Saket * Call Girls in Delhi - Phone 9711199012 Escorts Service at 6k to 50k a...
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and (3).pptx
1. VACHANA PITAMAHA Dr. P.G. HALAKATTI COLLEGE OF ENGINEERING &
TECHNOLOGY,VIJAYAPUR-586103
Department of Computer Since and Engineering
Final Year Project Demo on
Monitoring Pandemic Precautionary Protocols using Real-time
Surveillance and Artificial Intelligence
Guided by:
Prof. Santosh Chinchali
Submitted by:
Kunal Porwal (2BL16CS033)
Kiran Ambali
(2BL16CS030)
Niranjan Patil (2BL17CS041)
Nikhil
2. Introduction
• The worst possible situation faced by humanity, COVID-19, is proliferating across more than 180 countries and about 37,000,000
confirmed cases, along with 1,000,000 deaths worldwide as of October 2020. The absence of any medical and strategic expertise is
a colossal problem, and lack of immunity against it increases the risk of being affected by the virus. Since the absence of a vaccine
is an issue, social spacing and face covering are primary precautionary methods apt in this situation. This project proposes
automation with a deep learning framework for monitoring social distancing using surveillance video footage and face mask
detection in public and crowded places as a mandatory rule set for pandemic terms using computer vision. The project proposes a
framework is based on YOLO object detection model to define the background and human beings with bounding boxes and
assigned Identifications. In the same framework, a trained module checks for any unmasked individual. The automation will give
useful data and understanding for the pandemic’s current evaluation; this data will help analyze the individuals who do not follow
health protocol norms.
3. Literature Survey
S
.
N
O
TITLE AUTHOR METHOD
OLOGIES
USED
LIMITATION
1 Face detection
techniques: a review
A. Kumar, A.
Kaur, and M.
Kumar
K-NN It is used the face features like eyes, nose,
ears so it will detect only the face.
If you hide your eyes/nose this system won’t
recognize/ detect face.
2 Rational use of face
masks in the covid-19
pandemic
S. Feng, C. Shen,
N. Xia, W. Song,
M. Fan, and B. J.
Cowling
- In the above paper we have studied about why
mask is important for the people to protect from
the corona virus.
4. Literature Survey
S
.
N
O
TITLE AUTHOR METHODOLOGIE
S USED
LIMITATION
3 Masked face recognition
dataset and application
Z. Wang, G.
Wang, B. Huang,
Z. Xiong, Q.
Hong, H. Wu, P.
Yi, K. Jiang, N.
Wang, Y. Pei et
al.
Multi-granularity
masked face
recognition
model
It is limited to detecting all types of
masks.
4 Detect faces and
determine whether
people are wearing mask
D. Chiang., Faster R-CNN It works only for saved images lively
we can’t detect the masks.
It takes longer time to train the model.
5 Object detection with
deep learning: A review
Z.-Q. Zhao, P.
Zheng, S.-t. Xu,
and X. Wu
Yolo v2 We can only one object. It doesn’t
support for face detection.
5. PROBLEM DEFINITION
• A report from the World Health Organization (WHO) presented that
coronavirus disease (COVID-19) has globally infected millions of people and
caused deaths on a large scale.
• This virus was initially taken into account in December in Wuhan, and later
it was found it had spread across 216 countries, declared this as a
pandemic.
• Many healthcare facilities, medical experts, and scientists are in the
process of creating medicines or a vaccine for this deadly virus. However,
to date, the development processes are in the latter stages, but they are
still not sure of the effect caused by this unknown virus.
• Making the countries stop practicing their daily activities on which their
livelihoods depend, leads to a severe economic crisis during the pandemic
period. We have to be avoid spreading of those virus.
6. PROBLEM DEFINITION
• The worst possible situation faced by humanity, COVID-19, is
proliferating across more than 180 countries and about 37,000,000
confirmed cases, along with 1,000,000 deaths worldwide as of
October 2020. The absence of any medical and strategic expertise is a
colossal problem, and lack of immunity against it increases the risk of
being affected by the virus. Since the absence of a vaccine is an issue,
lot of people gets infected by this virus.
7. WORK CARRIED OUT
• A) Designed Methodology/algorithm
• B) Timeline of the project completion
• C) Implementation
• D)Result
8. Designed Methodology
• We are using the Yolov3 to detect the persons in the current frame.
• We are using the Euclidean distance calculation formula to calculate
the social distancing between the one person to other.
• We are using the MobileNet V2 to classify person wearing mask or
not.
