Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Peiyun Hu"'
Publikováno v:
CVPR
Safe local motion planning for autonomous driving in dynamic environments requires forecasting how the scene evolves. Practical autonomy stacks adopt a semantic object-centric representation of a dynamic scene and build object detection, tracking, an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a4498de20491806391d71436f2f9018
https://doi.org/10.1109/cvpr46437.2021.01254
https://doi.org/10.1109/cvpr46437.2021.01254
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585570
ECCV (5)
ECCV (5)
Most real-world 3D sensors such as LiDARs perform fixed scans of the entire environment, while being decoupled from the recognition system that processes the sensor data. In this work, we propose a method for 3D object recognition using light curtain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af4b35620b9d28fb73d901fa774d95b2
https://doi.org/10.1007/978-3-030-58558-7_44
https://doi.org/10.1007/978-3-030-58558-7_44
Autor:
Deva Ramanan, Peiyun Hu, Benzun P. Wisely Babu, Trenton Tabor, Herman Herman, Jonathan K. Chang, Carl Wellington, Zachary Pezzementi
Publikováno v:
Journal of Field Robotics. 35:545-563
Person detection from vehicles has made rapid progress recently with the advent of multiple high-quality datasets of urban and highway driving, yet no large-scale benchmark is available for the same problem in off-road or agricultural environments. H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::631dd35fda587d7b5b8c154d9d4d922f
https://doi.org/10.1002/rob.21760
https://doi.org/10.1002/rob.21760
Publikováno v:
CVPR
Recent advances in 3D sensing have created unique challenges for computer vision. One fundamental challenge is finding a good representation for 3D sensor data. Most popular representations (such as PointNet) are proposed in the context of processing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4971905e5ef45ade73c8b43c29bcb091
http://arxiv.org/abs/1912.04986
http://arxiv.org/abs/1912.04986
Publikováno v:
IROS
When building a geometric scene understanding system for autonomous vehicles, it is crucial to know when the system might fail. Most contemporary approaches cast the problem as depth regression, whose output is a depth value for each pixel. Such appr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9198349eae531cce89fa96ae498b0c98
https://doi.org/10.1109/iros40897.2019.8968065
https://doi.org/10.1109/iros40897.2019.8968065
Publikováno v:
ICCV Workshops
Objects are naturally captured over a continuous range of distances, causing dramatic changes in appearance, especially at low resolutions. Recognizing such small objects at range is an open challenge in object recognition. In this paper, we explore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e19c4eb4227e9f89600732189a42d247
https://doi.org/10.1109/iccvw.2019.00143
https://doi.org/10.1109/iccvw.2019.00143
We focus on the problem of class-agnostic instance segmentation of LiDAR point clouds. We propose an approach that combines graph-theoretic search with data-driven learning: it searches over a set of candidate segmentations and returns one where indi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79eeb4fc091873263a48db80fe0de691
Publikováno v:
ITSC
Vehicle segmentation is an important step in perception for autonomous driving vehicles, providing object-level environmental understanding. Its performance directly affects other functions in the autonomous driving car, including Decision-Making and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a660a1f709287b30788203e3c8f2f6d
https://doi.org/10.1109/itsc.2018.8569413
https://doi.org/10.1109/itsc.2018.8569413
Publikováno v:
2017 Second International Conference on Mechanical, Control and Computer Engineering (ICMCCE).
In view of the information redundancy of search results and the differences between user requirements and service matching, this paper presents a service matching technology on the basis of the intelligent question-answer system. Based on the OWL-S,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12941d8bdd82efe9fc420353d83f5f2f
https://doi.org/10.1109/icmcce.2017.58
https://doi.org/10.1109/icmcce.2017.58
Autor:
M. Al Jazaery, Mohammad Iqbal Nouyed, Jürgen Beyerer, C. Stankiewicz, Deva Ramanan, Peiyun Hu, Josef Kittler, Shufan Yang, Akshay Raj Dhamija, Terrance E. Boult, Chi-Ho Chan, Christian Herrmann, Manuel Günther, Guodong Guo, Min Jiang
Publikováno v:
IJCB
Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d63d9eb60eb86fa4bf90a79b1d12b8b1
http://arxiv.org/abs/1708.02337
http://arxiv.org/abs/1708.02337