Local binary feature based on census transform for mobile robot

This paper presents a very simple descriptor for local image feature that is detected by DOB (Difference of Boxes) proposed in CenSurE. Image feature is often used to navigate a mobile robot, and some methods that are robust for scale and illumination changes are developed such as SIFT and CenSurE. However these descriptors still has heavy computation, and to use them is a big burden for some computers of low specification. Therefore we proposed a simple feature descriptor that is strong for several changes such as illumination change based on census transform. As experimental results, the proposal method has strength for some image changes, furthermore it has a high robustness for illumination change.