Filters








1,784 Hits in 8.2 sec

Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues [article]

Lu Chi, Yadong Mu
2017 arXiv   pre-print
Our experimental study is based on about 6 hours of human driving data provided by Udacity.  ...  The technical contributions of this work are three-fold. First, the model is learned and evaluated on real human driving videos that are time-synchronized with other vehicle sensors.  ...  Left: steering wheel angles of the video sequence "Ch2 001: Udacity Self Driving Car". We plot the ground truth and the predictions of two models (our proposed model and VGG-16 based model).  ... 
arXiv:1708.03798v1 fatcat:qkbwh3aq4zhgdf6f6p3pkcmbey

2019 Index IEEE Transactions on Intelligent Transportation Systems Vol. 20

2019 IEEE transactions on intelligent transportation systems (Print)  
., and Ma, J  ...  ., +, TITS Nov. 2019 4160-4173 D Data analysis A User Study on the Capability of Three Geo-Based Features in Analyzing and Locating Trajectories.  ...  ., +, TITS July 2019 2540-2549 Data visualization A User Study on the Capability of Three Geo-Based Features in Analyzing and Locating Trajectories.  ... 
doi:10.1109/tits.2020.2966388 fatcat:xkvww7uabzhlzgfz3yiecyb75y

Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation [article]

Patrick Ruhkamp, Daoyi Gao, Hanzhi Chen, Nassir Navab, Benjamin Busam
2021 arXiv   pre-print
By combining our proposed regularization and the novel spatial-temporal-attention module we fully leverage both the geometric and appearance-based consistency across monocular frames.  ...  A novel temporal attention mechanism further processes the local geometric information in a global context across consecutive images.  ...  or autonomous driving [13] .  ... 
arXiv:2110.08192v1 fatcat:deddyenxjbgkxolvxpdrvhccsq

CVPRW 2020 TOC

2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
A Training Method for Image Compression Networks to Improve Perceptual Quality of Reconstructions 585 Jooyoung Lee (Broadcasting and Media Research Laboratory, Electronics and Telecommunications Research  ...  Institute, Daejeon, Korea), Donghyun Kim (Broadcasting and Media Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Korea), Younhee Kim (Broadcasting and Media Research  ...  Jing Nie (VimicroAI, Zhuhai city, Guangdong Provice, P.R.C) 3-D Context Entropy Model for Improved Practical Image Compression 520 Zongyu Guo (CAS Key Laboratory of Technology in Geo-spatial Information  ... 
doi:10.1109/cvprw50498.2020.00004 fatcat:6qao4eypyvg3xiiigih3kicniq

Reframing Societal Discourse as Requirements Negotiation: Vision Statement [article]

Kurt Schneider, Oliver Karras, Anne Finger, Barbara Zibell
2017 arXiv   pre-print
characteristics of spatial planning problems, we suggest using techniques of requirements engineering (RE) and CrowdRE for getting stakeholders (e.g. user groups) involved. (3) We propose video as a medium  ...  Spatial planning problems are characterized by large and heterogeneous groups of stakeholders, such as municipalities, companies, interest groups, citizens, women and men, young people and children.  ...  ACKNOWLEDGMENT This work was carried out within the interdisciplinary Mobile Man project at Leibniz Universität Hannover and was supported by the German Research Foundation (DFG) project ViViReq.  ... 
arXiv:1708.00279v1 fatcat:jv4l6327f5bfpmx2ddf6l5foem

RescueAR: Augmented Reality Supported Collaboration for UAV Driven Emergency Response Systems [article]

Ankit Agrawal, Jane Cleland-Huang
2021 arXiv   pre-print
According to our feasibility study, a user study, followed by a focus group session with police officers, RescueAR can support rescue teams in developing the spatial cognition of the scene, facilitate  ...  Traditional radio-based information exchange between humans during an emergency response suffers from a lack of visualization and often results in miscommunication.  ...  In contrast, Remote Augmented Reality (RAR) extends location or vision-based AR experiences by augmenting videos received from remote sources with 3D models and graphics in real-time.  ... 
arXiv:2110.00180v1 fatcat:uvleergf5zhaxfejzmc5r3mwpm

ADMT: Advanced Driver's Movement Tracking system using Spatio-temporal interest points and maneuver anticipation using deep neural networks

Shilpa Gite, Biswajeet Pradhan, Abdullah Alamri, Ketan Kotecha
2021 IEEE Access  
The training of 5 seconds of driving context is given on FFNN, and the internal context features are combined to train the FFNN.  ...  It is because of the sequential video data that is given as the input to the system model.  ...  CONFLICT OF INTEREST The authors declare no conflict of interest.  ... 
doi:10.1109/access.2021.3096032 fatcat:mcuy36ydyfaynp5itq6ft6txvi

Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review [article]

Abolfazl Razi, Xiwen Chen, Huayu Li, Brendan Russo, Yan Chen, Hongbin Yu
2022 arXiv   pre-print
This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated  ...  a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step.  ...  Jason Pacheco, Larry Head, and Junsuo Qu from their thoughtful comments on this paper. Special thanks go to Greg Leeming from Intel for his insightful comments and continued support of this project.  ... 
arXiv:2203.10939v1 fatcat:h4o5zghhhfezncn7luy56yjusm