10. Designed Methodology-MobileNet v2
We build our Sequential CNN model with various layers such as
Conv2D, MaxPooling2D, Flatten, Dropout and Dense. In the last Dense
layer, we use the ‘softmax’ function to output a vector that gives the
probability of each of the two classes. Here, we use the ‘adam’
optimizer and ‘binary_crossentropy’ as our loss function as there are
only two classes. We are using the MobileNetV2 for better accuracy.
11. Designed Methodology-YOLO v3
• The YOLO algorithm works by dividing the image into N grids, each having
an equal dimensional region of SxS. Each of these N grids is responsible for
the detection and localization of the object it contains.
• Correspondingly, these grids predict B bounding box coordinates relative to
their cell coordinates, along with the object label and probability of the
object being present in the cell.
12. Project Planning - Gantt Chart
Oct
15
Dec
10
Jan
10
Mar
10
Apr
15
May
15
Jun
25
Jun
26
Jun
30
Jul
1
Planning phase
Literature survey
Analysis phase
Design phase
Implementation
Testing
Deployment
Documentation
Report
13. IMPLEMENTATION
• We are developing this project with the following modules.
• Dataset Collection
• Building the Mobilenetv2 Model and YoloV3 model.
• Training
• Detection of face mask and social distancing violation.
• Work done till now
• We have collected face mask dataset and coco object dataset, and we have built and
trained the yolov3 and mobilenet v2 model to detect the violations in pandemic
precautionary protocols.
• Future work:
• We are planning to build a desktop application to integrate the both the model to
monitor violations in pandemic precautionary protocols in real time.
19. CONCLUSION
• The system works great, but it required some effort to overcome
some challenges. For Social distancing framework, the calibration of
the model by simulating a 3D depth factor based on the camera
position and orientation gives better analysis. For Face mask
detection small faces were hard to detect and even harder to track
hence using pose estimation, which is using the body to estimate the
head bounding box and using facial key points instead if they are
visible.
20. References
• [1] WHO (2020). “Advice for the public on COVID-19”. Retrieved August 2, 2020, from https://www.who.int/emergencies/diseases/novelcoronavirus-
2019/advice-for-public.
• [2] Pahuja, R. (2020, June 26). “How AI is helping maintain social distance at Indian factories”. Economic Times. Retrieved 2020, from
https://cio.economictimes.indiatimes.com/news/strategy-andmanagement/how-ai-is-helping-maintain-social-distance-at-indianfactories/76636929.
• [3] 3. Suma, V. “Computer Vision for Human-Machine InteractionReview.” Journal of trends in Computer Science and Smart technology (TCSST) 1, no.
02 (2019): 131-139.
• [4] Dhaya, R. “Deep Net Model for Detection of Covid-19 using Radiographs based on ROC Analysis.” Journal of Innovative Image Processing (JIIP) 2,
no. 03 (2020): 135-140.
• [5] J. Dhamija, T. Choudhury, P. Kumar and Y. S. Rathore, “An Advancement towards Efficient Face Recognition Using Live Video Feed: “For the Future”,”
2017 3rd International Conference on Computational Intelligence and Networks (CINE), Odisha, 2017, pp. 53- 56, doi: 10.1109/CINE.2017.21.
• [6] L. Koraqi and F. Idrizi, “Detection, identification and tracking of objects during the motion”, 2019 3rd International Symposium on Multidisciplinary
Studies and Innovative Technologies (ISMSIT), Ankara, Turkey, 2019, pp. 1-6, doi: 10.1109/ISMSIT.2019.8932833.
• [7] Redmon, J., & Farhadi, A. (2018). “YOLOv3: An Incremental Improvement”. ArXiv. Retrieved 2020, from https://pjreddie.com/darknet/yolo
• [8] Pias, P., “Object detection and distance measurement,” https://github.com/paul-pias/Object-Detection-and-DistanceMeasurement, 2020, [Online;
accessed 01-August-2020].
• [9] G. Deore, R. Bodhula, V. Udpikar and V. More, “Study of masked face detection approach in video analytics,”2016 Conference on Advances in Signal
Processing (CASP), Pune, 2016, pp. 196-200, doi: 10.1109/CASP.2016.7746164.
• [10]Singhal, M. (2020, July 07). Object Detection using SSD MobilenetV2 using Tensorflow API : Can detect any single class from... Retrieved from
https://medium.com/@techmayank2000/object-detection-usingssd-mobilenetv2-using-tensorflow-api-can-detect-any-single-class-
from31a31bbd0691.