Abstract:
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference funct...Show MoreMetadata
Abstract:
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using SVT for vehicle tracking in image sequences.
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 26, Issue: 8, August 2004)
MobileEye Vision Technologies Limited, Jerusalem, Israel
Shai Avidan received the BSc degree in mathematics and computer science from Bar-Ilan University, Ramat-Gan, Israel, in 1993, and the PhD degree from the Hebrew University, Jerusalem, Israel, in 1999. He was a postdoctoral fellow in the Vision Group at Microsoft Research, Redmond, Washington. He joined MobilEye in 2000 and, in addition, became a faculty member at the Interdisciplinary Center, Herzeliya, Israel. His resear...Show More
Shai Avidan received the BSc degree in mathematics and computer science from Bar-Ilan University, Ramat-Gan, Israel, in 1993, and the PhD degree from the Hebrew University, Jerusalem, Israel, in 1999. He was a postdoctoral fellow in the Vision Group at Microsoft Research, Redmond, Washington. He joined MobilEye in 2000 and, in addition, became a faculty member at the Interdisciplinary Center, Herzeliya, Israel. His resear...View more
Contents MobileEye Vision Technologies Limited, Jerusalem, Israel
Shai Avidan received the BSc degree in mathematics and computer science from Bar-Ilan University, Ramat-Gan, Israel, in 1993, and the PhD degree from the Hebrew University, Jerusalem, Israel, in 1999. He was a postdoctoral fellow in the Vision Group at Microsoft Research, Redmond, Washington. He joined MobilEye in 2000 and, in addition, became a faculty member at the Interdisciplinary Center, Herzeliya, Israel. His research interests are in computer vision, machine learning, and computer graphics. His previous work included work on multiview geometry and image-based rendering.
Shai Avidan received the BSc degree in mathematics and computer science from Bar-Ilan University, Ramat-Gan, Israel, in 1993, and the PhD degree from the Hebrew University, Jerusalem, Israel, in 1999. He was a postdoctoral fellow in the Vision Group at Microsoft Research, Redmond, Washington. He joined MobilEye in 2000 and, in addition, became a faculty member at the Interdisciplinary Center, Herzeliya, Israel. His research interests are in computer vision, machine learning, and computer graphics. His previous work included work on multiview geometry and image-based rendering.View more
