def main():
config = Config()
# 关系图中包括(include)哪些函数名。
#如果是某一类的函数，例如类gobang，则可以直接写'gobang.*'，表示以gobang.开头的所有函数。（利用正则表达式）。
config.trace_filter = GlobbingFilter(include=[
'main',
'pycallgraph.*',
'*.secret_function',
])
graphviz = GraphvizOutput()
graphviz.output_file = 'basic.png' #图片名称
with PyCallGraph(output=graphviz):
# coco
modelpath = "model/"
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Pose Model loads time: ", time.time() - start)
# yolo
start = time.time()
_yolo = YOLO() # 1.加载模型
print("[INFO]yolo Model loads time: ", time.time() - start)
img_path = 'D:/myworkspace/dataset/My_test/img/a_img/airplane_30.jpg'
getImgInfo(img_path, pose_model, _yolo)
f = os.path.join(path, labelname)
for i, imgname in enumerate(os.listdir(f)):
imgpath = os.path.join(f, imgname)
X.append(imgpath)
Y.append(labelname)
X = np.array(X)
Y = np.array(Y)
# ----------------------------------------------------------------------------------
# 第二步 识别infolist
# ----------------------------------------------------------------------------------
# coco
modelpath = "model/"
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Pose Model loads time: ", time.time() - start)
# yolo
start = time.time()
_yolo = YOLO() # 1.加载模型
print("[INFO]yolo Model loads time: ", time.time() - start)
infolist = []
for i in X:
hist = getImgInfo(i, pose_model, _yolo) # 识别
infolist.append(hist)
# ----------------------------------------------------------------------------------
# 第三步 存储信息docs/feature/features_all.csv
# ----------------------------------------------------------------------------------
# 路径存储到txt
def _loadmodel(self):
start = time.time()
self.pose_model = general_coco_model(self.model_path) # coco加载模型
self._yolo = YOLO() # 1.加载模型yolo
self.tips.SetValue(u"模型加载耗时:{:.2f} s".format(time.time() - start) +
"\n")
def getVideo_Info(modelpath, video_path, output_path=""):
from cv2 import cv2
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(cap.get(cv2.CAP_PROP_FOURCC)) # 获取原始视频的信息
video_fps = cap.get(cv2.CAP_PROP_FPS)
video_size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if output_path != "" else False # 如果设置了视频保存路径，则保存视频
if isOutput:
print("!!! TYPE:", type(output_path), type(video_FourCC),
type(video_fps), type(video_size))
out = cv2.VideoWriter(output_path, video_FourCC, video_fps,
video_size) # 根据原视频设置 保存视频的路径、大小、帧数
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = time.time()
yolo = YOLO()
pose_model = general_coco_model(modelpath) # 1.加载模型
while True:
return_value, frame = cap.read()
if return_value:
# 骨骼
bone_points = pose_model.getBoneKeypoints(frame) # 2.骨骼关键点
lineimage, dotimage = pose_model.vis_bone_pose(
frame, bone_points) # 骨骼连线图、标记图显示
# list1 = getBoneInformation(bone_points) # 3.骨骼特征
temp, labelinfo = yolo.detect_image(
Image.fromarray(frame), Image.fromarray(lineimage)) # 检测PIL格式
result = np.asarray(temp) # 画图到全部图上
curr_time = time.time()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result,
text=fps,
org=(3, 15),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50,
color=(255, 0, 0),
thickness=2)
cv2.putText(result,
"q-'quit'",
org=(3, 45),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50,
color=(0, 255, 0),
thickness=2) # 标注字体
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if isOutput:
out.write(result)
else:
print("Frame is end!")
break
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def getImageInfo(img_file, modelpath):
"""获得所有信息
:param 图片,模型路径
:return list单图的信息
"""
print("[INFO]Pose estimation.")
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Model loads time: ", time.time() - start)
# 骨骼
start = time.time()
img = cv2.imread(img_file)
bone_points = pose_model.getBoneKeypoints(img) # 2.骨骼关键点
print("[INFO]COCO18_Model predicts time: ", time.time() - start)
lineimage, dotimage, black_np = pose_model.vis_bone_pose(
img, bone_points) # 骨骼连线图、标记图显示cv2格式
list1 = getBoneInformation(bone_points) # 3.骨骼特征
#print("[INFO]Model Bone Information[25]: ", list1)
# yolo
_yolo = YOLO()
# cv2图片转PIL
image = Image.open(img_file)
lineimage = Image.fromarray(cv2.cvtColor(lineimage, cv2.COLOR_BGR2RGB))
black_np = Image.fromarray(cv2.cvtColor(black_np, cv2.COLOR_BGR2RGB))
r_image, labelinfo, hand_ROI_PIL = _yolo.detect_image(
image, black_np) # 原图，lineimage线图,黑幕图
# plt.figure(figsize=[5, 5])
# plt.subplot(1, 2, 1)
# plt.imshow(r_image)
# plt.xlabel(u'线图', fontsize=20)
# plt.axis("off")
# plt.subplot(1, 2, 2)
# plt.imshow(cv2.cvtColor(dotimage, cv2.COLOR_BGR2RGB))
# plt.xlabel(u'点图', fontsize=20)
# plt.axis("off")
# plt.show()
# # 手势
# print("[INFO]Hands estimation.by handpose")
# start = time.time()
# hand_model = general_hand_model(modelpath) # 1.加载模型
# hand_fd = hand_fourierDesciptor()
# for i,handimg in enumerate(hand_ROI_PIL):
# img = cv2.cvtColor(np.asarray(handimg),cv2.COLOR_RGB2BGR)
# # hand 模型
# onehandpoints = hand_model.getOneHandKeypoints(img)
# hand_model.vis_hand_pose(img, onehandpoints)# 显示
# # hand_FD 描述子
# res1 = hand_fd.skinMask(img) # 进行肤色检测
# ret1, fourier = hand_fd.fourierDesciptor(res1) # 傅里叶描述子获取轮廓点
info = []
for i in range(len(list1)):
info.append(list1[i])
for j in range(len(labelinfo)):
info.append(labelinfo[j])
print(labelinfo)
return r_image, info