-
网址：https://github.com/Netflix/vmaf
-
VMAF，即Video Muitimethod Assessment Fusion（视频多方法评价融合）；由 Netflix 推出的视频质量评价工具，用来解决传统指标不能反映多种场景、多种特征的视频情况。该指标是目前互联网视频最主流的客观视频评价指标，适用于衡量大规模环境中流播视频质量的观感。
-
vmaf是一种视频质量指标，将人类视觉建模与机器学习相结合，由Netflix和南加州大学C.-C Jay Kuo教授之间的研究合作；之后德克萨斯大学奥斯汀分校Alan Bovik教授和南特大学Patrick Le Callet教授之间展开合作，用来提高与人类主观感知有关的vmaf准确性，并扩大其范围涵盖更多用例；2016年6月完成开源。
-
vmaf可以用作优化准则，以获得更好的编码决策；VMAF被用于我们的整个生产流程中，不仅可以测量编码过程的结果，还可以指导编码达到最佳质量。在我们的动态优化器中，有一个关于如何在编码中使用VMAF的重要示例 Dynamic Optimizer，其中，每镜头的编码决策由每个编码器选项的比特率和质量测量确定。在优化过程中，VMAF 分数对于获取准确的质量测量以及选择 凸壳上的最终分辨率/比特率点至关重要。
-
VMAF分数范围从 0 到 100，其中 0 表示最低质量，100表示最高。思考VMAF分数的一种好方法是将其线性映射到人的意见量表，在此条件下可获得训练分数。例如，默认模型 v0.6.1 使用由绝对类别评分（ACR）方法收集的分数进行训练，该分数使用 1080p 显示屏，观看距离为3H。观看者对视频质量的评分为“很差”，“差”，“一般”，“好”和“优秀”，并且粗略地讲，“差”被映射为VMAF级别20，“优秀”为100。
-
视频数据源的内容特征：
○ 动漫、室内、室外、镜头摇移、面部拉近、人物、水面、显著的物体、多个物体；
○ 不同亮度、不同对比度、不同材质、不同活动、颜色变化、色泽浓郁度、锐利度；
○ 块效应、振铃效应、胶片颗粒度、蚊式噪声；
https://blog.csdn.net/yanceyxin/article/details/108075460
原理- 三种指标：视觉信息保真度（VIF：visual quality fidelity）、细节损失指标（DLM：detail loss measure）、时域运动指标/平均相关位置像素差（TI：temporal information）。其中VIF和DLM是空间域的，一帧画面之内的特征。TI 是时间域的，多帧画面之间相关性的特征。这些特性之间融合计算总分的过程使用了训练好的SVM来预测。
- VIF：视觉信息保真度指标来源于论文《image information and visual quality》https://ieeexplore.ieee.org/document/1576816
- DLM：细节损失指标来源于论文《Image Quality Assessment by Separately Evaluating Detail Losses and Additive Impairments》https://ieeexplore.ieee.org/document/5765502
- TI ：时域运动指标/平均相关位置像素差是一种衡量相邻帧之间时域差分的算法；这个仅仅计算像素亮度分量的均值作差即可得到该值。
[vmaf.c]
int main(int argc, char *arg[])
{
int err = 0;
//文件流相关操作
const int istty = isatty(fileno(stderr));
//解析命令行，传入CLISettings结构体中
CLISettings c;
cli_parse(argc, argv, &c);
//输出VMAF版本号
if (istty && !c.quiet) {
fprintf(stderr, "VMAF version %sn", vmaf_version());
}
//从路径读入视频数据
FILE *file_ref = fopen(c.path_ref, "rb");
if (!file_ref) {
fprintf(stderr, "could not open file: %sn", c.path_ref);
return -1;
}
FILE *file_dist = fopen(c.path_dist, "rb");
if (!file_dist) {
fprintf(stderr, "could not open file: %sn", c.path_dist);
return -1;
}
//从FILE中传入video_input结构体里
video_input vid_ref;
if (c.use_yuv) {
err = raw_input_open(&vid_ref, file_ref,
c.width, c.height, c.pix_fmt, c.bitdepth);
} else {
err = video_input_open(&vid_ref, file_ref);
}
if (err) {
fprintf(stderr, "problem with reference file: %sn", c.path_ref);
return -1;
}
video_input vid_dist;
if (c.use_yuv) {
err = raw_input_open(&vid_dist, file_dist,
c.width, c.height, c.pix_fmt, c.bitdepth);
} else {
err = video_input_open(&vid_dist, file_dist);
}
if (err) {
fprintf(stderr, "problem with distorted file: %sn", c.path_dist);
return -1;
}
//验证ref和dist视频的相容性
err = validate_videos(&vid_ref, &vid_dist);
if (err) {
fprintf(stderr, "videos are incompatible, %d %s.n",
err, err == 1 ? "problem" : "problems");
return -1;
}
//configure信息
VmafConfiguration cfg = {
.log_level = VMAF_LOG_LEVEL_INFO,
.n_threads = c.thread_cnt,
.n_subsample = c.subsample,
.cpumask = c.cpumask,
};
//1. 初始化，vmaf是上下文，cfg是选择结构体用来初始化上下文
VmafContext *vmaf;
err = vmaf_init(&vmaf, cfg);
if (err) {
fprintf(stderr, "problem initializing VMAF contextn");
return -1;
}
//内存申请
VmafModel **model;
