基于深度学习算法实现视频人脸自动打码

前言

1.在当下的环境上，短视频已是生活的常态，但这是很容易就侵犯别人肖像权，好多视频都会在后期给不相关的人打上码，这里是基于yolov5的人脸检测实现人脸自动打码功能。
2.开发环境是win10,显卡RTX3080，cuda10.2，cudnn7.1，OpenCV4.5,NCNN，IDE 是Vs2019。

一、人脸检测

1.首先最主要的一步是肯定是先检测到当前图像是否存在人脸，这个属于人脸检测的范围，目前有很多开源的人脸检测算法和模型，OpenCV本身也带有人脸检测的算法，但了帧率跟得上，这里使用更轻快些的yolov5。
2.实现代码

#ifndef YOLOFACE_H
#define YOLOFACE_H#include <opencv2/core/core.hpp>
#include <opencv2/opencv.hpp>#include <ncnn/net.h>struct Object
{cv::Rect rect;int label;float prob;std::vector<cv::Point2f> pts;float live;
};class YoloFace
{public:YoloFace();int loadModel(std::string model, bool use_gpu = true);int detection(const cv::Mat& rgb, std::vector<Object>& objects, float prob_threshold = 0.25f, float nms_threshold = 0.45f);int drawFace(cv::Mat& rgb,cv::Mat &cv_dst, std::vector<Object>& objects);private:ncnn::Net face_net;int target_size = 640;const float norm_vals[3] = { 1 / 255.f, 1 / 255.f, 1 / 255.f };int image_w;int image_h;int in_w;int in_h;
};#endif // NANODET_H

