The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of Rotating Invariant Multi Object Detection System Applying MI-FL Based on SSD Algorithm

SSD 알고리즘 기반 MI-FL을 적용한 회전 불변의 다중 객체 검출 시스템 구현

  • Received : 2019.01.28
  • Accepted : 2019.04.04
  • Published : 2019.05.31
⟨ Previous Next ⟩

Abstract

Recently, object detection technology based on CNN has been actively studied. Object detection technology is used as an important technology in autonomous vehicles, intelligent image analysis, and so on. In this paper, we propose a rotation change robust object detection system by applying MI-FL (Moment Invariant-Feature Layer) to SSD (Single Shot Multibox Detector) which is one of CNN-based object detectors. First, the features of the input image are extracted based on the VGG network. Then, a total of six feature layers are applied to generate bounding boxes by predicting the location and type of object. We then use the NMS algorithm to get the bounding box that is the most likely object. Once an object bounding box has been determined, the invariant moment feature of the corresponding region is extracted using MI-FL, and stored and learned in advance. In the detection process, it is possible to detect the rotated image more robust than the conventional method by using the previously stored moment invariant feature information. The performance improvement of about 4 ~ 5% was confirmed by comparing SSD with existing SSD and MI-FL.

최근 CNN을 기반으로 한 객체 검출 기술의 연구가 활발하다. 객체 검출 기술은 자율주행차, 지능형 영상분석 등에서 중요한 기술로 사용된다. 본 논문에서는 CNN 기반의 객체 검출기 중 하나인 SSD(Single Shot Multibox Detector)에 MI-FL(Moment Invariant-Feature Layer)을 적용하여 회전 변형에 강인한 객체 검출 시스템을 제안한다. 먼저 VGG 네트워크를 기반으로 입력 이미지의 특징을 추출한다. 그 후 총 6개의 특징 계층(Feature layer)을 적용하여 객체의 위치 정보와 종류를 예측해 경계 박스들을 생성한다. 그 후 NMS 알고리즘을 이용해 가장 객체일 확률이 높은 경계 박스를 얻는다. 하나의 객체 경계 박스가 정해지면 MI-FL을 이용해 해당 영역의 불변 모멘트 특징을 추출하여 미리 저장하고 학습한다. 이후 검출 과정에서 미리 저장해둔 불면모멘트 특징 정보를 이용해 검출함으로써 회전된 이미지에 대해 기존 방법보다 더 강인한 검출이 가능하다. 기존의 SSD와 MI-FL을 적용한 SSD의 비교를 통해 약 4~5%의 성능 향상을 확인하였다.

Keywords

References

  1. P. Viola, and M. J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features", Proc. IEEE CVPR, Vol. 1, pp. 511-518, Dec. 2001.
  2. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection", IEEE Computer Society Conference on CVPR, pp. 886-893, June. 2005.
  3. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition", Proc. IEEE, pp. 2278-2323, Nov. 1998.
  4. K. Alex, S Ilya, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks", NIPS, Vol. 1, pp. 1097-1105, Dec. 2012.
  5. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition", In ICLR, May. 2015.
  6. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions", Proc. IEEE, CVPR, pp. 1-9, June. 2015.
  7. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition", Proc. IEEE, CVPR, pp. 770-778, June. 2016.
  8. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proc. IEEE, CVPR, pp. 580-587, June. 2014.
  9. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks", NIPS, Dec. 2015.
  10. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection", Proc. IEEE, CVPR, pp. 779-788, June. 2016.
  11. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed, "SSD: Single shot multibox detector", ECCV, pp 21-37, Oct. 2016.
  12. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The PASCAL Visual Object Classes (VOC) Challenge", IJCV, Vol. 88, No.2, pp. 303-338, June. 2010. https://doi.org/10.1007/s11263-009-0275-4
  13. M. K. Hu, "Visual pattern recognition by moment invariants", IRE Trans, Vol. 8, pp. 179-187, Feb. 1962.
  14. G.W. Kim, J.H. Park, H.Y. Lim, and Dae-Seong Kang, "A System Development on ASL Numbers Recognition Using Hierarchical Moment Invariants Based on Edge Image", JKIIT, Vol. 13, No. 4, pp. 37-43, Apr. 2015.
  15. J. Redmon, A. Farhadi, "Yolov3: An incremental improvement", arXiv preprint arXiv:1804.02767, Apr. 2018.