Adaptive Soft Encoding: A General Unsupervised Feature Aggregation Method for Place Recognition

Adaptive Soft Encoding: A General Unsupervised Feature Aggregation Method for Place Recognition

Abstract

Place recognition (PR) is an important problem in environment perception, which can help simultaneous localization and mapping (SLAM), as well as scene understanding of mobile robots. For PR, feature aggregation plays an important role in the representation of environments. In this article, an adaptive soft encoding (ASE) method is proposed for aggregating numerous features into low-dimensional feature vectors, which includes a training phase and an encoding phase. For the training phase, the information along each dimension of the features is evaluated, which is further employed to assign all dimensions into different subdimensional intervals. After that, subdimensional Gaussian mixture models (SD-GMMs) are fit by features in the subdimensional intervals and organized into an ASE tree, of which the tree nodes hierarchically store the parameters of the SD-GMMs to reflect the distribution of the features. For the encoding phase, features are fed into the root node of the ASE tree. The weight of each node is calculated from top to bottom to generate multiple aggregated feature vectors with different description capabilities. In addition, an ASE-based framework for PR is proposed, in which local descriptors are extracted from sensor data (e.g., images or LiDAR data), and then aggregated into global descriptors by ASE. Finally, owing to the hierarchical structure of the ASE tree, a hierarchical matching strategy of the global descriptors is designed to recognize places efficiently. Experimental results demonstrate that feature vectors aggregated by ASE have strong distinguishability, and the ASE-based PR method achieves good accuracy and efficiency. The code of ASE can be accessed at https://github.com/wdyiwdwd/ASE-Encoder.

Code

• ASE-Encoder

Recommended citation: Y. Gong, J. Yuan, F. Sun, Q. Sun, W. Zhu and X. Zhang, "Adaptive Soft Encoding: A General Unsupervised Feature Aggregation Method for Place Recognition," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-15, 2023. http://wdyiwdwd.github.io/files/ASE-Encoder.pdf