#include "yoloface.h"#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>#define clip(x, y) (x < 0 ? 0 : (x > y ? y : x))static inline float intersection_area(const Object& a, const Object& b)
{cv::Rect_<float> inter = a.rect & b.rect;return inter.area();
}static void qsort_descent_inplace(std::vector<Object>& faceobjects, int left, int right)
{int i = left;int j = right;float p = faceobjects[(left + right) / 2].prob;while (i <= j){while (faceobjects[i].prob > p)i++;while (faceobjects[j].prob < p)j--;if (i <= j){// swapstd::swap(faceobjects[i], faceobjects[j]);i++;j--;}}#pragma omp parallel sections{#pragma omp section{if (left < j) qsort_descent_inplace(faceobjects, left, j);}#pragma omp section{if (i < right) qsort_descent_inplace(faceobjects, i, right);}}
}static void qsort_descent_inplace(std::vector<Object>& faceobjects)
{if (faceobjects.empty())return;qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
}static void nms_sorted_bboxes(const std::vector<Object>& faceobjects, std::vector<int>& picked, float nms_threshold)
{picked.clear();const int n = faceobjects.size();std::vector<float> areas(n);for (int i = 0; i < n; i++){areas[i] = faceobjects[i].rect.area();}for (int i = 0; i < n; i++){const Object& a = faceobjects[i];int keep = 1;for (int j = 0; j < (int)picked.size(); j++){const Object& b = faceobjects[picked[j]];// intersection over unionfloat inter_area = intersection_area(a, b);float union_area = areas[i] + areas[picked[j]] - inter_area;// float IoU = inter_area / union_areaif (inter_area / union_area > nms_threshold)keep = 0;}if (keep)picked.push_back(i);}
}static inline float sigmoid(float x)
{return static_cast<float>(1.f / (1.f + exp(-x)));
}static void generate_proposals(const ncnn::Mat& anchors, int stride, const ncnn::Mat& in_pad, const ncnn::Mat& feat_blob, float prob_threshold, std::vector<Object>& objects)
{const int num_grid = feat_blob.h;int num_grid_x;int num_grid_y;if (in_pad.w > in_pad.h){num_grid_x = in_pad.w / stride;num_grid_y = num_grid / num_grid_x;}else{num_grid_y = in_pad.h / stride;num_grid_x = num_grid / num_grid_y;}const int num_class = feat_blob.w - 5-10;const int num_anchors = anchors.w / 2;for (int q = 0; q < num_anchors; q++){const float anchor_w = anchors[q * 2];const float anchor_h = anchors[q * 2 + 1];const ncnn::Mat feat = feat_blob.channel(q);for (int i = 0; i < num_grid_y; i++){for (int j = 0; j < num_grid_x; j++){const float* featptr = feat.row(i * num_grid_x + j);// find class index with max class scoreint class_index = 0;float class_score = -FLT_MAX;for (int k = 0; k < num_class; k++){float score = featptr[5 +10+ k];if (score > class_score){class_index = k;class_score = score;}}float box_score = featptr[4];float confidence = sigmoid(box_score); //* sigmoid(class_score);if (confidence >= prob_threshold){// yolov5/models/yolo.py Detect forward// y = x[i].sigmoid()// y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i].to(x[i].device)) * self.stride[i]  # xy// y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # whfloat dx = sigmoid(featptr[0]);float dy = sigmoid(featptr[1]);float dw = sigmoid(featptr[2]);float dh = sigmoid(featptr[3]);float pb_cx = (dx * 2.f - 0.5f + j) * stride;float pb_cy = (dy * 2.f - 0.5f + i) * stride;float pb_w = pow(dw * 2.f, 2) * anchor_w;float pb_h = pow(dh * 2.f, 2) * anchor_h;float x0 = pb_cx - pb_w * 0.5f;float y0 = pb_cy - pb_h * 0.5f;float x1 = pb_cx + pb_w * 0.5f;float y1 = pb_cy + pb_h * 0.5f;Object obj;obj.rect.x = x0;obj.rect.y = y0;obj.rect.width = x1 - x0;obj.rect.height = y1 - y0;obj.label = class_index;obj.prob = confidence;for (int l = 0; l < 5; l++){float x = featptr[2 * l + 5] * anchor_w + j * stride;float y = featptr[2 * l + 1 + 5] * anchor_h + i * stride;obj.pts.push_back(cv::Point2f(x, y));}objects.push_back(obj);}}}}
}YoloFace::YoloFace()
{}int YoloFace::loadModel(std::string model, bool use_gpu)
{bool has_gpu = false;face_net.clear();face_net.opt = ncnn::Option();#if NCNN_VULKANncnn::create_gpu_instance();has_gpu = ncnn::get_gpu_count() > 0;
#endifbool to_use_gpu = has_gpu && use_gpu;face_net.opt.use_vulkan_compute = to_use_gpu;face_net.load_param((model+".param").c_str());face_net.load_model((model + ".bin").c_str());return 0;
}int YoloFace::detection(const cv::Mat& rgb, std::vector<Object>& objects, float prob_threshold, float nms_threshold)
