Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch Invariance
Binary feature descriptors have been widely used in various visual measurement tasks, particularly those with limited computing resources and storage capacities. Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations. It can be observed that when image illumination changes dramatically, the relative relationship among local patches mostly remains intact. Based on the observation, consequently, this study presents an illumination-insensitive binary (IIB) descriptor by leveraging the local inter-patch invariance exhibited in multiple spatial granularities to deal with unfavorable illumination variations. By taking advantage of integral images for local patch feature computation, a highly efficient IIB descriptor is achieved. It can encode scalable features in multiple spatial granularities, thus facilitating a computationally efficient hierarchical matching from coarse to fine. Moreover, the IIB descriptor can also apply to other types of image data, such as depth maps and semantic segmentation results, when available in some applications. Numerical experiments on both natural and synthetic datasets reveal that the proposed IIB descriptor outperforms state-of-the-art binary descriptors and some testing float descriptors. The proposed IIB descriptor has also been successfully employed in a demo system for long-term visual localization. The code of the IIB descriptor will be publicly available.
Code (1)
Tasks
Semantic SegmentationVisual LocalizationSimilar Papers 제목 키워드 기반
FWLBP: A Scale Invariant Descriptor for Texture Classification
In this paper we propose a novel texture descriptor called Fractal Weighted Local Binary Pattern (FWLBP). The fractal dimension (FD) measure is relatively invariant to scale-changes, and presents a good correlation with …
ClassificationGeneral ClassificationTexture ClassificationBoosting Binary Keypoint Descriptors
Binary keypoint descriptors provide an efficient alternative to their floating-point competitors as they enable faster processing while requiring less memory. In this paper, we propose a novel framework to learn an extre…
Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization
Many robotics applications require precise pose estimates despite operating in large and changing environments. This can be addressed by visual localization, using a pre-computed 3D model of the surroundings. The pose es…
Pose EstimationVisual LocalizationFeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints as the input, and uses an MLP-based self-…
GPUVisual LocalizationBit-Planes: Dense Subpixel Alignment of Binary Descriptors
Binary descriptors have been instrumental in the recent evolution of computationally efficient sparse image alignment algorithms. Increasingly, however, the vision community is interested in dense image alignment methods…