dolongbien/humanbehaviorbku

Abnormal Human Behaviors Detection/ Road Accident Detection From Surveillance Videos/ Real-World Anomaly Detection in Surveillance Videos/ C3D Feature Extraction

dolongbien

Parallel Computing 2018 (Lab)

humanbehaviorbku's Issues

how to generate TXT files

Hello,

when I upload a video into the project through GUI...
celery is running and producing .npy files in media/features/ folder.

But I need .TXT file for an uploaded video in media/features/ in order to run 'video/str:video_type/str:video_title' (from url for VideoDetailView)

1. How to generate .txt file for a particular video(which function is taking care of producing .txt file in the code)?
2. How to generate .mat file for a particular video(which function is taking care of producing .mat file in the code)?

Thanks in advance

Prediction of human behaviour on live video

Can we pass the link of live cctv camera while predicting

Modified version

Hi @dolongbien ,
Can you give me some change you did in your implementation ? I found the original git for this paper here: "https://github.com/vantage-vision-vv/Anomaly-Detection-in-Surveillance-Videos".

Thank you in advance!

Dataset

Can you please share the dataset.

Running on colab ..Unable to extract feature using c3d

extract feature

%cd /content/C3D/C3D-v1.0/examples/c3d_feature_extraction
!sudo bash c3d_sport1m_feature_extraction_video.sh

This is the error I am getting while executing the above code.
I0117 06:43:11.085855 4186 net.cpp:183] Collecting Learning Rate and Weight Decay.
I0117 06:43:11.085873 4186 net.cpp:176] Network initialization done.
I0117 06:43:11.085881 4186 net.cpp:177] Memory required for Data 5653289408
E0117 06:43:11.816212 4186 extract_image_features.cpp:81] Extracting features for 1 batches
F0117 06:43:13.534600 4186 vol2col.cu:75] Check failed: error == cudaSuccess (48 vs. 0) no kernel image is available for execution on the device
*** Check failure stack trace: ***
c3d_sport1m_feature_extraction_video.sh: line 3: 4186 Aborted (core dumped) GLOG_logtosterr=1 ../../build/tools/extract_image_features.bin prototxt/c3d_sport1m_feature_extractor_video.prototxt conv3d_deepnetA_sport1m_iter_1900000 0 50 1 prototxt/output_list_video_prefix.txt fc7-1 fc6-1 prob

Failed when upload new video

Hi @dolongbien, I have ran your project and it worked great. But when I add a new video, the webpage of that task is cracked while the other task still working well. The error is:
NoReverseMatch at /catalog/video-upload
Reverse for 'task_status' with arguments '('',)' not found. 1 pattern(s) tried: ['celery\-progress\/(?P<task_id>[\w-]+)/$']
Could you help me solved this. Thank you.

[web app] can't view any of the videos

The integration went mostly successful and after a few hours of debugging, I was successfully deployed the web app at localhost http://127.0.0.1:8000.

But when I click the "video demo" tab and click one of the videos,
I get the following error

any ideas on how to fix this?

thanks

edit:
here's the server-side error

Internal Server Error: /catalog/video/abnormal/RoadAccidents343_x264
Traceback (most recent call last):
  File "C:\Users\Anaconda3\envs\[]\lib\site-packages\django\core\handlers\exception.py", line 34, in inner
    response = get_response(request)
  File "C:\Users\c\Anaconda3\envs\trillion_question_mark\lib\site-packages\django\core\handlers\base.py", line 115, in _get_response
    response = self.process_exception_by_middleware(e, request)
  File "C:\Users\p\Anaconda3\envs\trillion_question_mark\lib\site-packages\django\core\handlers\base.py", line 113, in _get_response
    response = wrapped_callback(request, *callback_args, **callback_kwargs)
  File "C:\Users\c\Anaconda3\envs\trillion_question_mark\lib\site-packages\django\views\generic\base.py", line 71, in view
    return self.dispatch(request, *args, **kwargs)
  File "C:\Users\c\Anaconda3\envs\trillion_question_mark\lib\site-packages\django\views\generic\base.py", line 97, in dispatch
    return handler(request, *args, **kwargs)
  File "C:\Users\c\Anaconda3\envs\trillion_question_mark\lib\site-packages\django\views\generic\base.py", line 158, in get
    context = self.get_context_data(**kwargs)
  File "C:\\[]\HumanBehaviorBKU\WebApp\catalog\views.py", line 84, in get_context_data
    x, scores = get_score(video_path)
  File "C:\[]\HumanBehaviorBKU\WebApp\c3d\plot_controller.py", line 73, in get_score
    F_Score = np.matlib.repmat(predictions[iv],1,(int(total_segments[iv+1])-int(total_segments[iv])))
  File "C:\Users\[]\Anaconda3\envs\trillion_question_mark\lib\site-packages\numpy\matlib.py", line 362, in repmat
    c = a.reshape(1, a.size).repeat(m, 0).reshape(rows, origcols).repeat(n, 0)
ValueError: negative dimensions are not allowed
[17/Jul/2019 21:47:45] "GET /catalog/video/abnormal/RoadAccidents343_x264 HTTP/1.1" 500 115664

It failed to make build folder which helps in feature extractions

!make test

/usr/local/cuda/bin/nvcc -ccbin=/usr/bin/g++ -Xcompiler -fPIC -DNDEBUG -O2 -I/usr/local/include/python2.7 -I/usr/local/lib/python2.7/dist-packages/numpy/core/include -I/usr/local/include -I/usr/include/hdf5/serial/ -Ibuild/src -I./src -I./include -I/usr/local/cuda/include -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode=arch=compute_50,code=sm_50 -c src/caffe/util/im2col.cu -o build/src/caffe/util/im2col.cuo nvcc fatal : Unsupported gpu architecture 'compute_30' Makefile:347: recipe for target 'build/src/caffe/util/im2col.cuo' failed make: *** [build/src/caffe/util/im2col.cuo] Error 1

While running this file it failed to build. Is there any particular reason or configuration is match

AttributeError: 'int' object has no attribute 'set_progress'

Function -
def extract_feature_video(video_path, progress_recorder, features_per_bag = params.features_per_bag):
........
........
........

running this gives error:-

Models initialized
Traceback (most recent call last):
File "extract_feature.py", line 67, in
extract_feature_video('media/videos/anormaly/Shoplifting028_x264.mp4', 32)
File "extract_feature.py", line 30, in extract_feature_video
progress_recorder.set_progress(i, len(video_clips))

Has anyone got this error ?

Problems in protoc version

I would like to know which version of protoc is used, as I am encountering the following problem while compiling C3D:

In file included from build/src/caffe/proto/caffe_pretty_print.pb.cc:4:0:
build/src/caffe/proto/caffe_pretty_print.pb.h:17:2: error: #error This file was generated by an older version of protoc which is
#error This file was generated by an older version of protoc which is
^
build/src/caffe/proto/caffe_pretty_print.pb.h:18:2: error: #error incompatible with your Protocol Buffer headers. Please
#error incompatible with your Protocol Buffer headers. Please
^
build/src/caffe/proto/caffe_pretty_print.pb.h:19:2: error: #error regenerate this file with a newer version of protoc.
#error regenerate this file with a newer version of protoc.
^
In file included from build/src/caffe/proto/caffe.pb.cc:4:0:
build/src/caffe/proto/caffe.pb.h:17:2: error: #error This file was generated by an older version of protoc which is
#error This file was generated by an older version of protoc which is
^
build/src/caffe/proto/caffe.pb.h:18:2: error: #error incompatible with your Protocol Buffer headers. Please
#error incompatible with your Protocol Buffer headers.

greetings sir , have been trying the h5 model you shared in this git. however it doesn't seem to be working because model contains only weights. can you please share full version of the model? or is there anyway to make the model you shared work on my local PC? your answer will be highly appreciated .

The output score is all 0.The OneDrive link you put is invalid

Hello, I am running your HumanBehaviorBKU on GitHub. I converted fc-6 into TXT form and put it into the program. The output score is all 0.The OneDrive link you put is invalid, so could you please send me some testing videos (mp4 and fc-6) that you used in the experiment,Or repost a link on GitHub.so that I can check what's wrong with myself.Thank you very much!

Unable to run Save_C3DFeatures_32Segments.m file.

IndexError: list index out of range

when try to train the network, got this error

https://colab.research.google.com/drive/1FX8J7UioZKxuDAUz2y662_FJQ-bhXRu2

AttributeError: module 'theano' has no attribute 'tests'

already tried after install "pip install nose". but can't solve this.

`Using Theano backend.

---

AttributeError Traceback (most recent call last)

in ()
----> 1 from keras.models import Sequential
2 from keras.layers import Dense, Dropout, Activation, TimeDistributedDense ,LSTM,Reshape
3 from keras.regularizers import l2
4 from keras.optimizers import SGD,adam, Adagrad
5 from scipy.io import loadmat, savemat

3 frames

/usr/local/lib/python3.6/dist-packages/theano/init.py in ()
98 # needed during that phase.
99 import theano.tests
--> 100 if hasattr(theano.tests, "TheanoNoseTester"):
101 test = theano.tests.TheanoNoseTester().test
102 else:

AttributeError: module 'theano' has no attribute 'tests'`

https://drive.google.com/open?id=1a2JBxpTjYd_K7UhJXkQCYfJfso2jYHiM

about extracting c3d features

is it possible to share your computed c3d features?

thanks in advance.

Dataset

Thank you for your amazing work.
I wonder that which dataset you are using. Did you extract from UCF crime dataset?

Evaluate_anomaly_detector.m- C3D features for videos (.fc file) what's this .fc files

i was trying to run your Evaluate_anomaly_detector.m file but you mentioned there that for C3D_CNN_Path case needed to put .fc files there but how to get that .fc files

and got error like this

ivideo =

 1

Undefined variable "Annotation_file" or class "Annotation_file.VideoName".

Error in Evaluate_Anomaly_Detector_RoadAccident (line 33)
check=strmatch(All_Videos_scores(ivideo).name(1:end-6),Annotation_file.VideoName(1:end-3));

pytube3

Hello, opening this issue to let you know that there is a new, actively maintained, Python3 only pytube fork: https://github.com/hbmartin/pytube3