SimVODIS : Simultaneous Visual Odometry, Object Detection, and Instance Segmentation

Intelligent agents need to understand the surrounding environment to provide meaningful services to or interact intelligently with humans. The agents should perceive geometric features as well as semantic entities inherent in the environment. Contemporary methods in general provide one type of infor...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 1 vom: 30. Jan., Seite 428-441
1. Verfasser: Kim, Ue-Hwan (VerfasserIn)
Weitere Verfasser: Kim, Se-Ho, Kim, Jong-Hwan
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM31326046X
003 DE-627
005 20231225150209.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2020.3007546  |2 doi 
028 5 2 |a pubmed24n1044.xml 
035 |a (DE-627)NLM31326046X 
035 |a (NLM)32750805 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Kim, Ue-Hwan  |e verfasserin  |4 aut 
245 1 0 |a SimVODIS  |b Simultaneous Visual Odometry, Object Detection, and Instance Segmentation 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 10.01.2022 
500 |a Date Revised 10.01.2022 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a Intelligent agents need to understand the surrounding environment to provide meaningful services to or interact intelligently with humans. The agents should perceive geometric features as well as semantic entities inherent in the environment. Contemporary methods in general provide one type of information regarding the environment at a time, making it difficult to conduct high-level tasks. Moreover, running two types of methods and associating two resultant information requires a lot of computation and complicates the software architecture. To overcome these limitations, we propose a neural architecture that simultaneously performs both geometric and semantic tasks in a single thread: simultaneous visual odometry, object detection, and instance segmentation (SimVODIS). SimVODIS is built on top of Mask-RCNN which is trained in a supervised manner. Training the pose and depth branches of SimVODIS requires unlabeled video sequences and the photometric consistency between input image frames generates self-supervision signals. The performance of SimVODIS outperforms or matches the state-of-the-art performance in pose estimation, depth map prediction, object detection, and instance segmentation tasks while completing all the tasks in a single thread. We expect SimVODIS would enhance the autonomy of intelligent agents and let the agents provide effective services to humans 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Kim, Se-Ho  |e verfasserin  |4 aut 
700 1 |a Kim, Jong-Hwan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 44(2022), 1 vom: 30. Jan., Seite 428-441  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:44  |g year:2022  |g number:1  |g day:30  |g month:01  |g pages:428-441 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2020.3007546  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 44  |j 2022  |e 1  |b 30  |c 01  |h 428-441