Affiliation:
1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China
2. Institute of Intelligent Control and Robotics (IICR), Nanjing Forestry University, Nanjing 210037, China
Abstract
In dynamic environments, convolutional neural networks (CNNs) often produce image feature maps with significant redundancy due to external factors such as moving objects and occlusions. These feature maps are inadequate as precise image descriptors for similarity measurement, hindering loop closure detection. Addressing this issue, this paper proposes feature compression of convolutional neural network output. The approach is detailed as follows: (1) employing ResNet152 as the backbone feature-extraction network, a Siamese neural network is constructed to enhance the efficiency of feature extraction; (2) utilizing KL transformation to extract principal components from the backbone network’s output, thereby eliminating redundant information; (3) employing the compressed features as input for NetVLAD to construct a spatially informed feature descriptor for similarity measurement. Experimental results demonstrate that, on the New College dataset, the proposed improved method exhibits an approximately 9.98% enhancement in average accuracy compared to the original network. On the City Center dataset, there is an improvement of approximately 2.64%, with an overall increase of about 23.51% in time performance. These findings indicate that the enhanced ResNet152 performs better than the original network in environments with more moving objects and occlusions.
Funder
National Special Research Fund for Non-profit Sector
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference41 articles.
1. MonoSLAM: Real-time single camera SLAM;Davison;IEEE Trans. Pattern Anal. Mach. Intell.,2007
2. Past, present and future of simultaneous localization and mapping: Toward the robust-perception age;Cadena;IEEE Trans. Robot.,2016
3. Chatial, R., and Laumond, J.P. (1985, January 25–28). Position referencing and consistent world modeling for mobile robots. Proceedings of the IEEE International Conference on Robotics and Automation, St. Louis, MO, USA.
4. Research on SLAM Algorithm of Mobile Robot Based on the Fusion of 2D LiDAR and Depth Camera;Lili;IEEE Access,2020
5. A Survey on Deep Visual Place Recognition;Masone;IEEE Access,2021