{int img_w = rgb.cols;int img_h = rgb.rows;// letterbox pad to multiple of 32int w = img_w;int h = img_h;float scale = 1.f;if (w > h){scale = (float)target_size / w;w = target_size;h = h * scale;}else{scale = (float)target_size / h;h = target_size;w = w * scale;}ncnn::Mat in = ncnn::Mat::from_pixels_resize(rgb.data, ncnn::Mat::PIXEL_RGB, img_w, img_h, w, h);int wpad = (w + 31) / 32 * 32 - w;int hpad = (h + 31) / 32 * 32 - h;ncnn::Mat in_pad;ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 114.f);in_pad.substract_mean_normalize(0, norm_vals);ncnn::Extractor ex = face_net.create_extractor();ex.input("data", in_pad);std::vector<Object> proposals;// anchor setting from yolov5/models/yolov5s.yaml// stride 8{ncnn::Mat out;ex.extract("981", out);ncnn::Mat anchors(6);anchors[0] = 4.f;anchors[1] = 5.f;anchors[2] = 8.f;anchors[3] = 10.f;anchors[4] = 13.f;anchors[5] = 16.f;std::vector<Object> objects8;generate_proposals(anchors, 8, in_pad, out, prob_threshold, objects8);proposals.insert(proposals.end(), objects8.begin(), objects8.end());}// stride 16{ncnn::Mat out;ex.extract("983", out);ncnn::Mat anchors(6);anchors[0] = 23.f;anchors[1] = 29.f;anchors[2] = 43.f;anchors[3] = 55.f;anchors[4] = 73.f;anchors[5] = 105.f;std::vector<Object> objects16;generate_proposals(anchors, 16, in_pad, out, prob_threshold, objects16);proposals.insert(proposals.end(), objects16.begin(), objects16.end());}// stride 32{ncnn::Mat out;ex.extract("985", out);ncnn::Mat anchors(6);anchors[0] = 146.f;anchors[1] = 217.f;anchors[2] = 231.f;anchors[3] = 300.f;anchors[4] = 335.f;anchors[5] = 433.f;std::vector<Object> objects32;generate_proposals(anchors, 32, in_pad, out, prob_threshold, objects32);proposals.insert(proposals.end(), objects32.begin(), objects32.end());}// sort all proposals by score from highest to lowestqsort_descent_inplace(proposals);// apply nms with nms_thresholdstd::vector<int> picked;nms_sorted_bboxes(proposals, picked, nms_threshold);int count = picked.size();objects.resize(count);for (int i = 0; i < count; i++){objects[i] = proposals[picked[i]];// adjust offset to original unpaddedfloat x0 = (objects[i].rect.x - (wpad / 2)) / scale;float y0 = (objects[i].rect.y - (hpad / 2)) / scale;float x1 = (objects[i].rect.x + objects[i].rect.width - (wpad / 2)) / scale;float y1 = (objects[i].rect.y + objects[i].rect.height - (hpad / 2)) / scale;for (int j = 0; j < objects[i].pts.size(); j++){float ptx = (objects[i].pts[j].x - (wpad / 2)) / scale;float pty = (objects[i].pts[j].y - (hpad / 2)) / scale;objects[i].pts[j] = cv::Point2f(ptx, pty);}// clipx0 = std::max(std::min(x0, (float)(img_w - 1)), 0.f);y0 = std::max(std::min(y0, (float)(img_h - 1)), 0.f);x1 = std::max(std::min(x1, (float)(img_w - 1)), 0.f);y1 = std::max(std::min(y1, (float)(img_h - 1)), 0.f);objects[i].rect.x = x0;objects[i].rect.y = y0;objects[i].rect.width = x1 - x0;objects[i].rect.height = y1 - y0;}return 0;
}int YoloFace::drawFace(cv::Mat& rgb,cv::Mat &cv_dst, std::vector<Object>& objects)
{cv_dst = rgb.clone();static const unsigned char colors[19][3] = {{ 54,  67, 244},{ 99,  30, 233},{176,  39, 156},{183,  58, 103},{181,  81,  63},{243, 150,  33},{244, 169,   3},{212, 188,   0},{136, 150,   0},{ 80, 175,  76},{ 74, 195, 139},{ 57, 220, 205},{ 59, 235, 255},{  7, 193, 255},{  0, 152, 255},{ 34,  87, 255},{ 72,  85, 121},{158, 158, 158},{139, 125,  96}};int color_index = 0;for (size_t i = 0; i < objects.size(); i++){Object& obj = objects[i];const unsigned char* color = colors[color_index % 19];color_index++;cv::Scalar cc(color[0], color[1], color[2]);cv::rectangle(cv_dst,obj.rect, cc, 2);char text[256];sprintf(text, "Face = %.1f%%", obj.prob * 100);int baseLine = 0;cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);int x = obj.rect.x;int y = obj.rect.y - label_size.height - baseLine;if (y < 0)y = 0;if (x + label_size.width > rgb.cols)x = rgb.cols - label_size.width;cv::rectangle(cv_dst, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)), cc, -1);cv::Scalar textcc = (color[0] + color[1] + color[2] >= 381) ? cv::Scalar(0, 0, 0) : cv::Scalar(255, 255, 255);cv::putText(cv_dst, text, cv::Point(x, y + label_size.height), cv::FONT_HERSHEY_SIMPLEX, 0.5, textcc, 1);for (int j = 0; j < obj.pts.size(); j++){cv::circle(cv_dst, obj.pts[j], 2, cv::Scalar(0, 255, 0), -1);}}return 0;
}