const size_t model_sz = sizeof(*model) * c.model_cnt;
model = malloc(model_sz);
memset(model, 0, model_sz);
VmafModelCollection **model_collection;
const size_t model_collection_sz =
sizeof(*model_collection) * c.model_cnt;
model_collection = malloc(model_sz);
memset(model_collection, 0, model_collection_sz);
const char *model_collection_label[c.model_cnt];
unsigned model_collection_cnt = 0;
//对model次数进行循环操作
for (unsigned i = 0; i < c.model_cnt; i++) {
//根据判断version是否使用来调用不同的方法load模型
if (c.model_config[i].version) {
//加载默认内置模型之一
err = vmaf_model_load(&model[i], &c.model_config[i].cfg,
c.model_config[i].version);
} else {
//从系统文件读取模型文件
err = vmaf_model_load_from_path(&model[i], &c.model_config[i].cfg,
c.model_config[i].path);
}
//加载模型错误的情况下
if (err) {
// check for model_collection before failing
// this is implicit because the `--model` option could take either
// a model or model_collection
if (c.model_config[i].version) {
err = vmaf_model_collection_load(&model[i],
&model_collection[model_collection_cnt],
&c.model_config[i].cfg,
c.model_config[i].version);
} else {
err = vmaf_model_collection_load_from_path(&model[i],
&model_collection[model_collection_cnt],
&c.model_config[i].cfg,
c.model_config[i].path);
}
if (err) {
fprintf(stderr, "problem loading model: %sn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path);
return -1;
}
model_collection_label[model_collection_cnt] =
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path;
for (unsigned j = 0; j < c.model_config[i].overload_cnt; j++) {
err = vmaf_model_collection_feature_overload(
model[i],
&model_collection[model_collection_cnt],
c.model_config[i].feature_overload[j].name,
c.model_config[i].feature_overload[j].opts_dict);
if (err) {
fprintf(stderr,
"problem overloading feature extractors from "
"model collection: %sn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path);
return -1;
}
}
err = vmaf_use_features_from_model_collection(vmaf,
model_collection[model_collection_cnt]);
if (err) {
fprintf(stderr,
"problem loading feature extractors from "
"model collection: %sn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path);
return -1;
}
model_collection_cnt++;
continue;
}
//
for (unsigned j = 0; j < c.model_config[i].overload_cnt; j++) {
err = vmaf_model_feature_overload(model[i],
c.model_config[i].feature_overload[j].name,
c.model_config[i].feature_overload[j].opts_dict);
if (err) {
fprintf(stderr,
"problem overloading feature extractors from "
"model: %sn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path);
return -1;
}
}
//使用' vmaf_use_features_from_model() '注册模型所需的所有特征提取器
err = vmaf_use_features_from_model(vmaf, model[i]);
if (err) {
fprintf(stderr,
"problem loading feature extractors from model: %sn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path);
return -1;
}
}
//如果有辅助指标，使用‘vmaf_use_feature()’直接注册
for (unsigned i = 0; i < c.feature_cnt; i++) {
err = vmaf_use_feature(vmaf, c.feature_cfg[i].name,
c.feature_cfg[i].opts_dict);
if (err) {
fprintf(stderr, "problem loading feature extractor: %sn",
c.feature_cfg[i].name);
return -1;
}
}
//循环读取所有图像
float fps = 0.;
