In some complex circumstances, the detection of conflagration mostly depends on smog detectors, which have lots of limitations in precision, efficiency and safety. If we make full use of object detection algorithms to detect the flame in industries, it will benefit people’s safety obviously. Among all kinds of object detection algorithms, YOLO series play a very significant role. In this paper, we propose an improving strategy on YOLOv4 to enhance its precision based on multi-scale feature maps. Firstly, we create flame datasets including almost 4000 high-resolution flame pictures. Secondly, some improvements on feature extraction network are made to detect smaller objects. Finally, the total algorithm are trained and tested on our datasets for about 400 epochs. The result show that the method can generate high quality on flame detection in a great number of situations.

No abstract

No abstract

Nowadays, remote control applications via theInternet are going to be used more and more widely with the development of powerful chips and network technology. For applications which do not need realtime communication or persistent connection and have a little amount of data transportation, conventional approaches based on Web services either are a little bit complex, or have a higher overhead. In this paper we introduce another method called WeeRMES, a Web services based email extension for remote monitoring of embedded systems, to be supplement of conventional remote control methods in some special occasions. Thanks to the model, we are able to do all those things using emails such as sending devices instructions, inspecting device status and gathering data using XML capsulated messages. User interfaces can be dynamically achieved by means of XForms generated by Java classes loaded on target devices. Furthermore, researches are carried out on security mechanism to ensure safety and robustness of the system. An idiographic implementation is given as an example in the end.

No abstract