高通手机跑AI系列之——人脸变化算法

# 使用BlazeFace模型进行人脸检测
def blazeface(raw_output_a, raw_output_b, anchors):# 解码边界框和分数detections = net.tensors_to_detections(raw_box_tensor, raw_score_tensor, anchors)# 非极大值抑制过滤重叠检测filtered_detections = net.weighted_non_max_suppression(detections[i])

# 检测人脸的468个关键点
model_path1 = "models/face_landmark.tflite"
mesh = fast_interpreter1.get_output_tensor(0)
mesh = mesh.reshape(468, 3) / 192

# 基于Delaunay三角剖分的人脸变换
def warpTriangle(img1, img2, t1, t2):# 计算仿射变换矩阵warpMat = cv2.getAffineTransform(np.float32(srcTri), np.float32(dstTri))# 应用变换并融合dst = cv2.warpAffine(src, warpMat, (size[0], size[1]))

# 创建UI界面选择目标人脸
class MyApp(App):def main(self):# 创建摄像头组件和图像选择按钮self.img1 = Image('/res:' + back_img_path[0], height=80, margin='10px')self.img1.onclick.do(self.on_img1_clicked)

import cv2
import math
import sys
import numpy as np
import os
import subprocess
import time
from cvs import *
import aidlite# 背景图像路径列表
back_img_path = ('models/rs.jpeg', 'models/wy.jpeg', 'models/zyx.jpeg', 'models/monkey.jpg', 'models/star2.jpg', 'models/star1.jpg', 'models/star3.jpg', 'models/star4.jpg')# 读取第一张背景图像
faceimg = cv2.imread(back_img_path[0])
mod = -1
bfirstframe = True# 从文件中读取关键点
def readPoints(path):# 创建一个关键点数组points = []# 打开文件读取关键点with open(path) as file:for line in file:x, y = line.split()points.append((int(x), int(y)))return points# 应用仿射变换
def applyAffineTransform(src, srcTri, dstTri, size):# 计算仿射变换矩阵warpMat = cv2.getAffineTransform(np.float32(srcTri), np.float32(dstTri))# 应用仿射变换到源图像dst = cv2.warpAffine(src, warpMat, (size[0], size[1]), None, flags=cv2.INTER_LINEAR, borderMode=cv2.BORDER_REFLECT_101)return dst# 检查点是否在矩形内
def rectContains(rect, point):if point[0] < rect[0]:return Falseelif point[1] < rect[1]:return Falseelif point[0] > rect[0] + rect[2]:return Falseelif point[1] > rect[1] + rect[3]:return Falsereturn True# 计算Delaunay三角形
def calculateDelaunayTriangles(rect, points):# 创建Subdiv2D对象subdiv = cv2.Subdiv2D(rect)ttp = None# 将关键点插入到Subdiv2D对象中for p in points:try:subdiv.insert(p)ttp = pexcept:subdiv.insert(ttp)continue# 获取三角形列表triangleList = subdiv.getTriangleList()delaunayTri = []pt = []for t in triangleList:pt.append((t[0], t[1]))pt.append((t[2], t[3]))pt.append((t[4], t[5]))pt1 = (t[0], t[1])pt2 = (t[2], t[3])pt3 = (t[4], t[5])# 检查三角形的三个顶点是否都在矩形内if rectContains(rect, pt1) and rectContains(rect, pt2) and rectContains(rect, pt3):ind = []# 获取关键点的索引for j in range(0, 3):for k in range(0, len(points)):if (abs(pt[j][0] - points[k][0]) < 1.0 and abs(pt[j][1] - points[k][1]) < 1.0):ind.append(k)# 如果索引列表长度为3，则将其添加到Delaunay三角形列表中if len(ind) == 3:delaunayTri.append((ind[0], ind[1], ind[2]))pt = []return delaunayTri# 对三角形区域进行变形和融合
def warpTriangle(img1, img2, t1, t2):# 找到每个三角形的边界矩形r1 = cv2.boundingRect(np.float32([t1]))r2 = cv2.boundingRect(np.float32([t2]))# 偏移关键点t1Rect = []t2Rect = []t2RectInt = []for i in range(0, 3):t1Rect.append(((t1[i][0] - r1[0]), (t1[i][1] - r1[1])))t2Rect.append(((t2[i][0] - r2[0]), (t2[i][1] - r2[1])))t2RectInt.append(((t2[i][0] - r2[0]), (t2[i][1] - r2[1])))# 创建掩码mask = np.zeros((r2[3], r2[2], 3), dtype=np.float32)cv2.fillConvexPoly(mask, np.int32(t2RectInt), (1.0, 1.0, 1.0), 16, 0)# 对小矩形区域应用仿射变换img1Rect = img1[r1[1]:r1[1] + r1[3], r1[0]:r1[0] + r1[2]]size = (r2[2], r2[3])img2Rect = applyAffineTransform(img1Rect, t1Rect, t2Rect, size)img2Rect = img2Rect * mask# 将变形后的三角形区域复制到输出图像中img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] = img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] * ((1.0, 1.0, 1.0) - mask)img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] = img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] + img2Rect# 人脸变换函数
