infr/falldetector-public

Fall detector with an overhead camera

falldetector-public's Issues

Person detection dependent on Objects around

Hi I am running main.py from fall-detector-v2.
But I find that objects around me are detected and contours are drawn around instead of drawing around the person, hence giving wrong results.
Should full person be seen in the image for person to be detected ?

For Eg , In the attached image , contours are drawn on object behind me

Not able to run the video.py

Hi ,

I was looking through your code however i was not able to run the video.py file
It says cv2.putText(self.frame, "Status: {}".format(detectStatus), (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,(0, 140, 255),1)
cv2.putText(self.frame, "FPS: {}".format(fps), (400, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,(0, 140, 255),1)
Self is not defined
I converted the code to python 3 However I am not able to run the file.
Please help me for the same

Will raspberry pie screen update rate is very low?

Will raspberry pie screen update rate is very low?

Not able to run

Hi ,

Sorry to bother you again ,I installed python 2.17.13
and tried to run the code however i am facing the below error could you please help me for the same
C:\Users\sahil.d.arora\Desktop\sw\falldetector-public-master\fall-detector-v2\video.py", line 137, in compare
(contours, _) = cv2.findContours(self.thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) #find contours
ValueError: too many values to unpack