A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Scene-Specific Pedestrian Detection Based on Parallel Vision
[article]
2017
arXiv
pre-print
Preserved Fulltext
In this paper, we propose an ACP-based method, with augmented reality's help, we build the virtual world of specific scenes, and make people walking in the virtual scenes where it is possible for them ...
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. ...
RELATED WORK As a part of ACP method,the virtual scene, also as virtual world is important. ...
arXiv:1712.08745v1
fatcat:y6f3iuo5hbh3vmbq5ftf5sczte
Learning a multiview part-based model in virtual world for pedestrian detection
2013
2013 IEEE Intelligent Vehicles Symposium (IV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
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 ...
CONCLUSION In this paper we have presented a method to train a multiview deformable part-based model with virtual-world data for pedestrian detection. ...
doi:10.1109/ivs.2013.6629512
dblp:conf/ivs/XuVLMP13
fatcat:5skx3sik45athek27f4diykz5i
Learning appearance in virtual scenarios for pedestrian detection
2010
2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
The most promising detectors rely on appearance-based pedestrian classifiers trained with labelled samples. ...
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. ...
Conclusions In this paper we have explored how realistic virtual worlds can help in learning appearance-based models for pedestrian detection in the ADAS area. ...
doi:10.1109/cvpr.2010.5540218
dblp:conf/cvpr/MarinVGL10
fatcat:a7e3ocrplbgejbdmm6g6niuvzq
Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes
2013
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). ...
However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. ...
The idea is that at the end of the process we can end up with a large number of real-world pedestrian BBs without manually an- notating them, i.e. the virtual-world-based pedestrian detector provides BBs ...
doi:10.1109/cvprw.2013.107
dblp:conf/cvpr/VazquezXRLP13
fatcat:5b657dmquvbcpdhyg6wyuk4r6y
Virtual and Real World Adaptation for Pedestrian Detection
2014
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. ...
with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. ...
Analogously, we can learn a part-based pedestrian classifier with dense descriptors [20] , or using the pedestrian silhouette instead [21] . ...
doi:10.1109/tpami.2013.163
pmid:26353201
fatcat:igb6ie7fcfcblldqxyiu4ymepm
Domain Adaptation of Deformable Part-Based Models
2014
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Index Terms-domain adaptation, deformable part-based model, pedestrian detection ✦ This is the author's version of an article that has been published in this journal. ...
By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). ...
The figure shows the adaptation of a DPM-based pedestrian detector from a virtual-world source domain to a real-world target domain. ...
doi:10.1109/tpami.2014.2327973
pmid:26353145
fatcat:5c6tlp4vmnf3vpwe4elewdmzay
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this chapter we revisit the DA of a deformable part-based model (DPM) as an exemplifying case of virtual- to-real-world DA. ...
in the virtual world. ...
Learning
ference on Neural Information Processing Sys-
a part-based pedestrian detector in a virtual
tems (NIPS), Workshop on Domain ...
arXiv:1612.09134v1
fatcat:ky7jz3nvh5gkjaxe5npoztyooi
Learning scene-specific pedestrian detectors without real data
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
As a result, our method is able to learn a unique pedestrian classifier customized for every possible location in the scene. ...
This scenario may arise when a new surveillance system is installed in a novel location and a scene-specific pedestrian detector must be trained prior to any observations of pedestrians. ...
SSV: A single HOG+SVM based pedestrian detector trained only on virtual pedestrians whose appearance is simulated in the specific scene under consideration. ...
doi:10.1109/cvpr.2015.7299006
dblp:conf/cvpr/HattoriBKK15
fatcat:akli7fz3lvbvzanozub5kn67ku
Learning people detection models from few training samples
2011
CVPR 2011
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
In particular we employ a rendering-based reshaping method in order to generate thousands of synthetic training samples from only a few persons and views. ...
State-of-the-art methods learn appearance based models requiring tedious collection and annotation of large data corpora. ...
We would like to thank Javier Marin Tur for provided dataset of virtual pedestrians. ...
doi:10.1109/cvpr.2011.5995574
dblp:conf/cvpr/PishchulinJWATS11
fatcat:oesxilc4izfcpht56fdel6hlwi
Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations. ...
Using these renders we learn a scene-and-region specific spatially-varying fully convolutional neural network, for simultaneous detection, pose estimation and segmentation of pedestrians. ...
[29] combined synthetic pedestrian data with real pedestrian data to generate robust real world detectors. Pishchulin et al. ...
arXiv:1612.05234v1
fatcat:iwg7mrpt7jcjpe6wh5lsxtav2i
Using Synthetic Data to Improve and Evaluate the Tracking Performance of Construction Workers on Site
2020
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our approach is verified by means of a tracking system. For this, we train a YOLOv3 detector identifying pedestrian workers. ...
Using 3D computer graphics software, we model virtual construction site scenarios. These are rendered for the use as a synthetic dataset which augments a self-recorded real world dataset. ...
Acknowledgments: The motion capture data used in this project was obtained from mocap.cs.cmu.edu. The CMU database was created with funding from NSF EIA-0196217. ...
doi:10.3390/app10144948
fatcat:z5myerml3fcota6glvgqxfe4sm
Auto-Zooming CNN-Based Framework for Real-Time Pedestrian Detection in Outdoor Surveillance Videos
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a fast, lightweight, and auto-zooming-based framework for small pedestrian detection. ...
We have compared our framework performance with different single-step customized pedestrian detectors as well as the two-step detector faster R-CNN. ...
like to thank the graduate students: Xiangquan Chen, Xin LI, Yifei Gao, Yuyi Lin, Zeqiong Yu, Xin Luo, Kun Zhang, Qunqi Zeng, and Runze Chen for their contributions on annotating the utilized dataset in ...
doi:10.1109/access.2019.2931915
fatcat:ck4kai7ynzggxalwy6ku33itki
Instance Segmentation Method of User Interface Component of Games
2020
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is text/html.
A vision deep learning network exploits pure pixel information in the screen. ...
In this paper, we propose a methodology that segments UI components in a game by using synthetic game images created on a game engine. ...
In 2015, Ref. [ 43 ] proposed a deep learning-based face detector that determined the final face by separately detecting facial parts such as head, eyes, nose, mouth, and beard. ...
doi:10.3390/app10186502
fatcat:gxnwnfxetnbqvcjdvq24phqe4y
Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. ...
Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based ...
Supervised-SLSV [19] : A state-of-the-art scene-specific pedestrian detector learned from virtual pedestrians whose appearance is simulated in the specific scene under consideration. ...
doi:10.1109/cvpr.2017.222
dblp:conf/cvpr/YeZKQCSZ17
fatcat:4b6uc7qvfvhkhj5gljgim5a7ai
Hierarchical Adaptive Structural SVM for Domain Adaptation
[article]
2014
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In the former we apply HA-SSVM to the deformable part-based model (DPM) while in the latter HA-SSVM is applied to multi-category classifiers. ...
Altogether, we term our proposal as hierarchical A-SSVM (HA-SSVM). As proof of concept we use HA-SSVM for pedestrian detection and object category recognition. ...
Caltech shows results of adapting virtual-world DPM detector to a multi-resolution detector in Caltech pedestrian dataset. A-SSVM is trained with mixed high and low resolution samples. ...
arXiv:1408.5400v1
fatcat:scinfinrfvga7nc5ag7xz4x6me
« Previous
Showing results 1 — 15 out of 2,507 results