Only Look Once, Mining Distinctive Landmarks From Convnet For Visual Place Recognition
2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)(2017)
摘要
Recently, image representations derived from Convolutional Neural Networks (CNNs) have been demonstrated to achieve impressive performance on a wide variety of tasks, including place recognition. In this paper, we take a step deeper into the internal structure of CNNs and propose novel CNN-based image features for place recognition by identifying salient regions and creating their regional representations directly from the convolutional layer activations. A range of experiments is conducted on challenging datasets with varied conditions and viewpoints. These reveal superior precision-recall characteristics and robustness against both viewpoint and appearance variations for the proposed approach over the state of the art. By analyzing the feature encoding process of our approach, we provide insights into what makes an image presentation robust against external variations.
更多查看译文
关键词
ConvNet,visual place recognition,image representations,Convolutional Neural Networks,salient regions,regional representations,convolutional layer activations,appearance variations,feature encoding process,viewpoint variations,image presentation,distinctive landmarks mining,place recognition,CNN-based image features,precision-recall characteristics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络