TY - GEN
T1 - New object detection for on-board robot vision by lifting complex wavelet transforms
AU - Takano, Shigeru
AU - Suzuki, Einoshin
PY - 2011/12/1
Y1 - 2011/12/1
N2 - This paper aims to develop a fast algorithm for detecting a new object from video sequences captured by onboard robot vision. We first propose lifting complex wavelet, which is a new method for extracting local features in an image. The proposed lifting complex wavelet transforms can be detected the features faster than the conventional SIFT algorithm. Our new object detection is performed by using an overlap ratio between the local features of current- and past-frames. In experiments, we show that new objects can be detected fast from on-board robot vision.
AB - This paper aims to develop a fast algorithm for detecting a new object from video sequences captured by onboard robot vision. We first propose lifting complex wavelet, which is a new method for extracting local features in an image. The proposed lifting complex wavelet transforms can be detected the features faster than the conventional SIFT algorithm. Our new object detection is performed by using an overlap ratio between the local features of current- and past-frames. In experiments, we show that new objects can be detected fast from on-board robot vision.
UR - http://www.scopus.com/inward/record.url?scp=84857152582&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84857152582&partnerID=8YFLogxK
U2 - 10.1109/ICDMW.2011.129
DO - 10.1109/ICDMW.2011.129
M3 - Conference contribution
AN - SCOPUS:84857152582
SN - 9780769544090
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 911
EP - 916
BT - Proceedings - 11th IEEE International Conference on Data Mining Workshops, ICDMW 2011
T2 - 11th IEEE International Conference on Data Mining Workshops, ICDMW 2011
Y2 - 11 December 2011 through 11 December 2011
ER -