def faceswap(points1, points2, img1, img2):img1Warped = np.copy(img2)# 找到凸包hull1 = []hull2 = []hullIndex = cv2.convexHull(np.array(points2), returnPoints=False)for i in range(0, len(hullIndex)):hull1.append(points1[int(hullIndex[i])])hull2.append(points2[int(hullIndex[i])])# 计算凸包关键点的Delaunay三角形sizeImg2 = img2.shaperect = (0, 0, sizeImg2[1], sizeImg2[0])dt = calculateDelaunayTriangles(rect, hull2)if len(dt) == 0:quit()# 对Delaunay三角形应用仿射变换for i in range(0, len(dt)):t1 = []t2 = []for j in range(0, 3):t1.append(hull1[dt[i][j]])t2.append(hull2[dt[i][j]])warpTriangle(img1, img1Warped, t1, t2)# 计算掩码hull8U = []for i in range(0, len(hull2)):hull8U.append((hull2[i][0], hull2[i][1]))mask = np.zeros(img2.shape, dtype=img2.dtype)cv2.fillConvexPoly(mask, np.int32(hull8U), (255, 255, 255))r = cv2.boundingRect(np.float32([hull2]))center = ((r[0] + int(r[2] / 2), r[1] + int(r[3] / 2)))# 无缝克隆try:output = cv2.seamlessClone(np.uint8(img1Warped), img2, mask, center, cv2.NORMAL_CLONE)except:return Nonereturn output# 对图像进行预处理，用于TFLite模型
def preprocess_image_for_tflite32(image, model_image_size=192):# 将图像从BGR颜色空间转换为RGB颜色空间image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)# 调整图像大小image = cv2.resize(image, (model_image_size, model_image_size))# 添加一个维度image = np.expand_dims(image, axis=0)# 归一化处理image = (2.0 / 255.0) * image - 1.0# 将图像数据类型转换为float32image = image.astype('float32')return image# 对图像进行填充和预处理
def preprocess_img_pad(img, image_size=128):# 获取图像的形状shape = np.r_[img.shape]# 计算需要填充的像素数pad_all = (shape.max() - shape[:2]).astype('uint32')pad = pad_all // 2# 对原始图像进行填充img_pad_ori = np.pad(img,((pad[0], pad_all[0] - pad[0]), (pad[1], pad_all[1] - pad[1]), (0, 0)),mode='constant')# 将图像从BGR颜色空间转换为RGB颜色空间img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)# 对RGB图像进行填充img_pad = np.pad(img,((pad[0], pad_all[0] - pad[0]), (pad[1], pad_all[1] - pad[1]), (0, 0)),mode='constant')# 调整图像大小img_small = cv2.resize(img_pad, (image_size, image_size))# 添加一个维度img_small = np.expand_dims(img_small, axis=0)# 归一化处理img_small = (2.0 / 255.0) * img_small - 1.0# 将图像数据类型转换为float32img_small = img_small.astype('float32')return img_pad_ori, img_small, pad# 绘制检测到的人脸框
def plot_detections(img, detections, with_keypoints=True):output_img = imgprint(img.shape)x_min = 0x_max = 0y_min = 0y_max = 0print("找到 %d 个人脸" % len(detections))for i in range(len(detections)):# 计算人脸框的坐标ymin = detections[i][0] * img.shape[0]xmin = detections[i][1] * img.shape[1]ymax = detections[i][2] * img.shape[0]xmax = detections[i][3] * img.shape[1]w = int(xmax - xmin)h = int(ymax - ymin)h = max(w, h)h = h * 1.5x = (xmin + xmax) / 2.y = (ymin + ymax) / 2.xmin = x - h / 2.xmax = x + h / 2.ymin = y - h / 2. - 0.08 * hymax = y + h / 2. - 0.08 * hx_min = int(xmin)y_min = int(ymin)x_max = int(xmax)y_max = int(ymax)p1 = (int(xmin), int(ymin))p2 = (int(xmax), int(ymax))# 绘制人脸框cv2.rectangle(output_img, p1, p2, (0, 255, 255), 2, 1)return x_min, y_min, x_max, y_max# 绘制人脸网格
