Visual place recognition is an important issue in both computer vision and robotics. Changes in image content caused by viewpoint changes in natural scenes still pose a challenge to location recognition. To solve this problem, a novel feature reorganization method based on location clustering is proposed. Firstly, a general pyramid expansion scheme is extracted based on histogram features, called PyramidVLAD. To maximize the effect of the new function, the similarity is evaluated by clustering images with a certain threshold into same location. Extensive experiments have been conducted to verify the effectiveness of the proposed method using Pyramid VLAD to compare with the best method, APANet. These two datasets achieve improvements of 1.02 and 2.54 percent points in Recall@1, respectively. The results show that this method can consistently obtain better performance than the state-of-the-art methods on the two standard place recognition benchmarks.
YEHaifeng, ZHAOYuchen. Algorithm of signboard representing place in visual position recognition[J].Journal of Chinese Computer Systems, 2021, 42(4): 823-828. (in Chinese)
WANGHongjun, HAOJinlong, ZHAOHui, et al. Visual position recognition technology in large-scaleurban environment[J].Computer Applications and Software, 2021, 38(8): 194-198. (in Chinese)
[7]
ZAFFARM, GARGS, MILFORDM, et al. An open-source visual place recognition evaluation framework with quantifiable viewpoint and appearance change[J]. International Journal of Computer Vision, 2021, 129(7): 2136-2174.
ZHANGWenchi, CHENLihui, WUWei, et al. Traffic sign recognition based on feature fusion of convolutional neural networks[J]. Journal of Computer Applications, 2019, 39(S1): 21-25. (in Chinese)
[10]
LIT, MEIT, KWEONI S, et al. Contextual bag-of-words for visual categorization[J].IEEE Transactions on Circuits & Systems for Video Technology, 2011, 21(4): 381-392.
ZHUXiaobo, CHEJin. Multi-feature subspace person re-identification based on BOW model[J]. Computer Engineering and Applications, 2019, 55(18): 146-150. (in Chinese)
[13]
BHUVANESWARIN R, KUMARV G S.A multi feature fusion based image classifi cation using multi-class support vector machine[J]. International Journal of Control Theory and Applications, 2016, 9(36): 551-559.
[14]
ÖZDEMIRA, SCERRIM, BARRONA B, et al. EchVPR: echo state networks for visual place recognition[J].IEEE Robotics and Automation Letters, 2022, 7(2): 4520-4527.
[15]
HAUSLERS, JACOBSONA, MILFORDM. Multi-process fusion: visual place recognition using multiple image processing methods[J]. IEEE Robotics and Automation Letters, 2019, 4(2): 1924-1931.
[16]
GONGQ, LIUY, ZHANGL, et al.Ghost-dil-NetVLAD: a lightweight neural network for visual place recognition[J/OL].[2024-03-12]. arXiv:2112.11679.
[17]
CHAITANYAK J, CRISTIANB, SIMONV M, et al. On the expressive power of geometric graph neural networks[C]//Proceedings of the 40th International Conference on Machine Learning (ICML), 2022, 202: 15330-15355.
[18]
CHENW, LIUY, WANGW, et al. Deep learning for instance retrieval: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(6): 7270-7292.
[19]
HANK, WANGY H, GUOJ Y, et al. Vision GNN: an image is worth graph of nodes: a survey [J]. Neural Information Processing Systems, 2022, 35(4): 1-15.
JIADi, ZHUNingdan, YANGNinghua, et al. Image matching methods[J]. Journal of Image and Graphits, 2019, 24(5): 677-699. (in Chinese)
[22]
CHENY, GANW, JIAOS, et al.Salient feature selection for CNN-based visual place recognition[J].IEICE Transactions on Information and Systems, 2018, 101(12): 3102- 3107.
[23]
FRIEDMANJ, HASTIET, TIBSHIRANIR.Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors)[J].The Annals of Statistics, 2000, 28(2): 337-374.
[24]
TORIIA, SIVICJ, PAJDLAT, et al. Visual place recognition with repetitive structures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (11): 2346-2359.
[25]
ARANDJELOVICR, GRONATP, TORIIA, et al. Netvlad: CNN architecture for weakly supervised place recognition[J].IEEE Transactions on Ransactions Pattern Analysis and Machine Intelligence, 2018, 40 (6): 1437-1451.
[26]
LOWRYS, SÜNDERHAUFN, NEWMANP, et al. Visual place recognition: a survey[J]. IEEE Transactions on Robotics, 2016, 32 (1): 1-19.
[27]
CAMPOSJ, YEE A, VEGAI F. Simplifying VGG-16 for plant species identification[J]. IEEE Latin America Transactions, 2022, 20 (11): 2330-2338.
[28]
TORIIA, ARANDJELOVICR, SIVICJ, et al. 24/7 place recognition by view synthesis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40 (2): 257-271.