Localized region context and object feature fusion for people head detection

@article{Li2016LocalizedRC,
  title={Localized region context and object feature fusion for people head detection},
  author={Yule Li and Y. Dou and Xinwang Liu and Teng Li},
  journal={2016 IEEE International Conference on Image Processing (ICIP)},
  year={2016},
  pages={594-598}
}
  • Yule Li, Y. Dou, +1 author Teng Li
  • Published 2016
  • Computer Science
  • 2016 IEEE International Conference on Image Processing (ICIP)
  • People head detection in crowded scenes is challenging due to the large variability in clothing and appearance, small scales of people, and strong partial occlusions. Traditional bottom-up proposal methods and existing region proposal network approaches suffer from either poor recall or low precision. In this paper, we propose to improve both the recall and precision of head detection of region proposal models by integrating the local head information. In specific, we first use a region… CONTINUE READING
    Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture
    • 9
    • Highly Influenced
    • PDF
    HeadNet: An End-to-End Adaptive Relational Network for Head Detection
    • 10
    Scale Mapping and Dynamic Re-Detecting in Dense Head Detection
    • 2
    Head pose estimation with neural networks from surveillant images
    Representations, Analysis and Recognition of Shape and Motion from Imaging Data

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES
    Context-Aware CNNs for Person Head Detection
    • 79
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,437
    • Highly Influential
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,444
    • PDF
    Edge Boxes: Locating Object Proposals from Edges
    • 2,023
    • PDF
    Histograms of oriented gradients for human detection
    • 25,735
    • PDF
    Object Detection with Discriminatively Trained Part Based Models
    • 8,333
    • Highly Influential
    • PDF
    OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
    • 3,615
    • PDF
    Selective Search for Object Recognition
    • 3,583
    • PDF
    BING: Binarized normed gradients for objectness estimation at 300fps
    • 321
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,395
    • PDF