NDLI: Learning scene-specific pedestrian detectors without real data

Content Provider	IEEE Xplore Digital Library
Author	Hattori, H. Boddeti, V.N. Kitani, K. Kanade, T.
Copyright Year	2015
Description	Author affiliation: Sony Corp., Tokyo, Japan (Hattori, H.) \|\| Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA (Boddeti, V.N.; Kitani, K.; Kanade, T.)
Abstract	We consider the problem of designing a scene-specific pedestrian detector in a scenario where we have zero instances of real pedestrian data (i.e., no labeled real data or unsupervised real data). 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. The key idea of our approach is to infer the potential appearance of pedestrians using geometric scene data and a customizable database of virtual simulations of pedestrian motion. We propose an efficient discriminative learning method that generates a spatially-varying pedestrian appearance model that takes into the account the perspective geometry of the scene. As a result, our method is able to learn a unique pedestrian classifier customized for every possible location in the scene. Our experimental results show that our proposed approach outperforms classical pedestrian detection models and hybrid synthetic-real models. Our results also yield a surprising result, that our method using purely synthetic data is able to outperform models trained on real scene-specific data when data is limited.
Starting Page	3819
Ending Page	3827
File Size	1456816
Page Count	9
File Format	PDF
ISSN	10636919
e-ISBN	9781467369640
DOI	10.1109/CVPR.2015.7299006
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-06-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Detectors Cameras Computational modeling Surveillance Training Three-dimensional displays Solid modeling
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Monocular 3D scene understanding with explicit occlusion reasoning

Cross-View Action Modeling, Learning, and Recognition

Temporal Non-maximum Suppression for Pedestrian Detection Using Self-Calibration

Learning people detection models from few training samples

Holistic Scene Understanding for 3D Object Detection with RGBD Cameras

3DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding

Pedestrian Detection Using Augmented Training Data

Sampling bedrooms

Scene Parsing by Integrating Function, Geometry and Appearance Models

Learning scene-specific pedestrian detectors without real data

Similar Documents

Monocular 3D scene understanding with explicit occlusion reasoning

Cross-View Action Modeling, Learning, and Recognition

Temporal Non-maximum Suppression for Pedestrian Detection Using Self-Calibration

Learning people detection models from few training samples

Holistic Scene Understanding for 3D Object Detection with RGBD Cameras

3DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding

Pedestrian Detection Using Augmented Training Data

Sampling bedrooms

Scene Parsing by Integrating Function, Geometry and Appearance Models

Learning scene-specific pedestrian detectors without real data