• Saloni Patil
• Abhilasha Kulkarni
• Nikita Modi
• Sourabh Pawar
• Nikhil Thatte

In the Development of an Edge Agent for Video Analytics to be used in Video Monitoring (VIMO) Application we have implemented two main modules. They are detection on a Region of Interest (ROI) and Integrated Detection. In Region of Interest, we have selected two regions and applied Person Detection on one region and Car Detection on the other region. Alerts are generated as soon as person or car is detected. Integrated detection includes integration of Face Detection, Object Detection and Motion Detection. When any detection occurs, a Output.avi file is generated which includes recording of real time detection results. Once the detection is completed, a JSON file containing the details of detection including timestamp, the event occurred, coordinates, the object detected is generated. These result files are uploaded on S3 (Simple Storage Service offered by Amazon AWS) using Message Queuing Telemetry Transport (MQTT) protocol. We can implement this application using a Webcam or a CCTV Camera connected to the same network as the host on which the application is running.

Video Analytics, Video Monitoring, Tkinter, ROI, MQTT

"Development of an Edge Agent for Video Analytics to be used in Video Monitoring(VIMO) Applications", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.500-506, May-2019, Available :http://www.jetir.org/papers/JETIR1905F75.pdf

"Development of an Edge Agent for Video Analytics to be used in Video Monitoring(VIMO) Applications", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp500-506, May-2019, Available at : http://www.jetir.org/papers/JETIR1905F75.pdf