Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Ali Harakeh"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-16
As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9987ecf193376ec349acfd2e7743fab3
https://doi.org/10.1109/tpami.2022.3201541
https://doi.org/10.1109/tpami.2022.3201541
Publikováno v:
CVPR
Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::57e8eed775b5ca743a62c062e6dfbabf
https://doi.org/10.1109/cvpr46437.2021.00845
https://doi.org/10.1109/cvpr46437.2021.00845
Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed. However, there i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eebd2e736a22deedaac802530b47eb00
http://arxiv.org/abs/2011.10671
http://arxiv.org/abs/2011.10671
Publikováno v:
ICRA
When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions. Methods for uncertainty estimation in the output of deep object detectors (DNNs) have been p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75ed83eb1a5ddba24779801a6a93d309
https://doi.org/10.1109/icra40945.2020.9196544
https://doi.org/10.1109/icra40945.2020.9196544
Publikováno v:
Robotica. 36:1278-1300
SUMMARYThe ability to reliably estimate free space is an essential requirement for efficient and safe robot navigation. This paper presents a novel system, built upon a stochastic framework, which estimates free space quickly from stereo data, using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d33f9a75a189e7dc5feb89b11a683ff6
https://doi.org/10.1017/s0263574718000371
https://doi.org/10.1017/s0263574718000371
Autor:
Cody Reading, Matt Angus, Mohamed ElBalkini, Ali Harakeh, Krzysztof Czarnecki, Steven L. Waslander, Oles Andrienko, Samin Khan
Publikováno v:
ITSC
In training deep neural networks for semantic segmentation, the main limiting factor is the low amount of ground truth annotation data that is available in currently existing datasets. The limited availability of such data is due to the time cost and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4590c90a9e36a9cf3440a7f4a7b9d02
http://arxiv.org/abs/1807.06056
http://arxiv.org/abs/1807.06056
Publikováno v:
CRV
Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or signs, not both, which makes them unsuitable for real-life deployment due
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31de3157073fc4e5c824b03059c37bb2
https://doi.org/10.1109/crv.2018.00024
https://doi.org/10.1109/crv.2018.00024
Publikováno v:
CRV
With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms. This paper shows that with a wel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67488a1f0ac43738ae532b42f597bbbf
https://doi.org/10.1109/crv.2018.00013
https://doi.org/10.1109/crv.2018.00013
Publikováno v:
ITSC
Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations. Reducing both task complexity and the amount of task switching done by annotators is key to reducing the effort
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7faf75bbc18f4dae94b7846cf945aaf
Publikováno v:
IROS
We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::186243a1287bc8ab0ad7412c087236b5
http://arxiv.org/abs/1712.02294
http://arxiv.org/abs/1712.02294