Tracking algorithm for non-rigid objects based on the shape prediction

• Project/Area Number: 26330217
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Nishida Kenji 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (50344148)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Project Status: Completed (Fiscal Year 2017)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2014: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
• Keywords: オブジェクト・トラッキング / コンピュータ・ビジョン / パターン認識 / 画像処理 / スポーツ工学 / 姿勢推定

Outline of Final Research Achievements

A novel algorithm for tracking by shape with deforming prediction is proposed. The algorithm is based on the similarity of the predicted and actual object shape. Second order approximation for feature point movement by Taylor expansion is adopted for shape prediction, and the similarity is measured by using chamfer matching of the predicted and the actual shape. Chamfer matching is also used to detect the feature point movements to predict the object deformation. The proposed algorithm is applied to the tracking of a skier and showed a good tracking and shape prediction performance.

Research Products

• [Journal Article] Preindication Mining for Predicting Pedestrian.Action Change (2016)
  • Author(s): K.Nishida, T.Kobayashi, T.Iwamoto. S.Yamasaki
  • Journal Title: Computational Intelligence Volume: 669 Pages: 359-370
  • DOI: 10.1007/978-3-319-48506-5_18
  • ISBN: 9783319485041, 9783319485065
  • Peer Reviewed / Open Access
• [Journal Article] Accuracy Evaluation of Second-Order Shape Prediction on Tracking Non-Rigid Objects (2015)
  • Author(s): Kenji Nishida, Takumi Kobayashi, Jun Fujiki
  • Journal Title: International Journal on Advances in Systems and Measurements Volume: 8 Pages: 201-209
  • Peer Reviewed / Open Access / Acknowledgement Compliant
• [Journal Article] Video image recovery for occluded sklier's form by combining forward and backward prediction using motion feature (2015)
  • Author(s): Kenji Nishida, Takumi Kobayashi, Jun Fujiki
  • Journal Title: Science and Skiing Volume: 6 Pages: 251-259
  • Peer Reviewed
• [Journal Article] The Effect of 2nd-Order Shape Prediction on Tracking Non-Rigid Objects (2015)
  • Author(s): Kenji Nishida, Takumi Kobayashi, Jun Fujiki
  • Journal Title: Proc. 7th International Conference on Pervasive Patterns and Applications Volume: 1 Pages: 60-63
  • Peer Reviewed / Acknowledgement Compliant
• [Presentation] The Effect of 2nd-Order Shape Prediction on Tracking Non-Rigid Objects (2015)
  • Author(s): Kenji Nishida, Takumi Kobayashi, Jun Fujiki
  • Organizer: 7th International Conference on Pervasive patterns and Applications
  • Place of Presentation: ニース、フランス
  • Year and Date: 2015-03-22 – 2015-03-27