Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments
Shuo Wang, Xudong Lv, Xiaomin Liu, Dong Ye
Abstract
Detecting loop closures in dynamic environments is a severe challenge for the simultaneous localization and mapping (SLAM) system. Convolutional neural networks (ConvNet) could provide high-level and abstract representations extracted directly from images as image descriptors. Some novel ConvNet-based methods have been presented. In dynamic environments, they perform better than the state-of-the-art methods which use hand-crafted features. In this paper, (1) We proposed a flexible loop closure detection workflow based on the holistic representations; (2) In this workflow, a post-processing method is applied to the raw holistic ConvNet representations for redundant information compression; (3) In addition, a compression ratio is introduced in (2) to determine how much information will be retained depending on background change and moving objects. We evaluated our workflow in four open datasets. The experimental results demonstrate that the proposed workflow performs better than many state-of-the-art methods and ConvNet-based approaches.