TY - GEN
T1 - Line-Circle
T2 - 5th RSI International Conference on Robotics and Mechatronics, IcRoM 2017
AU - Tafrishi, Seyed Amir
AU - Kandjani, Vahid E.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2018/9/14
Y1 - 2018/9/14
N2 - This paper presents a state-of-the-art approach in object detection for being applied in future simultaneous localization and mapping (SLAM) problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face overconfidence and large computations during entrance to immense spaces with many landmarks. In particular, they suffer from impractical applications via sole reliance on the limited sensors like camera. Proposed method claims that unmanned ground vehicles without having huge amount of database for object definition and highly advance prediction parameters can deal with incoming objects during straight motion of camera in realtime. Line-Circle (LC) filter tries to apply detection, tracking and learning to each defined experts to obtain more information for judging scene without over-calculation. In this filter, circle expert let us summarize edges in groups. The Interactive feedback learning between each expert creates minimal error that fights against overwhelming landmark signs in crowded scenes without mapping. Our experts basically are dependent on trust factors' covariance with geometric definitions to ignore, emerge and compare detected landmarks. The experiment for validating the model is taken place via a camera beside an inertial measurement unit sensor for location estimation.
AB - This paper presents a state-of-the-art approach in object detection for being applied in future simultaneous localization and mapping (SLAM) problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face overconfidence and large computations during entrance to immense spaces with many landmarks. In particular, they suffer from impractical applications via sole reliance on the limited sensors like camera. Proposed method claims that unmanned ground vehicles without having huge amount of database for object definition and highly advance prediction parameters can deal with incoming objects during straight motion of camera in realtime. Line-Circle (LC) filter tries to apply detection, tracking and learning to each defined experts to obtain more information for judging scene without over-calculation. In this filter, circle expert let us summarize edges in groups. The Interactive feedback learning between each expert creates minimal error that fights against overwhelming landmark signs in crowded scenes without mapping. Our experts basically are dependent on trust factors' covariance with geometric definitions to ignore, emerge and compare detected landmarks. The experiment for validating the model is taken place via a camera beside an inertial measurement unit sensor for location estimation.
UR - http://www.scopus.com/inward/record.url?scp=85054505349&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054505349&partnerID=8YFLogxK
U2 - 10.1109/ICRoM.2017.8466193
DO - 10.1109/ICRoM.2017.8466193
M3 - Conference contribution
AN - SCOPUS:85054505349
SN - 9781538657034
T3 - 5th RSI International Conference on Robotics and Mechatronics, IcRoM 2017
SP - 588
EP - 594
BT - 5th RSI International Conference on Robotics and Mechatronics, IcRoM 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 25 October 2017 through 27 October 2017
ER -