2.人脸检测效果

二、人脸打码

代码：

#include <opencv2/opencv.hpp>
#include "yoloface.h"
#include <opencv2/video/video.hpp>cv::Rect targetResize(const cv::Mat& cv_src, cv::Mat& cv_dst, int target_w, int target__h);bool generate_mosaic(cv::Mat& src, std::vector<Object>& objects)
{if (objects.empty())return false;int step = 10;//步长for (int t = 0; t < objects.size(); t++){int x = objects[t].rect.tl().x;int y = objects[t].rect.tl().y;int width = objects[t].rect.width;int height = objects[t].rect.height;for (int i = y; i < (y + height); i += step){for (int j = x; j < (x + width); j += step){for (int k = i; k < (step + i); k++){for (int m = j; m < (step + j); m++){for (int c = 0; c < 3; c++){src.at<cv::Vec3b>(k, m)[c] = src.at<cv::Vec3b>(i, j)[c];}}}}}}return true;
}int main(void)
{YoloFace yolo_face;//加载人脸检测模型yolo_face.loadModel("models/face/face_lite");cv::VideoCapture cap;//打开摄像头或者是输入视频//cap.open(0);cap.open("222.mp4");if (!cap.isOpened()){return 0;}cv::Mat cv_src;while (1){cap >> cv_src;if (cv_src.empty()){break;}std::vector<Object> objects;//图像边界扩展，这步是为了提高精度cv::Mat cv_target;// cv::Rect rect = targetResize(cv_src, cv_target, target_w, target_h);//人脸检测yolo_face.detection(cv_src, objects);cv::Mat cv_dst;generate_mosaic(cv_src, objects);//yolo_face.drawFace(cv_src, cv_dst, objects);cv::namedWindow("face", 0);cv::imshow("face", cv_dst);cv::waitKey(20);}cap.release();return 0;
}
cv::Rect targetResize(const cv::Mat& cv_src, cv::Mat& cv_dst, int target_w, int target_h)
{float s;if (cv_src.cols > cv_src.rows){s = float(target_w) / cv_src.cols;}else{s = float(target_h) / cv_src.rows;}float w = cv_src.cols * s;float h = cv_src.rows * s;int w_p = (target_w - w) / 2;int h_p = (target_h - h) / 2;cv::Mat cv_size;cv::resize(cv_src, cv_size, cv::Size(w, h));cv::copyMakeBorder(cv_size, cv_dst, h_p, h_p, w_p, w_p, cv::BORDER_CONSTANT, 114.f);return cv::Rect(w_p, h_p, cv_size.cols, cv_size.rows);
}

打码效果：

三、源码

1.源码地址：https://mp.csdn.net/mp_download/manage/download/UpDetailed
2.源码配置方法
1.文件目录

2.配置include和lib路径

3.添加lib名，就是源码目录里面所有点lib后缀的名称。

4.IDE的配置

基于深度学习算法实现视频人脸自动打码相关推荐

清华大学矣晓沅：“九歌”——基于深度学习的中国古典诗歌自动生成系统
授权自AI科技大本营(ID:rgznai100) 本文共2714字,建议阅读6分钟. 本文为你介绍清华自然语言处理与社会人文计算实验室的自动作诗系统--"九歌"及其相关的技术方法和 ...
基于深度学习算法的语音识别（华为云）
基于深度学习算法的语音识别训练完模型后可反复使用,训练时可以选购云环境,节省时间,本地除非你的服务器性能够强劲,本次教程基本上也是实验级别的,主要是看看代码,本次实验我的小米配置不行,就直接把代码写 ...
基于深度学习的篮球战术数据自动采集技术研究——项目展示
1 项目背景篮球运动除了需要统计如2分投中.2分投篮.3分投中.3分投篮.扣篮.助攻.盖帽.抢断.失误.犯规和得分等技术信息,还需要统计战术信息.现在统计工作大多数是通过手工完成的,这样的统计方式存 ...
基于深度学习算法和传统立体匹配算法的双目立体视觉
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达 01 立体视觉是什么? 在开始之前,我相信很多站友都会有这个疑问, ...
Python基于深度学习算法实现图书推荐系统项目实战
说明:这是一个机器学习实战项目(附带数据+代码+文档+视频讲解),如需数据+代码+文档+视频讲解可以直接到文章最后获取. 1.项目背景在线推荐系统是许多电子商务网站的事情.推荐系统广泛地向最适合其口 ...
山东大学项目实训小组一——基于深度学习的AI视频剪辑器“易剪”
技术要点:图像处理计算机视觉深度学习多媒体前端一.项目研究背景: 随着短视频热潮的兴起,越来越多的人投入精力到了视频剪辑视频制作之中.然而利用现有的视频剪辑工具,剪辑一段视频是非常麻烦的,尤其 ...
014基于深度学习的脑电癫痫自动检测系统-2018(300引用)
An automated system for epilepsy detection using EEG brain signals based on deep learning approach ...
腾讯医疗AI实验室：基于深度学习的放疗靶区自动勾画
每年有超过六十万人被诊断患有头颈部癌症,其中许多人选择接受放射治疗. 但头颈部重要器官比较集中,解剖关系复杂,如果在治疗前未仔细隔离,放疗时周围组织可能会严重受损. 腾讯医疗 AI 实验室和美国加州大 ...
基于深度学习算法的行为识别解决方案：打电话、玩手机、摔倒等行为动作的识别，跟踪
文章大纲简介数据集准备一些难点 paddle 解决方案:PaddleDetection PP-human 行为识别打电话摔倒打架开源解决方案 deepsort 多目标跟踪 slow fa ...

基于深度学习算法实现视频人脸自动打码

前言

一、人脸检测

二、人脸打码

三、源码

基于深度学习算法实现视频人脸自动打码相关推荐

最新文章

热门文章