Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, we present the development of an algorithm for sidewalk following for a mobile robot. The algorithm classifies pixels of a video frame as either sidewalk or background. The classification of pixels is performed using color histograms of the hue and saturation of various areas of an image taken by an on-board camera. This color histogram approach allows the algorithm to detect and follow concrete paved areas of arbitrary shape and color. The development of the algorithm is performed using a robotics research platform developed by undergraduate students at Cal Poly State University, San Luis Obispo.