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

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

DOI QR Code

An Efficient Feature Point Extraction Method for 360˚ Realistic Media Utilizing High Resolution Characteristics

  • Won, Yu-Hyeon (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Jin-Sung (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Park, Byuong-Chan (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Young-Mo (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Seok-Yoon (Dept. of Computer Science and Engineering, Soongsil University)
  • Received : 2018.12.03
  • Accepted : 2019.01.08
  • Published : 2019.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a efficient feature point extraction method that can solve the problem of performance degradation by introducing a preprocessing process when extracting feature points by utilizing the characteristics of 360-degree realistic media. 360-degree realistic media is composed of images produced by two or more cameras and this image combining process is accomplished by extracting feature points at the edges of each image and combining them into one image if they cover the same area. In this production process, however, the stitching process where images are combined into one piece can lead to the distortion of non-seamlessness. Since the realistic media of 4K-class image has higher resolution than that of a general image, the feature point extraction and matching process takes much more time than general media cases.

Keywords

CPTSCQ_2019_v24n1_85_f0001.png 이미지

Fig. 1. Process of SIFT Algorithm

CPTSCQ_2019_v24n1_85_f0002.png 이미지

Fig. 2. Directional Assignment Process are Extracted by The Gradient Direction and Size

CPTSCQ_2019_v24n1_85_f0003.png 이미지

Fig. 3. Generate Integral Image

CPTSCQ_2019_v24n1_85_f0004.png 이미지

Fig. 4. Hessian Detection Using Box Filter

CPTSCQ_2019_v24n1_85_f0005.png 이미지

Fig. 5. Haar-like Feature Detection Method

CPTSCQ_2019_v24n1_85_f0006.png 이미지

Fig. 6. How to Get Integral Image

CPTSCQ_2019_v24n1_85_f0007.png 이미지

Fig. 7. Process of Cascade classifier

CPTSCQ_2019_v24n1_85_f0008.png 이미지

Fig. 8. Stitching Area in The Image

CPTSCQ_2019_v24n1_85_f0009.png 이미지

Fig. 9. Preprocessing Algorithm

CPTSCQ_2019_v24n1_85_f0010.png 이미지

Fig. 10. Stitching Area Extraction Algorithm

CPTSCQ_2019_v24n1_85_f0011.png 이미지

Fig. 11. I-Frame Image Extracted from The Image 360-degree Video

CPTSCQ_2019_v24n1_85_f0012.png 이미지

Fig. 12. Preprocessed Algorithm to Image applied

CPTSCQ_2019_v24n1_85_f0013.png 이미지

Fig. 13. Haar-like Feature Learning Image

CPTSCQ_2019_v24n1_85_f0014.png 이미지

Fig. 14. Detecting the Stitching Area by Cascading Classifier

CPTSCQ_2019_v24n1_85_f0015.png 이미지

Fig. 15. Original Image Matching by ORB Algorithm

CPTSCQ_2019_v24n1_85_f0016.png 이미지

Fig. 16. Stitching Distortion Area Image Matching byORB Algorithm

Table 1. Performance Comparison of Original Image Extraction Algorithms

CPTSCQ_2019_v24n1_85_t0001.png 이미지

Table 2. Performance comparison of image extraction algorithms after preprocessing

CPTSCQ_2019_v24n1_85_t0002.png 이미지

Table 3. Performance Comparison Based On Robustness Feature Point Extraction Algorithms

CPTSCQ_2019_v24n1_85_t0003.png 이미지

Table 4. Extract the Stitching Area by Learning The Number of Images

CPTSCQ_2019_v24n1_85_t0004.png 이미지

Table 5. ORB Algorithm Matching Comparison

CPTSCQ_2019_v24n1_85_t0005.png 이미지

References

  1. Lowe, D.G., "Distinctive image features from scale-invari ant keypoints", IJCV 2004.
  2. P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai Hawaii, 2001.
  3. H. Bay, T. Tuytelaars, and L. Van Gool. "SURF: Speeded-up robust features", Computer vision and image Understanding, vol. 110, no. 3, pp. 346-359, 2008. https://doi.org/10.1016/j.cviu.2007.09.014
  4. M. Calonder, V. Lepetit, and P. Fua, "Brief: Binary robust independent elementary features", Computer Vision ? ECCV, vol. 6314, pp. 778-792, 2010.
  5. Rainer Lienhart and Jochen Maydt, "An Extended Set of Haar-like Features for Rapid Object Detection". IEEE ICIP 2002, Vol. 1, pp. 900?903, Sep. 2002. 3.
  6. E. Rosten and T. Drummond, "Machine Learning for High-Speed Corner Detection", European Conference on Computer Vision ECCV, pp. 430-443, 2006.
  7. D. Lowe, "Distinctive Image Features from Scale-Invari ant Keypoints", International Jounal of Computer Vision, vol. 60, pp. 91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  8. Jin-Sung Kim, "A Study on Image Feature Point Extraction for Realistic Contents", Journal of The Korea Society of Computer and Information, vol. 26, no. 2, pp. 385-386, 2018.
  9. Byung Woo Chung, "A Fast and Efficient Haar-Like Feature Selection Algorithm for Object Detection", Sogang University, Masters dissertation, 2013.
  10. Jong Seong Kim, "A Study on the Auto-Threshold Value Decision Method of Region Merging for Minimization of Over-segmentation in Image", Cheongju University, Masters dissertation, 2004.
  11. Soo Woong Jung, "A study on the efficient face retrieval system using SURF-based feature extraction", Chung-Ang University, Masters dissertation, 2012.
  12. Hoon Heo, "FPGA based Implementation of FAST and BRIEF algorithm for Object Recognition", Institute of Korean Electrical and Electronics Engineers, vol. 17, no. 2, pp. 202-207, 2013.
  13. Dark-programer, http://darkpgmr.tistory.com