機械知覚&ロボティクスグループ
中部大学

Local Image Feature Human Detection 口頭発表

複数の特徴量間の関連性に着目したJoint-HOGによる物体検出

Author
藤吉弘亘, 山内悠嗣, 三井相和, 池村翔, 山下隆義
Publication
電気学会 一般産業研究会, pp. 51–56, 2008

Download: PDF (Japanese)

This paper presents a method for detecting people in a video using a Joint-HOG feature, which represents co-occurrence between multiple HOG features. Capturing the co-occurrence feature of Joint-HOG feature makes it possible to construct the effective human detector. We also describe effectiveness of multi-resolution HOG representation, co-occurrence of spatio-temporal features, and co-occurrence of depth information obtained by a TOF(Time of Flight) camera.

前の研究 次の研究