Smart Future City Laboratory

Deep on Edge: Damaged Road Markings Detection on Automotive Video with Convolutional Neural Networks

Person in Charge of the Project : Makoto KawanoCity infrastructures, such as roads, are elements of great importance in urban lives. Roads require constant inspection and repair due to deterioration, but it is expensive to do so with manual labor. Therefore, these works should be done automatically so that the cost of inspecting or repairing becomes cheap. While there are several works to address these road issues, our study focuses on detecting damaged road markings from automotive videos. Since our proposed system is implemented on an edge computer, it is easy to attach our system to vehicles. Our model, which we call Deep on Edge (DoE), is a deep convolutional neural networks that detect damaged road markings from high frame rates video.

Jikkyolizer: Effective and Intuitive Auralization

Person in Charge of the Project : Yoshiyuki InoueIn this research, I search for the effective auralization. While a variety of information presentation method exists, auralization is the method that the receiver can receive information passively. For example, in this situation, although auralization is prior to another information presentation method, auraliation has the feature of decreasing the value of conveyed information and difficult to convey information sensuously. So, I adopt methods to define auralization function to sort raw data in important order and devise methods to make auralization corresponding to the function. And in these way, I search for an intuitive auralization method.