A new edge feature for head-shoulder detection

  title={A new edge feature for head-shoulder detection},
  author={Shu Wang and Jian Zhang and Zhenjiang Miao},
  journal={2013 IEEE International Conference on Image Processing},
  • Shu WangJian ZhangZ. Miao
  • Published 1 September 2013
  • Computer Science
  • 2013 IEEE International Conference on Image Processing
In this work, we introduce a new edge feature to improve the head-shoulder detection performance. Since Head-shoulder detection is much vulnerable to vague contour, our new edge feature is designed to extract and enhance the head-shoulder contour and suppress the other contours. The basic idea is that head-shoulder contour can be predicted by filtering edge image with edge patterns, which are generated from edge fragments through a learning process. This edge feature can significantly enhance… 

Figures from this paper

Head-shoulder human contour estimation in still images

Experimental results indicate that the proposed technique works well in non trivial images, effectively estimating the contour of the head-shoulder even under partial occlusions.

Improved Head-Shoulder Human Contour Estimation through Clusters of Learned Shape Models

Experimental results indicate that the proposed clustering-based learning approach to improve an existing model for human head-shoulder contour estimation outperformed the original model, which is based on a single shape model, learned in a more simple way.

Head-Shoulder Detection using Deep Autoencoders

The proposed head-shoulder detection algorithm is able to perform robustly with arbitrary camera's point of view and in any environment in real time on the CPU and comparable or slightly outperforms the state-of-the-art methods.

Robust Head-shoulder Detection using Deformable Part-based Models

A robust head-shoulder detector in 2-D images using deformable part-based models is proposed and it is shown that the model learned with this method outperforms other methods proposed in related work on an ambient assisted living application.

Real-time Human Detection based on Personness Estimation

This work finds that the normed gradients, designed for generic objectness estimation, are also able to rapidly generate high quality object windows for a single category object, and proposes an efficient method to produce candidate windows that are highly likely to contain a person.

Selfie Detection by Synergy-Constraint Based Convolutional Neural Network

This work proposes a novel approach to address the subtle problem of selfie detection for image database segregation on the web, given rapid rise in the number of selfies being clicked.

Deep Learning for People Detection on Beach Images

This work presents a study on three recent convolutional architectures for the task of people detection in beach scenarios and suggests that the Faster R-CNN meta-architecture with the Resnet 101 feature extractor generates significantly better detections in terms of F-measure.

A Comparison Between Various Human Detectors and CNN-Based Feature Extractors for Human Activity Recognition Via Aerial Captured Video Sequences

This paper aims to address the problem of human detection in aerial captured video sequences using a moving camera attached to an aerial platform with dynamical events such as varied altitudes, illumination changes, camera jitter, and variations in viewpoints, object sizes and colors.

Study on Method of Multi-feature Reduction Based on Rough Set in Passenger Counting

  • She Xiang-yangWang Hao-wei
  • Computer Science
    2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII)
  • 2016
Experimental results show that the proposed algorithm has a high statistical precision and good efficiency and is evaluated with several criterions.



Robust Head-Shoulder Detection by PCA-Based Multilevel HOG-LBP Detector for People Counting

This paper proposes a robust and rapid head-shoulder detector for people counting that can detect the head-shoulders of people robustly, even though there are partial occlusions occurred, and uses Principal Components Analysis to reduce the dimension of the multilevel HOG-LBP feature set.

Rapid and robust human detection and tracking based on omega-shape features

A novel method for rapid and robust human detection and tracking based on the omega-shape features of people's head-shoulder parts, which shows great robustness in scenarios of crowding, background distractors and partial occlusions is proposed.

An HOG-LBP human detector with partial occlusion handling

By combining Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) as the feature set, this work proposes a novel human detection approach capable of handling partial occlusion and achieves the best human detection performance on the INRIA dataset.

Pedestrian Detection: An Evaluation of the State of the Art

An extensive evaluation of the state of the art in a unified framework of monocular pedestrian detection using sixteen pretrained state-of-the-art detectors across six data sets and proposes a refined per-frame evaluation methodology.

Efficient, high-quality image contour detection

This work examines efficient parallel algorithms for performing image contour detection, with particular attention paid to local image analysis as well as the generalized eigensolver used in Normalized Cuts, and proposes a contour detector that provides uncompromised contour accuracy.

Hierarchical Part-Template Matching for Human Detection and Segmentation

A Bayesian approach to human detection and segmentation combining local part-based and global template-based schemes that relies on the key ideas of matching a part-template tree to images hierarchically to generate a reliable set of detection hypotheses and optimizing it under a Bayesian MAP framework.

Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors

  • Bo WuR. Nevatia
  • Computer Science
    Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
The human detection problem is formulated as maximum a posteriori (MAP) estimation, and edgelet features are introduced, which are a new type of silhouette oriented features that are learned by a boosting method.

Detecting Pedestrians by Learning Shapelet Features

A method of detecting pedestrians, presented by Payam Sabzmeydani and Greg Mori, and a comparison to a composition of Andreas Opelt, Axel Pinz and Andrew Zisserman.

Estimating the number of people in crowded scenes

The efficiency and robustness of the proposed method are demonstrated by using PETS 2009 dataset and it is shown that it can be used to estimate the number of people in crowded scenes without using explicit object segmentation or tracking.

From contours to regions: An empirical evaluation

This work provides extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations.