Filters








9,802 Hits in 4.5 sec

Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes

David Vazquez, Jiaolong Xu, Sebastian Ramos, Antonio M. Lopez, Daniel Ponsa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem.  ...  Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation).  ...  Yet, the challenge consists in achieving good pedestrian detection performance with real-world images using classifiers learned from such virtual-world samples.  ... 
doi:10.1109/cvprw.2013.107 dblp:conf/cvpr/VazquezXRLP13 fatcat:5b657dmquvbcpdhyg6wyuk4r6y

Learning appearance in virtual scenarios for pedestrian detection

Javier Marin, David Vazquez, David Geronimo, Antonio M. Lopez
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
We test such classifiers in a publicly available dataset provided by Daimler AG for pedestrian detection benchmarking. This dataset contains real world images acquired from a moving car.  ...  This paper addresses the following question: can a pedestrian appearance model learnt in virtual scenarios work successfully for pedestrian detection in real images? (Fig. 1 ).  ...  Figure 5 shows some qualitative results from which we can see how similar are the particular detections coming from virtual and real world learning.  ... 
doi:10.1109/cvpr.2010.5540218 dblp:conf/cvpr/MarinVGL10 fatcat:a7e3ocrplbgejbdmm6g6niuvzq

Virtual and Real World Adaptation for Pedestrian Detection

David Vazquez, Antonio M. Lopez, Javier Marin, Daniel Ponsa, David Geronimo
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?.  ...  Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them  ...  CONCLUSION In this paper we have explored how virtual worlds can help in learning appearance-based models for pedestrian detection in real-world images.  ... 
doi:10.1109/tpami.2013.163 pmid:26353201 fatcat:igb6ie7fcfcblldqxyiu4ymepm

Scene-Specific Pedestrian Detection Based on Parallel Vision [article]

Wenwen Zhang, Kunfeng Wang, Hua Qu, Jihong Zhao, Fei-Yue Wang
2017 arXiv   pre-print
to appear to solve this problem of lacking labeled data and the results show that data from virtual world is helpful to adapt generic pedestrian detectors to specific scenes.  ...  As a special type of object detection, pedestrian detection in generic scenes has made a significant progress trained with large amounts of labeled training data manually.  ...  With different configurations, we can easily generate variable data from virtual scene to learn a pedestrian model for the truth.  ... 
arXiv:1712.08745v1 fatcat:y6f3iuo5hbh3vmbq5ftf5sczte

Learning a multiview part-based model in virtual world for pedestrian detection

Jiaolong Xu, David Vazquez, Antonio M. Lopez, Javier Marin, Daniel Ponsa
2013 2013 IEEE Intelligent Vehicles Symposium (IV)  
In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data.  ...  The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance  ...  VIRTUAL-WORLD TRAINING EXAMPLES The virtual-world dataset is created from the video game Half-Life 2 based on our previous work in [13] .  ... 
doi:10.1109/ivs.2013.6629512 dblp:conf/ivs/XuVLMP13 fatcat:5skx3sik45athek27f4diykz5i

Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers

Jiaolong Xu, David Vazquez, Sebastian Ramos, Antonio M. Lopez, Daniel Ponsa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
We evaluate our proposal on multiple real-world pedestrian detection datasets.  ...  In this paper, we propose a domain adaptation approach based on boosting LDA exemplar classifiers from both virtual and real worlds.  ...  Following [9] , we use a video-game to generate a virtual world from which we extract the pedestrian examples.  ... 
doi:10.1109/cvprw.2013.104 dblp:conf/cvpr/XuVRLP13 fatcat:c22ra42svrcwboj27desdmo2ia

Virtual to Real adaptation of Pedestrian Detectors [article]

Luca Ciampi, Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
2020 arXiv   pre-print
Pedestrian detection through Computer Vision is a building block for a multitude of applications.  ...  To mitigate this gap, we propose two different Domain Adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection.  ...  In our opinion, the result of this work opens new perspectives to address the scalability of pedestrian and object detection methods for large physical systems with limited supervisory resources.  ... 
arXiv:2001.03032v2 fatcat:237q7npudbeyveuophbuyqloya

Domain Adaptation of Deformable Part-Based Models

Jiaolong Xu, Sebastian Ramos, David Vazquez, Antonio M. Lopez
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera.  ...  We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection.  ...  Additionally, we thank Xu Hu from Oregon State Univ. for many fruitful discussions, and Dr. Andrew D. Bagdanov from the Computer Vision Center for helping us to improve paper readability.  ... 
doi:10.1109/tpami.2014.2327973 pmid:26353145 fatcat:5c6tlp4vmnf3vpwe4elewdmzay

Virtual to Real Adaptation of Pedestrian Detectors

Luca Ciampi, Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
2020 Sensors  
Pedestrian detection through Computer Vision is a building block for a multitude of applications.  ...  To mitigate this gap, we propose two different domain adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection.  ...  Authors in [31, 32] have also focused on learning features from synthetic data for the pedestrian detection task.  ... 
doi:10.3390/s20185250 pmid:32937977 fatcat:m275dyk4cbc65hg2xxh4qrl5ym

From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example [article]

Antonio M. Lopez, Jiaolong Xu, Jose L. Gomez, David Vazquez, German Ros
2016 arXiv   pre-print
As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data.  ...  in the virtual world.  ...  Learning appearance Computer Vision (ICCV), 2015. in virtual scenarios for pedestrian detection.  ... 
arXiv:1612.09134v1 fatcat:ky7jz3nvh5gkjaxe5npoztyooi

A mixed generative-discriminative framework for pedestrian classification

Markus Enzweiler, Dariu M. Gavrila
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classification performance of a discriminative  ...  Our generative model captures prior knowledge about the pedestrian class in terms of a number of probabilistic shape and texture models, each attuned to a particular pedestrian pose.  ...  A generative model is learned from a pedestrian dataset captured in real urban traffic and used to synthesize virtual samples of the target class, thus enlarging the training set of a discriminative pattern  ... 
doi:10.1109/cvpr.2008.4587592 dblp:conf/cvpr/EnzweilerG08 fatcat:t2s6tmys2jdhtezqsnrt3oc2ru

Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics

Aniket Bera, Sujeong Kim, Dinesh Manocha
2018 Collective Dynamics  
The learned behaviors are used to generate plausible trajectories of virtual agents as well as for long-term pedestrian trajectory prediction.  ...  Our formulation extracts the dynamic behavior features of real-world agents and uses them to learn movement characteristics on the fly.  ...  Acknowledgements This work was supported by National Science Foundation award 1305286, ARO contract W911NF-16-1-0085, and a grant from the Boeing company.  ... 
doi:10.17815/cd.2018.15 fatcat:i74i7bbap5fcfez5nexgt7l3tm

Big Data Scenarios Simulator for Deep Learning Algorithm Evaluation for Autonomous Vehicle

Jun Wei Dickson Ang, Chee Kiat Seow, Karthikk Subramanian, Sugiri Pranata
2020 GLOBECOM 2020 - 2020 IEEE Global Communications Conference  
This necessitates the virtual scenarios simulator to simulate the real environment by generating big data images from a virtual fisheye lens that can mimic the field of view and radial distortion of commercial  ...  One of the challenges in developing autonomous vehicles (AV) is the collection of suitable real environment data for the training and evaluation of machine learning algorithms for autonomous vehicles.  ...  [11] using virtual worlds created from a few seed real-world video sequences to generate annotated image datasets.  ... 
doi:10.1109/globecom42002.2020.9322480 fatcat:2t7bty22zzbdph7xnln54qvusy

Hierarchical Adaptive Structural SVM for Domain Adaptation [article]

Jiaolong Xu, Sebastian Ramos, David Vazquez, Antonio M. Lopez
2014 arXiv   pre-print
As proof of concept we use HA-SSVM for pedestrian detection and object category recognition.  ...  A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain.  ...  The virtual-world dataset contains less low-resolution pedestrians than the real-world ones. Fig. 8 8 Pedestrian detection results on KITTI benchmark.  ... 
arXiv:1408.5400v1 fatcat:scinfinrfvga7nc5ag7xz4x6me

Hierarchical Adaptive Structural SVM for Domain Adaptation

Jiaolong Xu, Sebastian Ramos, David Vázquez, Antonio M. López
2016 International Journal of Computer Vision  
As proof of concept we use HA-SSVM for pedestrian detection and object category recognition.  ...  A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain.  ...  The virtual-world dataset contains less low-resolution pedestrians than the real-world ones. Fig. 8 8 Pedestrian detection results on KITTI benchmark.  ... 
doi:10.1007/s11263-016-0885-6 fatcat:3ylautrdyfffblfifwlukgm7u4
« Previous Showing results 1 — 15 out of 9,802 results