Nanyang Technological University, Singapore
It is my honor to be the editor-in-chief of IJEETC. The journal publishes good papers which focous on the advanced researches in the field of electrical and electronic engineering & telecommunications.
Abstract—A process to receive raw materials from suppliers in an animal feed industry utilizes both automatic and semi-automatic machine control systems. The process called “truck dumper system” is the procedure that the suppliers provide raw materials carried by trucks; then, their tailgates open, and the raw materials are discharged by raising front end part of a truck to gather raw materials in a collection area. In general, the truck dumper system has been controlled manually by staff in a control room, not by a truck driver. However, serious accidents may occur during the process because when the dumper lifts up, the staff's vision has been blocked by the raised part of a truck. Therefore, if the staff controls the dumper to lift down by lacking safety awareness, people in the restricted area can be endangered. In this study, we proposed a framework of automatic human detection to prevent any accident that may occur from the truck dumper in the restricted area. The human detection model was developed to detect humans possibly in different blind corners that are difficult for staff in a control room to monitor these unseen areas for safety-awareness. The main technology of the proposed framework was the real-time human detection with fully convolutional neural network architecture called You Only Look Once, or YOLO. The framework has been designed to send a signal to terminate the truck dumper system immediately after the model detects people in the restricted area. In experiments, we discovered that the model could detect a human in all blind corners, including the corners that the staff's sight was completely bloacked by some barriers. The overall efficiency of this framework in an aspect of speed was high. The average time to process per image was 397 milliseconds by using CPUs and only 52 milliseconds by using GPUs. The results also showed that the model was effectively applicable to detect human in real-time due to its high-speed process.
Copyright © 2012-2021. International Journal of Electrical and Electronic Engineering & Telecommunications, All Rights Reserved