def draw_mesh(image, mesh, mark_size=2, line_width=1):# 获取图像的大小image_size = image.shape[0]# 将归一化的网格坐标转换为图像坐标mesh = mesh * image_size# 绘制关键点for point in mesh:cv2.circle(image, (point[0], point[1]),mark_size, (0, 255, 128), -1)# 绘制眼睛轮廓left_eye_contour = np.array([mesh[33][0:2],mesh[7][0:2],mesh[163][0:2],mesh[144][0:2],mesh[145][0:2],mesh[153][0:2],mesh[154][0:2],mesh[155][0:2],mesh[133][0:2],mesh[173][0:2],mesh[157][0:2],mesh[158][0:2],mesh[159][0:2],mesh[160][0:2],mesh[161][0:2],mesh[246][0:2]]).astype(np.int32)right_eye_contour = np.array([mesh[263][0:2],mesh[249][0:2],mesh[390][0:2],mesh[373][0:2],mesh[374][0:2],mesh[380][0:2],mesh[381][0:2],mesh[382][0:2],mesh[362][0:2],mesh[398][0:2],mesh[384][0:2],mesh[385][0:2],mesh[386][0:2],mesh[387][0:2],mesh[388][0:2],mesh[466][0:2]]).astype(np.int32)# 绘制眼睛轮廓线cv2.polylines(image, [left_eye_contour, right_eye_contour], False,(255, 255, 255), line_width, cv2.LINE_AA)# 获取关键点
def getkeypoint(image, mesh, landmark_point):# 获取图像的大小image_size = image.shape[0]# 将归一化的网格坐标转换为图像坐标mesh = mesh * image_size# 将关键点添加到列表中for point in mesh:landmark_point.append((point[0], point[1]))return image# 绘制关键点和面部特征线
def draw_landmarks(image, mesh, landmark_point):# 获取图像的大小image_size = image.shape[0]# 将归一化的网格坐标转换为图像坐标mesh = mesh * image_size# 绘制关键点for point in mesh:landmark_point.append((point[0], point[1]))cv2.circle(image, (point[0], point[1]), 2, (255, 255, 0), -1)if len(landmark_point) > 0:# 绘制左眉毛cv2.line(image, landmark_point[55], landmark_point[65], (0, 0, 255), 2, -3)cv2.line(image, landmark_point[65], landmark_point[52], (0, 0, 255), 2, -3)cv2.line(image, landmark_point[52], landmark_point[53], (0, 0, 255), 2, -3)cv2.line(image, landmark_point[53], landmark_point[46], (0, 0, 255), 2, -3)# 绘制右眉毛cv2.line(image, landmark_point[285], landmark_point[295], (0, 0, 255), 2)cv2.line(image, landmark_point[295], landmark_point[282], (0, 0, 255), 2)cv2.line(image, landmark_point[282], landmark_point[283], (0, 0, 255), 2)cv2.line(image, landmark_point[283], landmark_point[276], (0, 0, 255), 2)# 绘制左眼睛cv2.line(image, landmark_point[133], landmark_point[173], (0, 0, 255), 2)cv2.line(image, landmark_point[173], landmark_point[157], (0, 0, 255), 2)cv2.line(image, landmark_point[157], landmark_point[158], (0, 0, 255), 2)cv2.line(image, landmark_point[158], landmark_point[159], (0, 0, 255), 2)cv2.line(image, landmark_point[159], landmark_point[160], (0, 0, 255), 2)cv2.line(image, landmark_point[160], landmark_point[161], (0, 0, 255), 2)cv2.line(image, landmark_point[161], landmark_point[246], (0, 0, 255), 2)cv2.line(image, landmark_point[246], landmark_point[163], (0, 0, 255), 2)cv2.line(image, landmark_point[163], landmark_point[144], (0, 0, 255), 2)cv2.line(image, landmark_point[144], landmark_point[145], (0, 0, 255), 2)cv2.line(image, landmark_point[145], landmark_point[153], (0, 0, 255), 2)cv2.line(image, landmark_point[153], landmark_point[154], (0, 0, 255), 2)cv2.line(image, landmark_point[154], landmark_point[155], (0, 0, 255), 2)cv2.line(image, landmark_point[155], landmark_point[133], (0, 0, 255), 2)# 绘制右眼睛cv2.line(image, landmark_point[362], landmark_point[398], (0, 0, 255), 2)cv2.line(image, landmark_point[398], landmark_point[384], (0, 0, 255), 2)cv2.line(image, landmark_point[384], landmark_point[385], (0, 0, 255), 2)cv2.line(image, landmark_point[385], landmark_point[386], (0, 0, 255), 2)cv2.line(image, landmark_point[386], landmark_point[387], (0, 