Robust place recognition based on salient landmarks screening and convolutional neural network features

International Journal of Advanced Robotic Systems

article

Jie Niu¹  Kun Qian² 

[1] School of Electronic Engineering, Changzhou College of Information Technology;School of Automation, Southeast University

关键词: Saliency map;    visual place recognition;    CNN features;    Siamese network;    changing environment;   

DOI  :  10.1177/1729881420966966

学科分类：社会科学、人文和艺术（综合）

来源: InTech

【 摘 要 】

In this work, we propose a robust place recognition measurement in natural environments based on salient landmark screening and convolutional neural network (CNN) features. First, the salient objects in the image are segmented as candidate landmarks. Then, a category screening network is designed to remove specific object types that are not suitable for environmental modeling. Finally, a three-layer CNN is used to get highly representative features of the salient landmarks. In the similarity measurement, a Siamese network is chosen to calculate the similarity between images. Experiments were conducted on three challenging benchmark place recognition datasets and superior performance was achieved compared to other state-of-the-art methods, including FABMAP, SeqSLAM, SeqCNNSLAM, and PlaceCNN. Our method obtains the best results on the precision–recall curves, and the average precision reaches 78.43%, which is the best of the comparison methods. This demonstrates that the CNN features on the screened salient landmarks can be against a strong viewpoint and condition variations.

【 授权许可】

CC BY