http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Efficient Visual Place Recognition by Adaptive CNN Landmark Matching
( Yutian Chen ),( Wenyan Gan ),( Yi Zhu ),( Hui Tian ),( Cong Wang ),( Wenfeng Ma ),( Yunbo Li ),( Dong Wang ),( Jixian He ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.11
Visual place recognition (VPR) is a fundamental yet challenging task of mobile robot navigation and localization. The existing VPR methods are usually based on some pairwise similarity of image descriptors, so they are sensitive to visual appearance change and also computationally expensive. This paper proposes a simple yet effective four-step method that achieves adaptive convolutional neural network (CNN) landmark matching for VPR. First, based on the features extracted from existing CNN models, the regions with higher significance scores are selected as landmarks. Then, according to the coordinate positions of potential landmarks, landmark matching is improved by removing mismatched landmark pairs. Finally, considering the significance scores obtained in the first step, robust image retrieval is performed based on adaptive landmark matching, and it gives more weight to the landmark matching pairs with higher significance scores. To verify the efficiency and robustness of the proposed method, evaluations are conducted on standard benchmark datasets. The experimental results indicate that the proposed method reduces the feature representation space of place images by more than 75% with negligible loss in recognition precision. Also, it achieves a fast matching speed in similarity calculation, satisfying the real-time requirement.
Dongyang Ma,Liling Ren,Zhen Cao,Jianxue Li,Jian Cao,Wenyan Tian,Hong Yao 한국조직공학과 재생의학회 2016 조직공학과 재생의학 Vol.13 No.5
The repair of bone defects poses a great challenge for reconstructive surgeons. Although the development of tissue engineering has exhibited promise in replacing damaged bone, the fabrication of large constructs with functional blood vessels remains an obstacle. From the orthopedic surgeon’s point of view, the generation of axially vascularized bone, which can anastomose with the recipient vessel, might be a solution to this medical problem. In this study, we aimed to prefabricate an axially vascularized bone by combining a β-TCP scaffold, arteriovenous loop (AVL), and cell sheet in a bioreactor in vivo. Twelve rabbits were randomly allocated into two groups: the experimental group (presence of AVL) and the control group (absence of AVL). The constructs were explanted at 8 weeks postoperatively. The histomorphometric results showed 42.8±5.9% of the bone area in the AVL group and 26.6±3.5% in the control group. Similarly, vessel analysis revealed the average vessel density in the AVL group (12.5±3.3) was significantly more than that in the control group (6.1±1.5, p<0.05). Our research indicated that the combination of a β-TCP scaffold, AVL and cell sheet might engineer vascularized bone. This prefabrication strategy might facilitate clinical translation of bone tissue engineering in reconstructing large bone defects.