scaled_half_size, thumbnail_y, dest_width,
thumbnail_vu, dest_width, dest_width, dest_height);
}
SSourcePicture pic;
memset(&pic, 0, sizeof(SSourcePicture));
pic.iPicWidth = dest_width;
pic.iPicHeight = dest_width;
pic.iColorFormat = videoFormatI420;
pic.iStride[0] = dest_width;
pic.iStride[1] = pic.iStride[2] = scaled_half_size;
pic.uiTimeStamp = (long long) timeStamp;
pic.pData[0] = frame;
pic.pData[1] = pic.pData[0] + dest_width * dest_height;
pic.pData[2] = pic.pData[1] + (scaled_half_size * scaled_half_size);
float current_frame_rate = ((float) frame_count * 1000)
/ ((float) timeStamp);
frame_rate_sum += current_frame_rate;
LOG("current fps: %f", current_frame_rate);
/*if ((*encoder)->SetOption(encoder, ENCODER_OPTION_FRAME_RATE,
(void*) ¤t_frame_rate) != cmResultSuccess)
LOG("Could not update frame rate.");*/
EVideoFrameType frameType = (*encoder)->EncodeFrame(encoder, &pic, &info);
if (frameType == videoFrameTypeInvalid)
return JNI_FALSE;
LOG("Frame #%d", frame_count);
frame_count++;
if (frameType != videoFrameTypeSkip)
writeInfoToFile(&info);
return JNI_TRUE;
}