Outdoor Social Distancing Violation System Detection Using YOLO Algorithm

The government issued orders to implement social distancing or physical distancing. Social distancing is a method of maintaining a distance of at least one meter from other people. This is useful for reducing/preventing disease transmission (virus) and reducing the chain of the spread of covid-19. So the hospital can provide optimal service. For this reason, this research is structured to create a system that can detect violations of social distancing in an open place. This system uses the You Only Look Once (YOLO) algorithm. The developed system uses a pre-Trained Yolov4 model to detect 80 object classes. Testing of this system is carried out based on several scenarios. The system is programmed using Python, with tools for coding Microsoft Visual Studio Code and Anaconda. The best result from creating the detection mode is obtained from a dataset ratio of 90% train data and 10% test data, with the mean average precision results obtained being 54.11%. © 2022 IEEE.

Outdoor Social Distancing Violation Detection System using Faster R-CNN Algorithm

The implementation of social distancing at this time is essential because of the increasingly widespread cases of Covid-19. One of the easy and effective ways to break the chain of Covid-19 spread is by implementing social distancing. This research will discuss the design and implementation of social distancing detection. This detection will take a picture of the person caught on camera and then analyze whether they are doing social distancing. Detection of social distancing can be done in real-time. The Faster Region-based Convolutional Neural Network (Faster R-CNN) method is used to detect human objects, and the Euclidean Distance method is used to calculate human distance. The result of this research is that the system will detect humans caught on camera using models with 80% for training data and 20% testing data partitions, epoch 7000, learning rate 0.0004, and num steps 21000. The accuracy obtained using the Faster Region-based Convolutional Neural Network (Faster R-CNN) method reached 96.90%, a precision value of 97.81%, and a recall value of 98.67% obtained from confusion matrix calculations performed on datasets. The accuracy of social distancing tests obtained in CCTV scenarios was 82.35%, and in parallel scenarios was 86.66%. © 2022 IEEE.