Pedestrian Detection via Classification on Riemannian Manifolds

Authors:
Oncel Tuzel;Fatih Porikli;Peter Meer
Affiliations:
Rutgers University, Piscataway;Mitsubishi Electric Research Labs., Cambridge;Rutgers University, Piscataway
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2008

Citing 0
Cited 69

A neural network approach to pedestrian detection

ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers
Video condensation by ribbon carving

IEEE Transactions on Image Processing
The application of intrinsic variable preserving manifold learning method to tracking multiple people with occlusion reasoning

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Boosted forest for human detection

Proceedings of the First International Conference on Internet Multimedia Computing and Service
A Lie group based Gaussian Mixture Model distance measure for multimedia comparison

Proceedings of the First International Conference on Internet Multimedia Computing and Service
Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition

Foundations and Trends in Signal Processing
Recognizing affect from non-stylized body motion using shape of Gaussian descriptors

Proceedings of the 2010 ACM Symposium on Applied Computing
2D-3D-based on-board pedestrian detection system

Computer Vision and Image Understanding
Cascade of descriptors to detect and track objects across any network of cameras

Computer Vision and Image Understanding
Human detection using motion and appearance based feature

ICICS'09 Proceedings of the 7th international conference on Information, communications and signal processing
Surfing on artistic documents with visually assisted tagging

Proceedings of the international conference on Multimedia
Rerum novarum: interactive exploration of illuminated manuscripts

Proceedings of the international conference on Multimedia
Multi-class classification on Riemannian manifolds for video surveillance

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Multiresolution models for object detection

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Tensor sparse coding for region covariances

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Multi-stage sampling with boosting cascades for pedestrian detection in images and videos

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Emotion recognition from arbitrary view facial images

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Human posture recognition for intelligent vehicles

Journal of Real-Time Image Processing
Efficient HOG human detection

Signal Processing
Nearest-neighbor search algorithms on non-Euclidean manifolds for computer vision applications

Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Pyramid binary pattern features for real-time pedestrian detection from infrared videos

Neurocomputing
Riemannian geometry applied to BCI classification

LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
Motion compensation algorithm based on color orientation codes and covariance matching

ICIRA'10 Proceedings of the Third international conference on Intelligent robotics and applications - Volume Part II
Speeding up HOG and LBP features for pedestrian detection by multiresolution techniques

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
Face recognition using sparse representations and manifold learning

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
Silhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds

Computer Vision and Image Understanding
People localization in a camera network combining background subtraction and scene-aware human detection

MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part I
Pedestrian recognition with a learned metric

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part IV
Contextual information and covariance descriptors for people surveillance: an application for safety of construction workers

Journal on Image and Video Processing - Special issue on advanced video-based surveillance
Relevance feedback strategies for artistic image collections tagging

Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Information-geometric graph indexing from bags of partial node coverages

GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
Self-tuned Evolution-COnstructed features for general object recognition

Pattern Recognition
Feature space warping relevance feedback with transductive learning

ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Sparsity Driven People Localization with a Heterogeneous Network of Cameras

Journal of Mathematical Imaging and Vision
Recognition of adult images, videos, and web page bags

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) - Special section on ACM multimedia 2010 best paper candidates, and issue on social media
Shape matching using a binary search tree structure of weak classifiers

Pattern Recognition
Human Detection and Identification by Robots Using Thermal and Visual Information in Domestic Environments

Journal of Intelligent and Robotic Systems
Improving tracking algorithms using saliency

CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
A nonparametric Riemannian framework on tensor field with application to foreground segmentation

Pattern Recognition
Rapid pedestrian detection in unseen scenes

Neurocomputing
On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition

Image and Vision Computing
Conjugate gradient on Grassmann manifolds for robust subspace estimation

Image and Vision Computing
Boosted human re-identification using Riemannian manifolds

Image and Vision Computing
Advances in matrix manifolds for computer vision

Image and Vision Computing
Boosted translation-tolerable classifiers for fast object detection

Image and Vision Computing
Semi-supervised action recognition in video via Labeled Kernel Sparse Coding and sparse L1 graph

Pattern Recognition Letters
Augmented poselets for human body pose inference by a probabilistic graphical model

Proceedings of the 2nd ACM international workshop on Interactive multimedia on mobile and portable devices
Sparse coding and dictionary learning for symmetric positive definite matrices: a kernel approach

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Learning discriminative spatial relations for detector dictionaries: an application to pedestrian detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Manifold statistics for essential matrices

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Learning to match appearances by correlations in a covariance metric space

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
People orientation recognition by mixtures of wrapped distributions on random trees

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Semantic segmentation with second-order pooling

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Local descriptors encoded by fisher vectors for person re-identification

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Symmetry-driven accumulation of local features for human characterization and re-identification

Computer Vision and Image Understanding
Shadow Casting Out Of Plane (SCOOP) Candidates for Human and Vehicle Detection in Aerial Imagery

International Journal of Computer Vision
Simultaneous Bayesian clustering and feature selection using RJMCMC-based learning of finite generalized Dirichlet mixture models

Signal Processing
Adaptive discriminant learning for face recognition

Pattern Recognition
Classification of covariance matrices using a Riemannian-based kernel for BCI applications

Neurocomputing
Modeling local descriptors with multivariate gaussians for object and scene recognition

Proceedings of the 21st ACM international conference on Multimedia
A feature construction method for general object recognition

Pattern Recognition
Information-Theoretic dissimilarities for graphs

SIMBAD'13 Proceedings of the Second international conference on Similarity-Based Pattern Recognition
A multi-modal gesture recognition system using audio, video, and skeletal joint data

Proceedings of the 15th ACM on International conference on multimodal interaction
Kernel analysis on Grassmann manifolds for action recognition

Pattern Recognition Letters
Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Finite asymmetric generalized Gaussian mixture models learning for infrared object detection

Computer Vision and Image Understanding
People reidentification in surveillance and forensics: A survey

ACM Computing Surveys (CSUR)
Macrofeature layout selection for pedestrian localization and its acceleration using GPU

Computer Vision and Image Understanding
Creating robust high-throughput traffic sign detectors using centre-surround HOG statistics

Machine Vision and Applications

Quantified Score

Hi-index	0.14

Visualization

Abstract

We present a new algorithm to detect pedestrian in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, well known machine learning techniques are not well suited to learn the classifiers. The space of d-dimensional nonsingular covariance matrices can be represented as a connected Riemannian manifold. The main contribution of the paper is a novel approach for classifying points lying on a connected Riemannian manifold using the geometry of the space. The algorithm is tested on INRIA and DaimlerChrysler pedestrian datasets where superior detection rates are observed over the previous approaches.