全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

多方向线积分的梯度特征

DOI: 10.11834/jig.20111218

Keywords: 梯度特征,梯度方向直方图,多方向线积分,头肩检测

Full-Text   Cite this paper   Add to My Lib

Abstract:

典型的梯度特征包括HOG(梯度方向直方图)、Shapelet及Edgelet等,这些特征被广泛用于目标检测、目标识别、图像检索及场景分类等领域。针对HOG特征运算复杂度高的问题,提出了一种新的多方向线积分的梯度特征(MDIG)。通过避免计算梯度方向并利用积分图,该特征简化了计算过程,提高了计算速度,因而便于在DSP等硬件上实现。实验中新特征被应用于人体头肩检测。实验结果表明当使用AdaBoost算法训练分类器时,该特征的描述能力与HOG相当,同时其计算时间仅为HOG的1/3,整体性能优于HOG。最后,针对梯度特征的适用范围对其未来应用的发展方向进行了讨论。

References

[1]  Freund Yoav, Schapire Robert E. A decision-theoretic generalization of on-line learning and an application to boosting [J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139.
[2]  Dalal N, Triggs B. Histograms of oriented gradients for human detection //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Diego, CA: IEEE, 2005: 886-893.
[3]  Li M, Zhang Z, Huang K, et al. Rapid and robust human detection and tracking based on omega-shape features //Proceedings of IEEE International Conference on Image Processing. Cairo: IEEE, 2009: 2545-2548.
[4]  Lin Z, Davis L. Shape-based human detection and segmentation via hierarchical part-template matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 604-618.
[5]  Wu B, Nevatia R. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors //Proceedings of IEEE International Conference on Computer Vision. Beijing: IEEE, 2005: 90-97.
[6]  Papageorgiou C, Poggio T. A trainable system for object detection [J]. International Journal of Computer Vision, 2000, 38(1): 15-33.
[7]  Zhu Qiang, Avidan Shai, Yeh Mei Chen, et al. Fast human detection using a cascade of histograms of oriented gradients //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.New York, NY:IEEE, 2006: 1491-1498.
[8]  Friedman Jerome, Hastie Trevor, Tibshirani Robert. Additive logistic regression: A statistical view of boosting [J]. The Annals of Statistics, 2000, 28(2): 337-407.
[9]  Li M, Zhang Z, Huang K, et al. Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection //Proceedings of International Conference on Pattern Recognition. Tampa, FL: IEEE, 2008: 1-4.
[10]  Sabzmeydani P, Mori G. Detecting pedestrians by learning shapelet features //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN: IEEE, 2007: 1-8.
[11]  Wu B, Nevatia R. Tracking of multiple humans in meetings //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops. New York, NY: IEEE, 2006: 143-143.
[12]  Dollar Piotr, Wojek Christian, Schiele Bernt, et al. Pedestrian detection: A benchmark //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009: 304-311.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133