IFTD: Image Feature Triangle Descriptor for Loop Detection in Driving Scenes
In this work, we propose a fast and robust Image Feature Triangle Descriptor (IFTD) based on the STD method, aimed at improving the efficiency and accuracy of place recognition in driving scenarios. We extract keypoints from BEV projection image of point cloud and construct these keypoints into triangle descriptors. By matching these feature triangles, we achieved precise place recognition and calculated the 4-DOF pose estimation between two keyframes. Furthermore, we employ image similarity inspection to perform the final place recognition. Experimental results on three public datasets demonstrate that our IFTD can achieve greater robustness and accuracy than state-of-the-art methods with low computational overhead.
Code (1)
Tasks
Pose EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LiftPool: Bidirectional ConvNet Pooling
Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a loss…
image-classificationImage ClassificationImage-to-Image TranslationPhilosophy+2SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules
Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with va…
Image GenerationDualQuat-LOAM: LiDAR Odometry and Mapping parameterized on Dual Quaternions
Mobile robotics is increasingly in need of low bias and computationally efficient odometry methods. In response to this need, we present a LiDAR odometry estimation approach by fully parameterizing the system using dual …
Pose EstimationRE-TRIP : Reflectivity Instance Augmented Triangle Descriptor for 3D Place Recognition
While most people associate LiDAR primarily with its ability to measure distances and provide geometric information about the environment (via point clouds), LiDAR also captures additional data, including reflectivity or…
3D Place RecognitionInstance SegmentationSemantic SegmentationSTD: Stable Triangle Descriptor for 3D place recognition
In this work, we present a novel global descriptor termed stable triangle descriptor (STD) for 3D place recognition. For a triangle, its shape is uniquely determined by the length of the sides or included angles. Moreove…
3D Place Recognition