0, 255), 2)cv2.line(image, landmark_point[387], landmark_point[388], (0, 0, 255), 2)cv2.line(image, landmark_point[388], landmark_point[466], (0, 0, 255), 2)cv2.line(image, landmark_point[466], landmark_point[390], (0, 0, 255), 2)cv2.line(image, landmark_point[390], landmark_point[373], (0, 0, 255), 2)cv2.line(image, landmark_point[373], landmark_point[374], (0, 0, 255), 2)cv2.line(image, landmark_point[374], landmark_point[380], (0, 0, 255), 2)cv2.line(image, landmark_point[380], landmark_point[381], (0, 0, 255), 2)cv2.line(image, landmark_point[381], landmark_point[382], (0, 0, 255), 2)cv2.line(image, landmark_point[382], landmark_point[362], (0, 0, 255), 2)# 绘制嘴巴cv2.line(image, landmark_point[308], landmark_point[415], (0, 0, 255), 2)cv2.line(image, landmark_point[415], landmark_point[310], (0, 0, 255), 2)cv2.line(image, landmark_point[310], landmark_point[311], (0, 0, 255), 2)cv2.line(image, landmark_point[311], landmark_point[312], (0, 0, 255), 2)cv2.line(image, landmark_point[312], landmark_point[13], (0, 0, 255), 2)cv2.line(image, landmark_point[13], landmark_point[82], (0, 0, 255), 2)cv2.line(image, landmark_point[82], landmark_point[81], (0, 0, 255), 2)cv2.line(image, landmark_point[81], landmark_point[80], (0, 0, 255), 2)cv2.line(image, landmark_point[80], landmark_point[191], (0, 0, 255), 2)cv2.line(image, landmark_point[191], landmark_point[78], (0, 0, 255), 2)cv2.line(image, landmark_point[78], landmark_point[95], (0, 0, 255), 2)cv2.line(image, landmark_point[95], landmark_point[88], (0, 0, 255), 2)cv2.line(image, landmark_point[88], landmark_point[178], (0, 0, 255), 2)cv2.line(image, landmark_point[178], landmark_point[87], (0, 0, 255), 2)cv2.line(image, landmark_point[87], landmark_point[14], (0, 0, 255), 2)cv2.line(image, landmark_point[14], landmark_point[317], (0, 0, 255), 2)cv2.line(image, landmark_point[317], landmark_point[402], (0, 0, 255), 2)cv2.line(image, landmark_point[402], landmark_point[318], (0, 0, 255), 2)cv2.line(image, landmark_point[318], landmark_point[324], (0, 0, 255), 2)cv2.line(image, landmark_point[324], landmark_point[308], (0, 0, 255), 2)return image# BlazeFace人脸检测模型类
class BlazeFace():def __init__(self):# 类别数量self.num_classes = 1# 锚点数量self.num_anchors = 896# 坐标数量self.num_coords = 16# 分数裁剪阈值self.score_clipping_thresh = 100.0# x坐标缩放因子self.x_scale = 128.0# y坐标缩放因子self.y_scale = 128.0# 高度缩放因子self.h_scale = 128.0# 宽度缩放因子self.w_scale = 128.0# 最小分数阈值self.min_score_thresh = 0.75# 最小抑制阈值self.min_suppression_threshold = 0.3# Sigmoid函数def sigmoid(self, inX):if inX >= 0:return 1.0 / (1 + np.exp(-inX))else:return np.exp(inX) / (1 + np.exp(inX))# 将原始输出张量转换为检测结果def tensors_to_detections(self, raw_box_tensor, raw_score_tensor, anchors):assert len(raw_box_tensor.shape) == 3assert raw_box_tensor.shape[1] == self.num_anchorsassert raw_box_tensor.shape[2] == self.num_coordsassert len(raw_score_tensor.shape) == 3assert raw_score_tensor.shape[1] == self.num_anchorsassert raw_score_tensor.shape[2] == self.num_classesassert raw_box_tensor.shape[0] == raw_score_tensor.shape[0]# 解码边界框detection_boxes = self._decode_boxes(raw_box_tensor, anchors)# 裁剪分数thresh = self.score_clipping_threshraw_score_tensor = raw_score_tensor.clip(-thresh, thresh)# 计算检测分数detection_scores = 1 / (1 + np.exp(-raw_score_tensor)).squeeze(axis=-1)# 过滤掉分数低于阈值的检测结果mask = detection_scores >= self.min_score_threshoutput_detections = []for i in range(raw_box_tensor.shape[0]):boxes = detection_boxes[i, mask[i]]scores = np.expand_dims(detection_scores[i, mask[i]], axis=-1)output_detections.append(np.concatenate((boxes, scores), axis=-1))return output_detections# 解码边界框def _decode_boxes(self, raw_boxes, anchors):boxes = np.zeros(raw_boxes.shape)# 计算边界框的中心点坐标x_center = raw_boxes[..., 0] / self.x_scale * anchors[:, 2] + anchors[:, 0]y_center = raw_boxes[..., 1] / self.y_scale * anchors[:, 3] + anchors[:, 1]# 计算边界框的宽度和高度w = raw_boxes[..., 2] / self.w_scale * anchors[:, 2]h = raw_boxes[..., 3] / self.h_scale * anchors[:, 3]# 计算边界框的左上角和右下角坐标boxes[..., 0] = y_center - h / 2.  # yminboxes[..., 1] = x_center - w / 2.  # xminboxes[..., 2] = y_center + h / 2.  # ymaxboxes[..., 3] = x_center + w / 2.  # xmax# 计算关键点坐标for k in range(6):offset = 4 + k * 2keypoint_x = raw_boxes[..., offset] / self.x_scale * anchors[:, 2] + anchors[:, 0]keypoint_y = raw_boxes[..., offset + 1] / self.y_scale * anchors[:, 3] + anchors[:, 1]boxes[..., offset] = keypoint_xboxes[..., offset + 1] = keypoint_yreturn boxes# 加权非极大值抑制def weighted_non_max_suppression(self, detections):if len(detections) == 0: return []output_detections = []# 按分数从高到低排序remaining = np.argsort(-detections[:, 16])while len(remaining) > 0:detection = detections[remaining[0]]# 计算第一个框与其他框的重叠度first_box = detection[:4]other_boxes = detections[remaining, :4]ious = overlap_similarity(first_box, other_boxes)# 过滤掉重叠度低于阈值的框mask = ious > self.min_suppression_thresholdoverlapping = remaining[mask]remaining = remaining[~mask]# 计算加权检测结果weighted_detection = detection.copy()if len(overlapping) > 1:coordinates = detections[overlapping, :16]scores = detections[overlapping, 16:17]total_score = scores.sum()weighted = (coordinates * scores).sum(axis=0) / total_scoreweighted_detection[:16] = weightedweighted_detection[16] = total_score / len(overlapping)output_detections.append(weighted_detection)return output_detections# BlazeFace人脸检测函数
def blazeface(raw_output_a, raw_output_b, anchors):if raw_output_a.size == 896:raw_score_tensor = raw_output_araw_box_tensor = raw_output_belse:raw_score_tensor = raw_output_braw_box_tensor = raw_output_aassert (raw_score_tensor.size == 896)assert (raw_box_tensor.size == 896 * 16)# 调整输出张量的形状raw_score_tensor = raw_score_tensor.reshape(1, 896, 1)raw_box_tensor = raw_box_tensor.reshape(1, 896, 16)net = BlazeFace()# 后处理原始预测结果detections = net.tensors_to_detections(raw_box_tensor, raw_score_tensor, anchors)# 非极大值抑制filtered_detections = []for i in range(len(detections)):faces = net.weighted_non_max_suppression(detections[i])if len(faces) > 0:faces = np.stack(faces)filtered_detections.append(faces)return filtered_detections# 将检测结果从填充图像坐标转换为原始图像坐标
def convert_to_orig_points(results, orig_dim, letter_dim):# 计算缩放比例inter_scale = min(letter_dim / orig_dim[0], letter_dim / orig_dim[1])inter_h, inter_w = int(inter_scale * orig_dim[0]), int(inter_scale * orig_dim[1])# 计算偏移量offset_x, offset_y = (letter_dim - inter_w) / 2.0 / letter_dim, (letter_dim - inter_h) / 2.0 / letter_dimscale_x, scale_y = letter_dim / inter_w, letter_dim / inter_h# 调整检测结果的坐标results[:, 0:2] = (results[:, 0:2] - [offset_x, offset_y]) * [scale_x, scale_y]results[:, 2:4] = results[:, 2:4] * [scale_x, scale_y]results[:, 4:16:2] = (results[:, 4:16:2] - offset_x) * scale_xresults[:, 5:17:2] = (results[:, 5:17:2] - offset_y) * scale_y# 将坐标从0-1范围转换为原始图像范围results[:, 0:16:2] *= orig_dim[1]results[:, 1:17:2] *= orig_dim[0]return results.astype(np.int32)# 计算两个边界框的交并比（IoU）
