Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

A Framework for Human Body Parts Detection in RGB-D Image

RGB-D 이미지에서 인체 영역 검출을 위한 프레임워크

  • Hong, Sungjin (Sportainment Research Section, Creative Contents Research Division, SW.Contents Research Laboratory, Electronics and Telecommunications Research Institute) ;
  • Kim, Myounggyu (Sportainment Research Section, Creative Contents Research Division, SW.Contents Research Laboratory, Electronics and Telecommunications Research Institute)
  • Received : 2016.10.04
  • Accepted : 2016.11.23
  • Published : 2016.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper propose a framework for human body parts in RGB-D image. We conduct tasks of obtaining person area, finding candidate areas and local detection in order to detect hand, foot and head which have features of long accumulative geodesic distance. A person area is obtained with background subtraction and noise removal by using depth image which is robust to illumination change. Finding candidate areas performs construction of graph model which allows us to measure accumulative geodesic distance for the candidates. Instead of raw depth map, our approach constructs graph model with segmented regions by quadtree structure to improve searching time for the candidates. Local detection uses HOG based SVM for each parts, and head is detected for the first time. To minimize false detections for hand and foot parts, the candidates are classified with upper or lower body using the head position and properties of geodesic distance. Then, detect hand and foot with the local detectors. We evaluate our algorithm with datasets collected Kinect v2 sensor, and our approach shows good performance for head, hand and foot detection.

Keywords

References

  1. J. Shotton, R. Girshick, A. Fitzgibbon, T. Sharp, M. Cook, M. Finocchio, et al., "Efficient Human Pose Estimation from Single Depth Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 12, pp. 2821-2840, 2013. https://doi.org/10.1109/TPAMI.2012.241
  2. C. Plagemann, V. Ganapathi, D. Koller, and S. Thrun, "Real-time Identification and Localization," Proceeding of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 3108-3133, 2010.
  3. L.A. Schwarz, A. Mkhitaryan, D. Mateus, and N. Navab, "Estimating Human 3D Pose from Time-of-Flight Images Based on Geodesic Distances and Optical Flow," Proceeding of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 700-706, 2011.
  4. A. Baak, M. Müller, G. Bharaj, H.P. Seidel, and S. Theobalt, "A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera," Proceeding of IEEE International Conference on Computer Vision, pp. 71-98, 2011.
  5. Dijkstra's Algorithm in Wikipedia, https://en.wikipedia.org/wiki/Dijkstra%27s_algorithm, (accessed Aug., 28, 2016).
  6. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Computer Vision and Pattern Recognition, Vol. 1, pp. 886-893, 2005.
  7. P.F. Felzenszwalb, R.B. Girshick, D. McAllester, and D. Ramanan, "Object Detection with Discriminatively Trained Part Based Models," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 9, pp. 1627-1645, 2010. https://doi.org/10.1109/TPAMI.2009.167
  8. G. Jiang, J. Cheng, J. Pang, and Y. Guo, "Realtime Hand Detection Based on Multi-stage HOG-SVM Classifier," Proceeding of IEEE International Conference on Image Processing, pp. 4108-4111, 2013.
  9. C. Stoll, N. Hasler, J. Gall, H.P. Seidel, and C. Theobalt, "Fast Articulated Motion Tracking using a Sums of Gaussians Body Model," Proceeding of International Conference on Computer Vision, pp. 951-958, 2011.
  10. Quadtree in Wikipedia, https://en.wikipedia.org/wiki/Quadtree, (accessed Sep., 1, 2016).
  11. I.S. Oh, Pattern Recogntion, Kyobobook, Seoul, 2008.
  12. T.B. Nguyen, V.T. Nguyen, and S.T. Chung,, "A Real-time Pedestrian Detection based on AGMM and HOG for Embedded Surveillance," Journal of Korea Multimedia Society, Vol. 18, No. 11, pp. 1289-1301, 2015. https://doi.org/10.9717/kmms.2015.18.11.1289

Cited by

  1. Development of Dance Learning System Using Human Depth Information vol.18, pp.8, 2016, https://doi.org/10.9728/dcs.2017.18.8.1627
  2. Stochastic Remote Sensing Event Classification over Adaptive Posture Estimation via Multifused Data and Deep Belief Network vol.13, pp.5, 2021, https://doi.org/10.3390/rs13050912