dzungvpham / fall-detection-two-stream-cnn

Real-time fall detection using two-stream convolutional neural net (CNN) with Motion History Image (MHI)

fall-detection-two-stream-cnn

Real-time fall detection using two-stream convolutional neural net (CNN) with Motion History Image (MHI)

This repository contains code for a real-time fall detection model using two-stream CNN. The optical flow stream is replaced with Motion History Image (MHI) to allow for real-time inference. The utils.py file contains utility code for generating the data, the train_model.py file creates and trains the model, and the fall_detection.py file contains code that runs the model with the weight in the weights folder either on the FDD dataset, a video, or your webcam. More detailed description of the model architecture, performance, as well as demo footage/pictures to come in the near future. Achieved fairly good cross-validated error rate on a subset of data generated. Currently working on acquiring more data and refining data generation technique.

fall-detection-two-stream-cnn's Issues

problem with using the "depth_multiplier" argument

Hi thank you for the wonderful work
There is a problem with using the depth_multiplier argument
This is in the next line
#L19

base_model = MobileNetV2(
        input_shape = (224, 224, 3), alpha = 1.0, depth_multiplier = 1,
        include_top = False, weights = "imagenet"
    )

It may appear like the following error

TypeError: ('Invalid keyword argument: %s', 'depth_multiplier')
It seems that he has been stopped summoning him in recent versions of the kers library

cut ... In the docs (https://keras.io/applications/#mobilenetv2), depth_multiplier is listed and used as an argument to keras.applications.MobileNetV2, even though it is not implemented in .....

see keras-team/keras#12327

Please be amended or removed, if it is worth, from your point of view.
__
Another thing .. What about the training data, are there any tips on processing more training data, or can you share your data?

Thanks again
Mohammed Emad:

about dataset

Could you tell me which dataset you use? I can not find the download link fot the FDD dataset, could you share it with me?Thank you !

could you share your weights pelase

Hi, @dzungvpham , if you still happen to work on this project, could you please share your weights and some guidelines on how to inference videos? Than you!

About DATA_PATH

Can u please provide "datasets/fdd.hdf5" this file @VietDzung

is there a publication linked to this repo?

could you please share the PDF of the publication/technical report linked to this repo?

Hi, What is your opencv version?

cv.motempl.updateMotionHistory(...)
AttributeError: module 'cv2.cv2' has no attribute 'motempl'
I can't use opencv4.1.2 or 3.4.2

Tensorflow DLL load failed

I am receiving having this error on launch fall_detection.py :

I am using the newer version of TensorFlow, as the old one is not usable:

Connected to pydev debugger (build 191.7479.30)
Traceback (most recent call last):
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow.py", line 58, in <module>
    from tensorflow.python.pywrap_tensorflow_internal import *
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow_internal.py", line 28, in <module>
    _pywrap_tensorflow_internal = swig_import_helper()
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow_internal.py", line 24, in swig_import_helper
    _mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\imp.py", line 242, in load_module
    return load_dynamic(name, filename, file)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\imp.py", line 342, in load_dynamic
    return _load(spec)
ImportError: DLL load failed: The specified module could not be found.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\Apps\JetBrains\PyCharm Community Edition 2019.1.3\helpers\pydev\pydevd.py", line 1758, in <module>
    main()
  File "D:\Apps\JetBrains\PyCharm Community Edition 2019.1.3\helpers\pydev\pydevd.py", line 1752, in main
    globals = debugger.run(setup['file'], None, None, is_module)
  File "D:\Apps\JetBrains\PyCharm Community Edition 2019.1.3\helpers\pydev\pydevd.py", line 1147, in run
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "D:\Apps\JetBrains\PyCharm Community Edition 2019.1.3\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "D:/Multiverse_Projects/Final year project- Fall Detection/fall-detection-two-stream-cnn-master/tensorflow_test.py", line 1, in <module>
    import tensorflow as tf
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\__init__.py", line 101, in <module>
    from tensorflow_core import *
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\__init__.py", line 40, in <module>
    from tensorflow.python.tools import module_util as _module_util
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\__init__.py", line 50, in __getattr__
    module = self._load()
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\__init__.py", line 44, in _load
    module = _importlib.import_module(self.__name__)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\importlib\__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\__init__.py", line 49, in <module>
    from tensorflow.python import pywrap_tensorflow
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow.py", line 74, in <module>
    raise ImportError(msg)
ImportError: Traceback (most recent call last):
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow.py", line 58, in <module>
    from tensorflow.python.pywrap_tensorflow_internal import *
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow_internal.py", line 28, in <module>
    _pywrap_tensorflow_internal = swig_import_helper()
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\pywrap_tensorflow_internal.py", line 24, in swig_import_helper
    _mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\imp.py", line 242, in load_module
    return load_dynamic(name, filename, file)
  File "C:\Users\prahu\AppData\Local\Programs\Python\Python37\lib\imp.py", line 342, in load_dynamic
    return _load(spec)
ImportError: DLL load failed: The specified module could not be found.


Failed to load the native TensorFlow runtime.

See https://www.tensorflow.org/install/errors

for some common reasons and solutions.  Include the entire stack trace
above this error message when asking for help.

Process finished with exit code -1

Any help is appreciated

AttributeError: module 'cv2.cv2' has no attribute 'motempl'

Traceback (most recent call last):
File "fall_detection.py", line 300, in
start_fall_detector_realtime("Evening_108(3).mp4")
File "fall_detection.py", line 210, in start_fall_detector_realtime
cv.motempl.updateMotionHistory(motion_mask, prev_mhi[prev_ind], prev_timestamp[prev_ind], MHI_DURATION)
AttributeError: module 'cv2.cv2' has no attribute 'motempl'

i install requirements and python3.6 and opencv-contrib-python,opencv-python (4.0.0.21)
plz help me

Hack COVID19 participation

@VietDzung great project!

Would you be interested in joining the COVID19 hackathon this weekend. There is a project on remote elderly care. Fall detection is a main use case:

https://devpost.com/software/remote-elderly-home-care-via-privacy-preserving-surveillance

Hi,

Where is annotation_path = "datasets/FDD/Annotations_all.txt" file?

Thanks a lot for open-sourcing your code for fall detection on FDD dataset.

When I tried to preprocess the Le2i_FDD dataset that I downloaded from your Google Drive, I got the following error.

Could you please tell me know how I could fix this?

(fall) mona@goku:~/research/code/fall-detection-two-stream-cnn$ python utils.py 
Traceback (most recent call last):
  File "utils.py", line 607, in <module>
    create_two_stream_dataset_FDD()
  File "utils.py", line 370, in create_two_stream_dataset_FDD
    with open(annotation_path, "r") as annotation_file:
FileNotFoundError: [Errno 2] No such file or directory: 'datasets/FDD/Annotations_all.txt'

additionally, I had a quick report of some missing files in FDD that I downloaded from your Website since the original Website gave me 503 error.

nithiroj/Fall-Detection-PyTorch#3

Thanks a lot for your help.

URFD Dataset

Hey brother you have tried to make your programme for urfd dataset. I am trying to combine more dataset to train your model.