def overlap_similarity(box, other_boxes):def union(A, B):x1, y1, x2, y2 = Aa = (x2 - x1) * (y2 - y1)x1, y1, x2, y2 = Bb = (x2 - x1) * (y2 - y1)ret = a + b - intersect(A, B)return retdef intersect(A, B):x1 = max(A[0], B[0])y1 = max(A[1], B[1])x2 = min(A[2], B[2])y2 = min(A[3], B[3])return (x2 - x1) * (y2 - y1)ret = np.array([max(0, intersect(box, b) / union(box, b)) for b in other_boxes])return ret# 自定义应用类
class MyApp(App):def __init__(self, *args):super(MyApp, self).__init__(*args)# 空闲时更新摄像头def idle(self):self.aidcam0.update()# 主函数，创建UI界面def main(self):# 创建垂直容器main_container = VBox(width=360, height=680, style={'margin': '0px auto'})# 创建摄像头组件self.aidcam0 = OpencvVideoWidget(self, width=340, height=400)self.aidcam0.style['margin'] = '10px'i = 0exec("self.aidcam%(i)s = OpencvVideoWidget(self)" % {'i': i})exec("self.aidcam%(i)s.identifier = 'aidcam%(i)s'" % {'i': i})eval("main_container.append(self.aidcam%(i)s)" % {'i': i})main_container.append(self.aidcam0)# 创建标签self.lbl = Label('点击图片选择你喜欢的明星脸：')main_container.append(self.lbl)# 创建底部容器bottom_container = HBox(width=360, height=130, style={'margin': '0px auto'})# 创建图像组件self.img1 = Image('/res:' + os.getcwd() + '/' + back_img_path[0], height=80, margin='10px')self.img1.onclick.do(self.on_img1_clicked)bottom_container.append(self.img1)self.img2 = Image('/res:' + os.getcwd() + '/' + back_img_path[1], height=80, margin='10px')self.img2.onclick.do(self.on_img2_clicked)bottom_container.append(self.img2)self.img3 = Image('/res:' + os.getcwd() + '/' + back_img_path[2], height=80, margin='10px')self.img3.onclick.do(self.on_img3_clicked)bottom_container.append(self.img3)self.img4 = Image('/res:' + os.getcwd() + '/' + back_img_path[3], height=80, margin='10px')self.img4.onclick.do(self.on_img4_clicked)bottom_container.append(self.img4)# 创建按钮容器bt_container = HBox(width=360, height=130, style={'margin': '0px auto'})self.img11 = Image('/res:' + os.getcwd() + '/' + back_img_path[4], height=80, margin='10px')self.img11.onclick.do(self.on_img11_clicked)bt_container.append(self.img11)self.img22 = Image('/res:' + os.getcwd() + '/' + back_img_path[5], height=80, margin='10px')self.img22.onclick.do(self.on_img22_clicked)bt_container.append(self.img22)self.img33 = Image('/res:' + os.getcwd() + '/' + back_img_path[6], height=80, margin='10px')self.img33.onclick.do(self.on_img33_clicked)bt_container.append(self.img33)self.img44 = Image('/res:' + os.getcwd() + '/' + back_img_path[7], height=80, margin='10px')self.img44.onclick.do(self.on_img44_clicked)bt_container.append(self.img44)main_container.append(bottom_container)main_container.append(bt_container)return main_container# 点击第一张图片的回调函数def on_img1_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[0])faceimg = bgndglobal modmod = 0# 点击第二张图片的回调函数def on_img2_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[1])faceimg = bgndglobal modmod = 1# 点击第三张图片的回调函数def on_img3_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[2])faceimg = bgndglobal modmod = 2# 点击第四张图片的回调函数def on_img4_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[3])faceimg = bgndglobal modmod = 3# 点击第五张图片的回调函数def