Spatial-temporal granularity-tunable gradients partition (STGGP) descriptors for human detection
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Multi-class classification on Riemannian manifolds for video surveillance
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Activities as time series of human postures
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Disparity statistics for pedestrian detection: combining appearance, motion and stereo
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
A monocular human detection system based on EOH and oriented LBP features
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
Pedestrian detection and tracking using HOG and oriented-LBP features
NPC'11 Proceedings of the 8th IFIP international conference on Network and parallel computing
Local response context applied to pedestrian detection
CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Segmentation of objects in a detection window by Nonparametric Inhomogeneous CRFs
Computer Vision and Image Understanding
Creating Picture Legends for Group Photos
Computer Graphics Forum
Detecting humans under partial occlusion using Markov logic networks
Proceedings of the 10th Performance Metrics for Intelligent Systems Workshop
An HOG-CT human detector with histogram-based search
Multimedia Tools and Applications
| Hi-index | 0.00 |
We present a learning-based, sliding window-style approach for the problem of detecting humans in still images. Instead of traditional concatenation-style image location-based feature encoding, a global descriptor more invariant to pose variation is introduced. Specifically, we propose a principled approach to learning and classifying human/non-human image patterns by simultaneously segmenting human shapes and poses, and extracting articulation-insensitive features. The shapes and poses are segmented by an efficient, probabilistic hierarchical part-template matching algorithm, and the features are collected in the context of poses by tracing around the estimated shape boundaries. Histograms of oriented gradients are used as a source of low-level features from which our pose-invariant descriptors are computed, and kernel SVMs are adopted as the test classifiers. We evaluate our detection and segmentation approach on two public pedestrian datasets.