mohamedsebaie / fight_detection_from_surveillance_cameras-pytorch_project

Fight Detection From Surveillance Cameras by fine-tuning a PyTorch Pretrained Model

Fight Detection Project

---

Video_app.online-video-cutter.com.mp4

Video_app.online-video-cutter.com.1.mp4

Abstract

Vision-based activity recognition is one of the most challenging research topics of computer vision and pattern recognition. A specific application of it, namely, detecting fights from surveillance cameras in public areas, prisons, etc., is desired, to get violent incidents under control quickly to reduce casualties.

Results

Model	Top-1 Accuracy	Batch Size (Videos)	Input Frames	Recall (Fight)	Inference Rate (Videos/sec)
r2plus1d_18	77.5%	4	16	0.75	10
r3d_18	82.5%	4	16	0.85	10
mc3_18	90%	4	16	0.80	10
mc3_18	92.5%	8	16	0.90	10
mc3_18	85%	4	32	0.90	5.7

Pytorch Pretrained Models

All pretrained models can be found in this link. https://pytorch.org/vision/stable/models.html

Confusion Matrix

Inference

Run the infer.py script and pass the required arguments (modelPath, streaming, inputPath, outputPath, sequenceLength, skip, showInfo)

python -m infer \
--modelPath="./FDSC/models/model_16_m3_0.8888.pth" \
--streaming=False \
--inputPath="./inputTestVideo.mp4" Or Streaming Url in case of streaming = True \
--outputPath="./outputVideo.mp4" \
--sequenceLength=16 \
--skip=2 \
--showInfo=True

Instructions to Install our Fight Detection Package

Our Package can be found in this link. https://pypi.org/project/Fight-Detection/0.0.3/

1. Install:

pip install Fight-Detection==0.0.3
pip install pytube

2. Download Our Finetuned Model Weights:

import gdown
url = 'https://drive.google.com/uc?id=1MWDeLnpEaZDrKK-OjmzvYLxfjwp-GDcp'
output = 'model_16_m3_0.8888.pth'
gdown.download(url, output, quiet=False)

3. Detect Fight or Not by Pass your Local Video:

from fight_detection import Fight_utils
# Run the Below Function by Input your Test Video Path to get the outPut Video with Fight Detection or Not
Fight_utils.fightDetection(inputPath,seq,skip,outputPath,showInfo)

4. Show the Output Video with Detection:

from moviepy.editor import *
VideoFileClip(outputPath, audio=False, target_resolution=(300,None)).ipython_display()

5- Detect the Fight on Streaming:

Fight_utils.start_streaming(streamingURL)

fight_detection_from_surveillance_cameras-pytorch_project's Issues

Problem when Download Finetuned Model Weights

Hello,
Thank for interesting project.
But I can not download Finetuned Model Weights, can you share it again ?
https://drive.google.com/uc?id=1MWDeLnpEaZDrKK-OjmzvYLxfjwp-GDcp
above link is not available anymore, please check.

Thank you!

infer error

when I run the code python -m infer --modelPath="./Models/model_16_m3_0.8888.pth" --streaming=False --inputPath='/mnt/Data/ProjectCode/fightDetection/Fight_Detection_From_Surveillance_Cameras-PyTorch_Project/dataset/fight/fi001.mp4' --outputPath="./outputVideo.mp4" --sequenceLength=16 --skip=2
I get that error:
Traceback (most recent call last): File "/home/dong/.conda/envs/fightDetection/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/dong/.conda/envs/fightDetection/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/mnt/Data/ProjectCode/fightDetection/Fight_Detection_From_Surveillance_Cameras-PyTorch_Project/infer.py", line 35, in <module> main() File "/mnt/Data/ProjectCode/fightDetection/Fight_Detection_From_Surveillance_Cameras-PyTorch_Project/infer.py", line 25, in main start_streaming(model, args.inputPath) File "/mnt/Data/ProjectCode/fightDetection/Fight_Detection_From_Surveillance_Cameras-PyTorch_Project/FDSC/Fight_utils.py", line 461, in start_streaming cv2.imshow("RTSP", frame) cv2.error: OpenCV(4.6.0) /io/opencv/modules/highgui/src/window.cpp:967: error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'imshow'

It seems occurred some error, than no frame return. So get that error. Could you help me to solve it.

Request for Guidance on Fine-Tuning the Model on Custom Datasets

Thank you for sharing this great project! It has been incredibly useful for my work.

I would like to ask if you could provide some guidance or code examples on how to fine-tune the existing model on custom datasets. Specifically, I'm interested in:

Thank you in advance for your help!

permission denied to access google drive link

Access denied with the following error:

Cannot retrieve the public link of the file. You may need to change
the permission to 'Anyone with the link', or have had many accesses. 

You may still be able to access the file from the browser:

 https://drive.google.com/uc?id=1MWDeLnpEaZDrKK-OjmzvYLxfjwp-GDcp 

ModuleNotFoundError: No module named 'FDSC'

I run
python -m infer
--modelPath="./Models/model_16_m3_0.8888.pth"
--streaming=False
--inputPath="./dataset/fight/fi148.mp4"
--outputPath="./outputVideo.mp4"
--sequenceLength=16
--skip=2
--showInfo=True

get this error！