on_img11_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[4])faceimg = bgndglobal modmod = 4# 点击第六张图片的回调函数def on_img22_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[5])faceimg = bgndglobal modmod = 5# 点击第七张图片的回调函数def on_img33_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[6])faceimg = bgndglobal modmod = 6# 点击第八张图片的回调函数def on_img44_clicked(self, widget):global faceimgbgnd = cv2.imread(back_img_path[7])faceimg = bgndglobal modmod = 7# 点击第一个按钮的回调函数def on_button_pressed1(self, widget):global modmod = 0# 点击第二个按钮的回调函数def on_button_pressed2(self, widget):global modmod = 1# 点击第三个按钮的回调函数def on_button_pressed3(self, widget):global modmod = 2# 获取摄像头ID
def get_cap_id():try:# 构造命令，使用awk处理输出cmd = "ls -l /sys/class/video4linux | awk -F ' -> ' '/usb/{sub(/.*video/, \"\", $2); print $2}'"result = subprocess.run(cmd, shell=True, capture_output=True, text=True)output = result.stdout.strip().split()# 转换所有捕获的编号为整数，找出最小值video_numbers = list(map(int, output))if video_numbers:return min(video_numbers)else:return Noneexcept Exception as e:print(f"发生错误: {e}")return None# 处理函数，实现人脸变换
def process():cvs.setCustomUI()# 初始化人脸检测模型inShape = [[1, 128, 128, 3]]outShape = [[1, 896, 16], [1, 896, 1]]model_path = "models/face_detection_front.tflite"model = aidlite.Model.create_instance(model_path)if model is None:print("创建face_detection_front模型失败！")model.set_model_properties(inShape, aidlite.DataType.TYPE_FLOAT32, outShape, aidlite.DataType.TYPE_FLOAT32)config = aidlite.Config.create_instance()config.implement_type = aidlite.ImplementType.TYPE_FASTconfig.framework_type = aidlite.FrameworkType.TYPE_TFLITEconfig.accelerate_type = aidlite.AccelerateType.TYPE_CPUconfig.number_of_threads = 4fast_interpreter = aidlite.InterpreterBuilder.build_interpretper_from_model_and_config(model, config)if fast_interpreter is None:print("face_detection_front模型build_interpretper_from_model_and_config失败！")result = fast_interpreter.init()if result != 0:print("face_detection_front模型解释器初始化失败！")result = fast_interpreter.load_model()if result != 0:print("face_detection_front模型解释器加载模型失败！")print("face_detection_front模型加载成功！")# 初始化人脸关键点检测模型model_path1 = "models/face_landmark.tflite"inShape1 = [[1 * 192 * 192 * 3]]outShape1 = [[1 * 1404 * 4], [1 * 4]]model1 = aidlite.Model.create_instance(model_path1)if model1 is None:print("创建face_landmark模型失败！")model1.set_model_properties(inShape1, aidlite.DataType.TYPE_FLOAT32, outShape1, aidlite.DataType.TYPE_FLOAT32)config1 = aidlite.Config.create_instance()config1.implement_type = aidlite.ImplementType.TYPE_FASTconfig1.framework_type = aidlite.FrameworkType.TYPE_TFLITEconfig1.accelerate_type = aidlite.AccelerateType.TYPE_GPUconfig1.number_of_threads = 4fast_interpreter1 = aidlite.InterpreterBuilder.build_interpretper_from_model_and_config(model1, config1)if fast_interpreter1 is None:print("face_landmark模型build_interpretper_from_model_and_config失败！")result = fast_interpreter1.init()if result != 0:print("face_landmark模型解释器初始化失败！")result = fast_interpreter1.load_model()if result != 0:print("face_landmark模型解释器加载模型失败！")print("face_landmark模型加载成功！")