Robust Stereo Feature Descriptor for Visual Odometry
This work addresses the challenge of robust feature matching in visual odometry for applications like autonomous driving, though it is incremental as it builds on existing descriptors like SIFT and FREAK.
The paper tackles the problem of improving feature descriptors for visual odometry by leveraging stereo camera data to estimate feature scale, making descriptors more robust to scale changes without significant computational overhead. The method improves SIFT by 8.75% and FREAK by 28.65% in feature tracking, and using stereo FREAK increases inlier matches by 19% and visual odometry accuracy by 23% on the KITTI dataset.
In this paper, we propose a simple way to utilize stereo camera data to improve feature descriptors. Computer vision algorithms that use a stereo camera require some calculations of 3D information. We leverage this pre-calculated information to improve feature descriptor algorithms. We use the 3D feature information to estimate the scale of each feature. This way, each feature descriptor will be more robust to scale change without significant computations. In addition, we use stereo images to construct the descriptor vector. The Scale-Invariant Feature Transform (SIFT) and Fast Retina Keypoint (FREAK) descriptors are used to evaluate the proposed method. The scale normalization technique in feature tracking test improves the standard SIFT by 8.75% and improves the standard FREAK by 28.65%. Using the proposed stereo feature descriptor, a visual odometry algorithm is designed and tested on the KITTI dataset. The stereo FREAK descriptor raises the number of inlier matches by 19% and consequently improves the accuracy of visual odometry by 23%.