# Classify action
if DO_INFERENCE:
prediced_label = classifier.predict(skeleton)
print("prediced label is :", prediced_label)
else:
prediced_label = action_type
print("Ground_truth label is :", prediced_label)
if 1:
# Draw skeleton
if ith_skel == 0:
my_detector.draw(image_disp, humans)
# Draw bounding box and action type
drawActionResult(image_disp, skeleton, prediced_label)
# Write result to txt/png
if SAVE_RESULTANT_SKELETON_TO_TXT_AND_IMAGE:
myio.save_skeletons(SAVE_DETECTED_SKELETON_TO
+ int2str(ith_img, 5)+".txt", skelsInfo)
cv2.imwrite(SAVE_DETECTED_SKELETON_IMAGES_TO
+ int2str(ith_img, 5)+".png", image_disp)
if 1: # Display
cv2.imshow("action_recognition",
cv2.resize(image_disp,(0,0),fx=1.5,fy=1.5))
q = cv2.waitKey(1)
if q!=-1 and chr(q) == 'q':
break
def show_camera(self):
start = time.time()
ret, frame = self.cap.read()
#show = cv2.resize(frame, (settings.winWidth, settings.winHeight))
show = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if ret:
if self.__flag_mode == 1:
self.infoBox.setText(u'Pose estimation')
humans = my_detector.detect(show)
skelsInfo = SkeletonDetector.humans_to_skelsInfo(humans)
print('SkelsInfo: ', skelsInfo)
for ith_skel in range(0, len(skelsInfo)):
skeleton = SkeletonDetector.get_ith_skeleton(
skelsInfo, ith_skel)
if ith_skel == 0:
my_detector.draw(show, humans)
elif self.__flag_mode == 2:
self.infoBox.setText(u'Multiplayer tracking')
prediced_label = ''
humans = my_detector.detect(show)
skelsInfo = SkeletonDetector.humans_to_skelsInfo(humans)
for ith_skel in range(0, len(skelsInfo)):
skeleton = SkeletonDetector.get_ith_skeleton(
skelsInfo, ith_skel)
if ith_skel == 0:
my_detector.draw(show, humans)
print('show.shape: ', show.data)
drawActionResult(
show, skeleton,
prediced_label) #draw bboxs, prediced label
#show = np.array(show)
elif self.__flag_mode == 3:
self.infoBox.setText(u'Sign language recognition')
humans = my_detector.detect(show)
skelsInfo_choose = SkeletonDetector.humans_to_skelsInfo_choose(
humans, joint_choose)
skelsInfo = SkeletonDetector.humans_to_skelsInfo(humans)
if len(skelsInfo) == 0:
self.text = ''
for ith_skel in range(0, len(skelsInfo)):
skeleton = SkeletonDetector.get_ith_skeleton(
skelsInfo, ith_skel)
skeleton_choose = SkeletonDetector.get_ith_skeleton_choose(
skelsInfo_choose, ith_skel)
print('skeleton_choose.shape: ', skeleton_choose)
if len(skeleton_choose) == 20:
prediced_label, acc = classifier.predict(
skeleton_choose)
if acc < 0.95:
prediced_label = ''
if prediced_label != self.flag:
self.text = self.text + ' ' + prediced_label
self.flag = prediced_label
else:
prediced_label = ''
my_detector.draw(show, humans)
drawActionResult(show, skeleton, prediced_label)
self.textBox.setText('ID-1: ' + self.text)
end = time.time()
self.fps = 1. / (end - start)
cv2.putText(show, 'FPS: %.2f' % self.fps, (30, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
showImage = QtGui.QImage(show, show.shape[1], show.shape[0],
QtGui.QImage.Format_RGB888)
self.label_show_camera.setPixmap(
QtGui.QPixmap.fromImage(showImage))