# 加载锚点anchors = np.load('models/anchors.npy').astype(np.float32)# 0-后置，1-前置camid = 1capId = get_cap_id()if capId is None:print("使用MIPI摄像头")else:print("使用USB摄像头")camid = -1cap = cvs.VideoCapture(camid)bFace = Falsex_min, y_min, x_max, y_max = (0, 0, 0, 0)fface = 0.0global bfirstframebfirstframe = Truefacepath = "Biden.jpeg"global faceimgfaceimg = cv2.resize(faceimg, (256, 256))roi_orifirst = faceimgpadfaceimg = faceimgfpoints = []spoints = []global modmod = -1while True:# 读取帧frame = cvs.read()if frame is None:continueif camid == 1:frame = cv2.flip(frame, 1)if mod > -1 or bfirstframe:x_min, y_min, x_max, y_max = (0, 0, 0, 0)faceimg = cv2.resize(faceimg, (256, 256))frame = faceimgbFace = Falseroi_orifirst = faceimgpadfaceimg = faceimgbfirstframe = Truefpoints = []spoints = []# 记录开始时间start_time = time.time()# 对图像进行填充和预处理img_pad, img, pad = preprocess_img_pad(frame, 128)if bFace == False:# 设置输入数据result = fast_interpreter.set_input_tensor(0, img.data)if result != 0:print("face_detection_front模型解释器set_input_tensor()失败")# 执行推理result = fast_interpreter.invoke()if result != 0:print("face_detection_front模型解释器invoke()失败")# 获取输出数据raw_boxes = fast_interpreter.get_output_tensor(0)if raw_boxes is None:print("示例: face_detection_front模型解释器->get_output_tensor(0)失败！")classificators = fast_interpreter.get_output_tensor(1)if classificators is None:print("示例: face_detection_front模型解释器->get_output_tensor(1)失败！")# 进行人脸检测detections = blazeface(raw_boxes, classificators, anchors)[0]if len(detections) > 0:bFace = Trueif bFace:for i in range(len(detections)):# 计算人脸框的坐标ymin = detections[i][0] * img_pad.shape[0]xmin = detections[i][1] * img_pad.shape[1]ymax = detections[i][2] * img_pad.shape[0]xmax = detections[i][3] * img_pad.shape[1]w = int(xmax - xmin)h = int(ymax - ymin)h = max(w, h)h = h * 1.5x = (xmin + xmax) / 2.y = (ymin + ymax) / 2.xmin = x - h / 2.xmax = x + h / 2.ymin = y - h / 2.ymax = y + h / 2.ymin = y - h / 2. - 0.08 * hymax = y + h / 2. - 0.08 * hx_min = int(xmin)y_min = int(ymin)x_max = int(xmax)y_max = int(ymax)x_min = max(0, x_min)y_min = max(0, y_min)x_max = min(img_pad.shape[1], x_max)y_max = min(img_pad.shape[0], y_max)roi_ori = img_pad[y_min:y_max, x_min:x_max]roi = preprocess_image_for_tflite32(roi_ori, 192)# 设置输入数据result = fast_interpreter1.set_input_tensor(0, roi.data)if result != 0:print("face_landmark模型解释器set_input_tensor()失败")# 执行推理result = fast_interpreter1.invoke()if result != 0:print("face_landmark模型解释器invoke()失败")# 获取输出数据mesh = fast_interpreter1.get_output_tensor(0)if mesh is None:print("示例: face_landmark模型解释器->get_output_tensor(0)失败！")stride8 = fast_interpreter1.get_output_tensor(1)if stride8 is None:print("示例: face_landmark模型解释器->get_output_tensor(1)失败！")ffacetmp = stride8[0]print('fface:', abs(fface - ffacetmp))if abs(fface - ffacetmp) > 0.5:bFace = Falsefface = ffacetmpspoints = []mesh = mesh.reshape(468, 3) / 192if bfirstframe:# 获取关键点getkeypoint(roi_ori, mesh, fpoints)roi_orifirst = roi_ori.copy()bfirstframe = Falsemod = -1else:# 获取关键点getkeypoint(roi_ori, mesh, spoints)# 进行人脸变换roi_ori = faceswap(fpoints, spoints, roi_orifirst, roi_ori)if roi_ori is None:continueimg_pad[y_min:y_max, x_min:x_max] = roi_orishape = frame.shapex, y = img_pad.shape[0] / 2, img_pad.shape[1] / 2frame = img_pad[int(y - shape[0] / 2):int(y + shape[0] / 2), int(x - shape[1] / 2):int(x + shape[1] / 2)]# 计算处理时间t = (time.time() - start_time)lbs = 'Fps: ' + str(int(100 / t) / 100.) + " ~~ Time:" + str(t * 1000) + "ms"cvs.setLbs(lbs)# 显示帧cvs.imshow(frame)# 休眠1毫秒time.sleep(0.001)if __name__ == '__main__':initcv(startcv, MyApp)process()