Host: Japanese Society for the Science of Design
The most common walking aids used by the visually impaired people are white canes and guide dogs. However, neither of these can be used to walk safely. In this study, we proposed a method for detecting moving objects using template matching in a small and lightweight camera device to create a walking support system for visually impaired people. By using template matching, it is possible to detect moving objects without shaking caused by the action of walking, without using machine learning or optical flow. The experimental results showed that the proposed method can detect moving objects even with a shaking camera device by setting the similarity.
