Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Advanced Bounding Box Prediction With Multiple Probability Map

  • Lee, Poo-Reum (Dept. of Computer and Communications Engineering, Kangwon National University) ;
  • Kim, Yoon (Dept. of Computer and Communications Engineering, Kangwon National University)
  • Received : 2017.11.22
  • Accepted : 2017.12.09
  • Published : 2017.12.29
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a bounding box prediction algorithm using multiple probability maps to improve object detection result of object detector. Although the performance of object detectors has been significantly improved, it is still not perfect due to technical problems and lack of learning data. Therefore, we use the result correction method to obtain more accurate object detection results. In the proposed algorithm, the preprocessed bounding box created as a result of object detection by the object detector is clustered in various form, and a conditional probability is given to each cluster to make multiple probability map. Finally, multiple probability map create new bounding box of object using morphological elements. Experiment results show that the newly predicted bounding box reduces the error in ground truth more than 45% on average compared to the previous bounding box.

Keywords

References

  1. S. W. Jang, S. W. Byun, "Robust Detection of Body Area Using an Adaboost Algorithm," Journal of the Korea Academia-Industrial, Vol. 17, No. 11, pp. 403-409, June 2017.
  2. Pedro F. Felzenszwalb, Ross B. Girshick, "Object Detection with Discriminatively Trained Part Based Models," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 32, No. 9, pp. 1627-1645, Sep. 2009. https://doi.org/10.1109/TPAMI.2009.167
  3. Joseph Redmon, Santosh Divvala, "You Only Look Once: Unified, Real-Time Object Detection," Computer Vision and Pattern Recognition (CVPR), June 2016.
  4. Y. Y. Boykov, M. P. Jolly, "Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images," Proceedings of Internation Conference on Computer Vision, Vol. 1, pp. 105-112, July 2001.
  5. H. J. Park, K. B. Kim, "Improved k-means Color Quantization based on Octree," Joural of The Korea Society of Computer and Information, Vol. 20, No. 12, Dec. 2015.
  6. Dawei Yang, Lin Mao, "A Superpixel Segmentation Algorithm with Region Correlation Saliency Analysis for Video Pedestrian Detection", 36th Chinese Control Conference (CCC), pp. 5396-5399, Sep. 2017
  7. Brian Fulkerson, Andrea Vedaldi, "Class segmentation and object localization with superpixel neighborhoods," IEEE 12th International Conference on Computer Vision, pp.670-677, Oct. 2009.
  8. Xiaodi Hou, Liqing Zhang, "Saliency Detection: A Spectral Residual Approach," IEEE Conference on Computer Vision and Pattern Recognition, pp.1-8, June 2007.
  9. Hiba Ramadan, Hamid Tairi, "Pattern mining based video saliency detection," Intelligent Systems and Computer Vision (ISCV), pp.1-6, Oct. 2017.
  10. Xiaoou Tang, Heung-Yeung Shum, "Background Cut," ResearchGate, Jan. 1970.
  11. Nyma Alamgir, J. M. Kim, "Effective Image Segmentation using a Locally Weighted Fuzzy C-Means Clustering," Joural of The Korea Society of Computer and Information, Vol. 17, No. 12, Dec. 2012.
  12. C. Rother, V. Kolmogorov, A. Blake, "GrabCut - Interactive Foreground Extraction using Iterated Graph Cuts," ACM Transactions on Graphics(SIGGRAPH'04), Vol. 23, No. 3, pp. 309-314, August 2004.