const time_t t0 = clock();
unsigned picture_index;
for (picture_index = 0 ;; picture_index++) {
if (c.frame_cnt && picture_index >= c.frame_cnt)
break;
//核心就是封装了vmaf_picture_alloc，要分配“VmafPicture”，请使用“vmaf_picture_alloc”。分配之后，可以用像素数据填充缓冲区。
VmafPicture pic_ref, pic_dist;
int ret1 = fetch_picture(&vid_ref, &pic_ref);
int ret2 = fetch_picture(&vid_dist, &pic_dist);
if (ret1 && ret2) {
break;
} else if (ret1 < 0 || ret2 < 0) {
fprintf(stderr, "nproblem while reading picturesn");
break;
} else if (ret1) {
fprintf(stderr, "n"%s" ended before "%s".n",
c.path_ref, c.path_dist);
break;
} else if (ret2) {
fprintf(stderr, "n"%s" ended before "%s".n",
c.path_dist, c.path_ref);
break;
}
if (istty && !c.quiet) {
if (picture_index > 0 && !(picture_index % 10)) {
fps = (picture_index + 1) /
(((float)clock() - t0) / CLOCKS_PER_SEC);
}
fprintf(stderr, "r%d frame%s %s %.2f FPS 33[K",
picture_index + 1, picture_index ? "s" : " ",
spinner[picture_index % spinner_length], fps);
fflush(stderr);
}
//使用' vmaf_read_pictures() '循环读取所有输入的图片。当您完成图片读取时，一些特征提取器可能仍然需要刷新内部缓冲区
err = vmaf_read_pictures(vmaf, &pic_ref, &pic_dist, picture_index);
if (err) {
fprintf(stderr, "nproblem reading picturesn");
break;
}
}
if (istty && !c.quiet)
fprintf(stderr, "n");
//一旦缓冲区被刷新，所有对' vmaf_read_pictures() '的进一步调用都无效。
err |= vmaf_read_pictures(vmaf, NULL, NULL, 0);
if (err) {
fprintf(stderr, "problem flushing contextn");
return err;
}
//在图片被读取后，您可以检索一个vmaf分数。使用' vmaf_score_at_index '来获取单个索引的分数，并使用' vmaf_score_pooled() '来获得跨多个帧的分数
if (!c.no_prediction) {
for (unsigned i = 0; i < c.model_cnt; i++) {
double vmaf_score;
err = vmaf_score_pooled(vmaf, model[i], VMAF_POOL_METHOD_MEAN,
&vmaf_score, 0, picture_index - 1);
if (err) {
fprintf(stderr, "problem generating pooled VMAF scoren");
return -1;
}
if (istty && (!c.quiet || !c.output_path)) {
fprintf(stderr, "%s: %fn",
c.model_config[i].version ?
c.model_config[i].version : c.model_config[i].path,
vmaf_score);
}
}
//使用模型集合预测特定指数的VMAF得分
for (unsigned i = 0; i < model_collection_cnt; i++) {
VmafModelCollectionScore score = { 0 };
err = vmaf_score_pooled_model_collection(vmaf, model_collection[i],
VMAF_POOL_METHOD_MEAN, &score,
0, picture_index - 1);
if (err) {
fprintf(stderr, "problem generating pooled VMAF scoren");
return -1;
}
switch (score.type) {
case VMAF_MODEL_COLLECTION_SCORE_BOOTSTRAP:
if (istty && (!c.quiet || !c.output_path)) {
fprintf(stderr, "%s: %f, ci.p95: [%f, %f], stddev: %fn",
model_collection_label[i],
score.bootstrap.bagging_score, score.bootstrap.ci.p95.lo,
score.bootstrap.ci.p95.hi,
score.bootstrap.stddev);
}
break;
default:
break;
}
}
}
//输出结果到指定路径
if (c.output_path)
vmaf_write_output(vmaf, c.output_path, c.output_fmt);
//销毁、释放实例与内存
for (unsigned i = 0; i < c.model_cnt; i++)
vmaf_model_destroy(model[i]);
free(model);
for (unsigned i = 0; i < model_collection_cnt; i++)
vmaf_model_collection_destroy(model_collection[i]);
free(model_collection);
video_input_close(&vid_ref);
video_input_close(&vid_dist);
//清除vmaf
vmaf_close(vmaf);
cli_free(&c);
return err;
}
使用案例
- FFmpeg
- Elecard StreamEye
- MSU Video Quality Measurement Tool
