期刊文献+

基于改进NetVLAD图像特征提取的回环检测算法

Loop Closure Detection Based on Improved Net VLAD Image Feature Extraction
下载PDF
导出
摘要 传统回环检测算法大都采用手工特征来表征图像,在应对光照、视角等环境变化时的鲁棒性较差,并且特征提取比较耗时,很难满足实时性要求。针对上述问题,提出了一种改进的基于深度神经网络提取图像特征的回环检测算法。具体地,在经典NetVLAD算法中引入空洞空间金字塔池化模块,通过多尺度特征融合,在降维的同时提高了特征图的分辨率,得到更加鲁棒且紧凑的图像特征描述。在公共数据集上的实验结果表明,所提出的算法在精确率和召回率上均有一定的提升,可以较好地应对环境变化,图像特征提取耗时也有明显改善。 Traditional loop closure detection algorithms mostly utilize handcrafted features to represent images.The robustness of dealing environmental changes such as illumination and viewpoint changes is vulnerable,and the features extraction is time-consuming,which cannot meet the real-time requirements.To address these problems,we propose an improved algorithm which uses deep neural network to extract more robust image features.Specifically,the atrous spatial pyramid pooling(ASPP)module is introduced into the classic NetVLAD model to characterize the image.By the fusion of multi-scale features,the feature maps have fewer dimension and higher resolution,and thus,more accurate and compact image features are obtained.Experiments on public datasets show that the proposed algorithm has higher precision and recall rate.It can deal with the changes of illumination and viewpoint to a certain extent,and has less time cost in extracting image features.
作者 邱长滨 王庆芝 刘其朋 QIU Changbin;WANG Qingzhi;LIU Qipeng(Institute of Complexity Science,Qingdao University,Qingdao 266071,China)
出处 《复杂系统与复杂性科学》 CAS CSCD 北大核心 2023年第4期92-97,106,共7页 Complex Systems and Complexity Science
基金 国家自然科学基金(61903212)。
关键词 回环检测 特征提取 深度神经网络 空洞空间金字塔池化 NetVLAD loop closure detection feature extraction deep neural network atrous spatial pyramid pooling NetVLAD
  • 相关文献

参考文献2

二级参考文献64

  • 1Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60 (2) 91 110.
  • 2Dalai N, Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society Conference on. San Diego, USA: IEEE, 2005, 1 886-893.
  • 3Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786) : 504-507.
  • 4Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functional architecture in the catrs visual cortex[J]. The Journal of Physiology, 1962, 160(1): 106-154.
  • 5Fukushima K, Miyake S. Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in posi- tion[J]. Pattern Recognition, 1982, 15(6): 455-469.
  • 6Ruck D W, Rogers S K, Kabrisky M. Feature selection using a multilayer perceptron[J]. Journal of Neural Network Com- puting, 1990, 2(2): 40-48.
  • 7Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986,3231 533 538.
  • 8LeCun Y, Denker J S, Henderson D, et al. Handwritten digit recognition with a back-propagation network[C]//Advances in Neural Information Processing Systems. Colorado, USA Is. n. ], 1990: 396-404.
  • 9LeCun Y, Cortes C. MNIST handwritten digit database[EB/OL], http//yann, lecun, com/exdb/mnist, 2010.
  • 10Waibe[ A, Hanazawa T, Hinton G, et al. Phoneme recognition using time-delay neural networks[J]. Acoustics, Speech and Signal Processing, IEEF. Transactions on, 1989, 37(3): 328-339.

共引文献572

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部