JAKARTA - A number of cross-faculty students at Universitas Gadjah Mada (UGM) have developed a crowd detection system to prevent the transmission of COVID-19. in a written statement in Yogyakarta, Thursday. Zulfa said the system, which is named "Syncrom" or stands for "System of Detection and Crowd Mapping", was made based on Deep Learning and WebGIS. Thus, the tool is able to detect crowds by providing information on the number of people in the crowd. and displays a visualization of conditions in the field, both the time and place where the crowd occurs in "near realtime" (close to realtime). "With this platform the monitoring system can be carried out continuously for 24 hours. Geography of UGM. Syncrom was developed by Zulfa together with the four at his colleagues, namely M. Ihsanur Adib (Cartography and Remote Sensing), Wahyu Afrizal Bahrul Alam (Information Technology), Malik Al-Aminullah Samansya (Nuclear Engineering), and Najmuddin Muntashir 'Abdussalam (Industrial Engineering) under the guidance of Dr. Taufik Hery Purwanto.
The prototype of crowd detection was born through the Student Creativity Program in the Field of Copyright (PKM-KC) in 2021 which received a development grant of Rp. 9 million from the Ministry of Education and Culture. The system, said Zulfa, is also equipped with an early warning feature of crowds. A crowd warning at the detected location will be conveyed through loudspeakers automatically. He explained that Syncrom is able to detect crowds through visual data input obtained via CCTV via a web cam connected to a local computer that has previously been programmed with deep learning to detect human presence and predict crowds. After that, the data results are sent to WebGIS in the form of information related to the location, time, and number of crowd events in one location monitored by CCTV. to give warnings," said Zulfa. Later, they will also add a feature in the form of text alerts to make it easier for officers to monitor. For example, when officers are not in the control room, they can still receive information via SMS or telegram if there is a crowd. "Currently there is no product that integrates crowd detection with mapping which is also accompanied by an early warning. Usually crowd detection using proximity sensors uses user devices such as smart phones," he said. Another researcher, Najmuddin, said that the development of Syncrom started with concerns that there were still many violations of health protocols that occurred in the community, especially regarding social distancing and avoiding crowds. keep your distance and avoid crowds, because the monitoring of the apparatus is not optimal. Therefore, we took the initiative to develop this detection tool to make it easier for officers to monitor and take immediate action," he said. I'm using a web cam, haven't used CCTV yet, due to limited funds. However, the results can monitor the crowd optimally and accurately. The system, which was developed since June 2021, has been tested in the field. As a result, it has an accuracy of more than 75 percent in detecting crowds in a room. "Even with a web cam, it can produce quite good accuracy for detecting crowds with medium and low image resolutions. However, in the future, high resolution CCTV will be developed so that results could be more accurate," he said.
The English, Chinese, Japanese, Arabic, and French versions are automatically generated by the AI. So there may still be inaccuracies in translating, please always see Indonesian as our main language. (system supported by DigitalSiber.id)
