A Stereo Algorithm for Thin Obstacles and Reflective Objects
This addresses a critical safety issue for outdoor lightweight, low-cost robotics by improving obstacle avoidance, though it is incremental as it builds on existing stereo methods with new hardware and algorithmic tweaks.
The paper tackled the problem of stereo cameras failing to sense thin and reflective objects in outdoor robotics by introducing a trinocular setup with a micropolarizer camera and a hierarchical disparity algorithm, resulting in a reduction of bad pixels from 18.4% to 9.27% for reflective objects and an increase in wire pixel detection from 5% to 53%.
Stereo cameras are a popular choice for obstacle avoidance for outdoor lighweight, low-cost robotics applications. However, they are unable to sense thin and reflective objects well. Currently, many algorithms are tuned to perform well on indoor scenes like the Middlebury dataset. When navigating outdoors, reflective objects, like windows and glass, and thin obstacles, like wires, are not well handled by most stereo disparity algorithms. Reflections, repeating patterns and objects parallel to the cameras' baseline causes mismatches between image pairs which leads to bad disparity estimates. Thin obstacles are difficult for many sliding window based disparity methods to detect because they do not take up large portions of the pixels in the sliding window. We use a trinocular camera setup and micropolarizer camera capable of detecting reflective objects to overcome these issues. We present a hierarchical disparity algorithm that reduces noise, separately identify wires using semantic object triangulation in three images, and use information about the polarization of light to estimate the disparity of reflective objects. We evaluate our approach on outdoor data that we collected. Our method contained an average of 9.27% of bad pixels compared to a typical stereo algorithm's 18.4% of bad pixels in scenes containing reflective objects. Our trinocular and semantic wire disparity methods detected 53% of wire pixels, whereas a typical two camera stereo algorithm detected 5%.