Deep Learning for Edge Computing Applications: A State-of-the-art Survey

Fangxin Wang, Miao Zhang, Xiangxiang Wang, Xiaoqiang Ma, Jiangchuan Liu
2020 IEEE Access  
Besides, the recent breakthroughs in deep learning have greatly facilitated the data processing capacity, enabling a thrilling development of novel applications, such as video surveillance and autonomous  ...  driving.  ...  efficiency. 3) CONTEXT-AWARE SERVICE Context-aware computing [25] is playing an important role in IoT and edge computing applications, since good modeling and reasoning of collected data can highly  ... 
doi:10.1109/access.2020.2982411 fatcat:43atfhktujbuxns2bsl2cfpnay

Visual and Object Geo-localization: A Comprehensive Survey [article]

Daniel Wilson, Xiaohan Zhang, Waqas Sultani, Safwan Wshah
2021 arXiv   pre-print
, the fields of visual and object geo-localization have emerged due to its significant impact on a wide range of applications such as augmented reality, robotics, self-driving vehicles, road maintenance  ...  As massive datasets of GPS tagged media have rapidly become available due to smartphones and the internet, and deep learning has risen to enhance the performance capabilities of machine learning models  ...  Li, “Spatial-aware views using overhead imagery,” in European confer- feature aggregation for image based cross-view geo- ence on computer vision (ECCV), B. Leibe, J.  ... 
arXiv:2112.15202v1 fatcat:ipwas72ro5ho5fjiakm6de7ji4

Context modeling in computer vision: techniques, implications, and applications

Oge Marques, Elan Barenholtz, Vincent Charvillat
2010 Multimedia tools and applications  
In recent years there has been a surge of interest in context modeling for numerous applications in computer vision.  ...  The current paper provides a 'roadmap' of this new research, including a discussion of the basic motivation behind context-modeling, an overview of the most representative techniques, and a discussion  ...  Acknowledgements The authors would like to thank Geraldine Morin, Pierre Gurdjos, Viorica Patraucean, and Jerôme Guenard, for the insightful discussions and constructive suggestions.  ... 
doi:10.1007/s11042-010-0631-y fatcat:cspmqzbtinexrghz2zxjklkyva

5G Beyond 3GPP Release 15 for Connected Automated Mobility in Cross-Border Contexts

Gorka Velez, Ángel Martín, Giancarlo Pastor, Edward Mutafungwa
2020 Sensors  
of highly automated driving in cross-border corridors.  ...  In order to conduct this study, a set of representative use cases and the related communication requirements were identified. Then, for each use case, the most relevant 5G features were proposed.  ...  vision of the driving situation by gathering data from all the actors in place.  ... 
doi:10.3390/s20226622 pmid:33228020 fatcat:2av6xzqidngcjc2ewelezxiqhm

2018 Index IEEE Transactions on Visualization and Computer Graphics Vol. 24

2019 IEEE Transactions on Visualization and Computer Graphics  
June 2018 2023-2036 Summarization and Stage Analysis of Event Sequence Data; TVCG Jan. 2018 56-65 Guo, Y., see Liu, L., TVCG June 2018 1956-1968  ...  ., and Dai, Q., Errata to "Robust Non-Rigid Motion Tracking and Surface Reconstruction Using L 0 Regularization"; TVCG July 2018 2268 Guo, K., Xu, F., Wang, Y., Liu, Y., and Dai, Q., Robust Non-Rigid  ...  ., þ, TVCG Jan. 2018 23-33 Data models A Data Model and Task Space for Data of Interest (DOI) Eye-Tracking Analyses.  ... 
doi:10.1109/tvcg.2018.2885445 fatcat:xtccdnalwfhudp3qdxofz4kqpi

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art [article]

Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
2021 arXiv   pre-print
, scene understanding, and end-to-end learning for autonomous driving.  ...  Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles.  ...  The autonomous driving project Apollo from Baidu created the Data Open Platform 19 consisting of simulation, annotation, and demonstration data for autonomous driving.  ... 
arXiv:1704.05519v3 fatcat:xiintiarqjbfldheeg2hsydyra

3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey

Sumaira Manzoor, Sung-Hyeon Joo, Eun-Jin Kim, Sang-Hyeon Bae, Gun-Gyo In, Jeong-Won Pyo, Tae-Yong Kuc
2021 Sensors  
Instigated by the recognition capability of social robots, we present the analysis of data representation methods based on sensor modalities for 3D object and place recognition using deep learning models  ...  as a guide to those who are interested in vision-based robotics applications.  ...  Acknowledgments: Thanks for the help of reviewers and editors. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21217120 pmid:34770429 pmcid:PMC8587961 fatcat:qqoqlkaycbc4xk24j7j2nzqabe
« Previous Showing results 1 — 15 out of 1,784 results