TY - GEN
T1 - KR-net
T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
AU - Hyeon, Janghun
AU - Kim, Dongwoo
AU - Jang, Bumchul
AU - Choi, Hyunga
AU - Yi, Dong Hoon
AU - Yoo, Kyungho
AU - Choi, Jeongae
AU - Doh, Nakju
N1 - Funding Information:
This research was supported by the Brain Korea 21 Plus project in 2020.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/24
Y1 - 2020/10/24
N2 - In this paper, we propose a dependable visual kidnap recovery (KR) framework that pinpoints a unique pose in a given 3D map when a device is turned on. For this framework, we first develop indoor-GeM (i-GeM), which is an extension of GeM [1] but considerably more robust than other global descriptors [2]-[4], including GeM itself. Then, we propose a convolutional neural network (CNN)-based system called KR-Net, which is based on a coarse-to-fine paradigm as in [5] and [6]. To our knowledge, KR-Net is the first network that can pinpoint a wake-up pose with a confidence level near 100% within a 1.0 m translational error boundary. This dependable success rate is enabled not only by i-GeM, but also by a combinatorial pooling approach that uses multiple images around the wake-up spot, whereas previous implementations [5], [6] were constrained to a single image. Experiments were conducted in two challenging datasets: a large-scale (12, 557 m2) area with frequent featureless or repetitive places and a place with significant view changes due to a one-year gap between prior modeling and query acquisition. Given 59 test query sets (eight images per pose), KR-Net successfully found all wake-up poses, with average and maximum errors of 0.246 m and 0.983 m, respectively.
AB - In this paper, we propose a dependable visual kidnap recovery (KR) framework that pinpoints a unique pose in a given 3D map when a device is turned on. For this framework, we first develop indoor-GeM (i-GeM), which is an extension of GeM [1] but considerably more robust than other global descriptors [2]-[4], including GeM itself. Then, we propose a convolutional neural network (CNN)-based system called KR-Net, which is based on a coarse-to-fine paradigm as in [5] and [6]. To our knowledge, KR-Net is the first network that can pinpoint a wake-up pose with a confidence level near 100% within a 1.0 m translational error boundary. This dependable success rate is enabled not only by i-GeM, but also by a combinatorial pooling approach that uses multiple images around the wake-up spot, whereas previous implementations [5], [6] were constrained to a single image. Experiments were conducted in two challenging datasets: a large-scale (12, 557 m2) area with frequent featureless or repetitive places and a place with significant view changes due to a one-year gap between prior modeling and query acquisition. Given 59 test query sets (eight images per pose), KR-Net successfully found all wake-up poses, with average and maximum errors of 0.246 m and 0.983 m, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85102411542&partnerID=8YFLogxK
U2 - 10.1109/IROS45743.2020.9341597
DO - 10.1109/IROS45743.2020.9341597
M3 - Conference contribution
AN - SCOPUS:85102411542
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 8527
EP - 8533
BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 24 October 2020 through 24 January 2021
ER -