Road Traversing Knowledge for Surface Classification

This dataset consists of 62.662 labeled images from Brazil's inner country roads captured by a low-cost camera (HP Webcam HD-4110) attached to a moving vehicle. The dataset presents three surface kinds: asphalt, paved and unpaved. There are 43.263, 13.697, and 5.702 images for asphalt, paved, and unpaved classes, respectively.

All images were collected during the daytime in good weather conditions. The frames present lighting variations, shadows, and a few frames with solar glare. Moreover, it is also noticed intra-class variations, such as asphalt surfaces with different color intensities, e.g., older asphalts are usually lighter than the new ones; paved surfaces formed by different patterns, e.g., cobblestone and concrete; and unpaved surfaces, which are naturally uneven.

The directory is organized by subdirectories with the class name, i.e., the surface kind.