TY - GEN
T1 - Compact environment-invariant codes for robust visual place recognition
AU - Jain, Unnat
AU - Namboodiri, Vinay P.
AU - Pandey, Gaurav
PY - 2018/2/7
Y1 - 2018/2/7
N2 - Robust visual place recognition (VPR) requires scene representations that are invariant to various environmental challenges such as seasonal changes and variations due to ambient lighting conditions during day and night. Moreover, a practical VPR system necessitates compact representations of environmental features. To satisfy these requirements, in this paper we suggest a modification to the existing pipeline of VPR systems to incorporate supervised hashing. The modified system learns (in a supervised setting) compact binary codes from image feature descriptors. These binary codes imbibe robustness to the visual variations exposed to it during the training phase, thereby, making the system adaptive to severe environmental changes. Also, incorporating supervised hashing makes VPR computationally more efficient and easy to implement on simple hardware. This is because binary embeddings can be learned over simple-to-compute features and the distance computation is also in the low dimensional hamming space of binary codes. We have performed experiments on several challenging data sets covering seasonal, illumination and viewpoint variations. We also compare two widely used supervised hashing methods of CCAITQ [1] and MLH [1] and show that this new pipeline out-performs or closely matches the state-of-the-art deep learning VPR methods that are based on high-dimensional features extracted from pre-trained deep convolutional neural networks.
AB - Robust visual place recognition (VPR) requires scene representations that are invariant to various environmental challenges such as seasonal changes and variations due to ambient lighting conditions during day and night. Moreover, a practical VPR system necessitates compact representations of environmental features. To satisfy these requirements, in this paper we suggest a modification to the existing pipeline of VPR systems to incorporate supervised hashing. The modified system learns (in a supervised setting) compact binary codes from image feature descriptors. These binary codes imbibe robustness to the visual variations exposed to it during the training phase, thereby, making the system adaptive to severe environmental changes. Also, incorporating supervised hashing makes VPR computationally more efficient and easy to implement on simple hardware. This is because binary embeddings can be learned over simple-to-compute features and the distance computation is also in the low dimensional hamming space of binary codes. We have performed experiments on several challenging data sets covering seasonal, illumination and viewpoint variations. We also compare two widely used supervised hashing methods of CCAITQ [1] and MLH [1] and show that this new pipeline out-performs or closely matches the state-of-the-art deep learning VPR methods that are based on high-dimensional features extracted from pre-trained deep convolutional neural networks.
KW - convolutional neural network
KW - dynamic time warping
KW - hashing
KW - similarity learning
KW - visual place recognition
UR - http://www.scopus.com/inward/record.url?scp=85048053758&partnerID=8YFLogxK
U2 - 10.1109/CRV.2017.22
DO - 10.1109/CRV.2017.22
M3 - Chapter in a published conference proceeding
AN - SCOPUS:85048053758
T3 - Proceedings - 2017 14th Conference on Computer and Robot Vision, CRV 2017
SP - 40
EP - 47
BT - Proceedings - 2017 14th Conference on Computer and Robot Vision, CRV 2017
PB - IEEE
T2 - 14th Conference on Computer and Robot Vision, CRV 2017
Y2 - 17 May 2017 through 19 May 2017
ER -