Baumberg, A. M. and Hogg, D. C. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, 1995.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....lead to a useful characterization of periodic motion. Hogg [16] was among the first to study the motion of a walking figure using an articulated model. There have recently been several attempts to recover characteristics of gait from image sequences, without the aid of annotation via lights [35, 5, 27, 28, 31, 32, 3, 4]. Niyogi and Adelson [27, 28] emphasize segmentation over a long sequence of frames. Their technique relies on recovering the boundaries of moving figures in the xt domain [27] and recently [28] xyt spatiotemporal solids, followed by fitting deformable splines to the contours. These splines are ....

....two representations further in Section 2.2. Baumberg and Hogg [3] present a method of representing the shape of a moving body at an instance in time. Their method produces a description composed of a set of principal spline components and a direction of motion. In later work, Baumberg and Hogg [4] add temporal variation by modeling the changing shape as a vibrating plate. They create a vibration model for a generic pedestrian and then are able to measure the quality of fit of the generic data to another pedestrian. Liu and Picard [22] detect and segment areas of periodic motion in ....

[Article contains additional citation context not shown here]

Baumberg, A. M. and Hogg, D. C. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, 1995.

....under large rotations in depth to be handled. Kalman ltering could be used to track the feature positions, thereby increasing robustness and allowing faster visual motion to be handled. Temporal aspects of deformation might be more directly incorporated using spatio temporal models (see e.g. [3]) ....

A. M. Baumberg and D. C. Hogg. Learning spatio-temporal models from training examples. Technical report, School of Computer Studies, University of Leeds, March 1995.

....spatial distributions of motion for a figure engaged in some activity. They are able to recognize different activities by comparing motion statistics computed over a coarse mesh. Baumberg and Hogg [3] give a method to describe the shape of a walking human body as a function of time. In later work [4], they describe the variation in the shape over time as the changing shape of a vibrating plate. Bobick and Davis [10] describe another non structural approach that analyzes the shape of a motion energy image (MEI) a summation of optical flow over a sequences of images. Features that describe ....

A. M. Baumberg and D. C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, March 1995.

....can be used to discriminate among differing activities. Baumberg and Hogg [2] present a method of representing the global shape of a moving body at an instant in time. Their method produces a description composed of a set of principal spline components and a direction of motion. In later work [3], Baumberg and Hogg add temporal variation by modeling the changing shape as a vibrating plate. They create a vibration model for a generic pedestrian and then measure the quality of fit of the generic data to another pedestrian. In contrast, a recent example of a structured approach is that of ....

A. M. Baumberg and D. C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, March 1995.

....Cootes and al. in [13] where flexible shape templates are fitted to data according to a statistical model of grey level information around model points. In a more recent study [14] Active Appearance Model (A.A.M. are used, modeling the object shape and gray level appearance. Baumberg and Hogg in [15] [16] use a Point Distribution Models of the shapes of walking pedestrians. The main characteristics of the body shapes deformations are captured by a Principal Component Analysis of these point sets. This approach is robust to occlusion, but it requires a background segmentation to allow the ....

Adam M. Baumberg and David C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, School of Computer Studies, Division of Artificial Intelligence, University of Leeds, March 1995.

....Hogg [Hog83] was among the first to study the motion of a walking figure using an articulated model. There have recently been several attempts to recover characteristics of gait from image sequences, without the aid of annotation via lights[Roh94, BDP 94, NA94b, NA94a, PN93, PN94, PN95, BH93, BH95] Niyogi and Adelson emphasize segmentation over a long sequence of frames [NA94b, NA94a] Their technique relies on recovering the boundaries of moving figures in the xt domain [NA94a] and recently [NA94b] xyt spatiotemporal solids, followed by fitting deformable splines to the contours. These ....

....will discuss these two representations further in Section 2.2. Baumberg and Hogg [BH93] present a method of representing the shape of a moving body at an instance in time. Their method produces a description composed of a set of principal spline components and a direction of motion. In later work [BH95] Baumberg and Hogg add temporal variation by modeling the changing shape as a vibrating plate. They create a vibration model for a generic pedestrian and then are able to measure the quality of fit of the generic data to another pedestrian. Liu and Picard [LP96] detect and segment areas of ....

[Article contains additional citation context not shown here]

A. M. Baumberg and D. C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, March 1995.

....under large rotations in depth to be handled. Kalman filtering could be used to track the feature positions, thereby increasing robustness and allowing faster visual motion to be handled. Temporal aspects of deformation might be more directly incorporated using spatio temporal models (see e.g. [3]) ....

A. M. Baumberg and D. C. Hogg. Learning spatio-temporal models from training examples. Technical report, School of Computer Studies, University of Leeds, March 1995.

....can be used to discriminate among differing activities. Baumberg and Hogg [2] present a method of representing the global shape of a moving body at an instant in time. Their method produces a description composed of a set of principal spline components and a direction of motion. In later work [3], BaumbergandHoggadd temporal variation by modeling the changing shape as a vibrating plate. They create a vibration model for a generic pedestrian and then measure the quality of fit of the generic data to another pedestrian. Bobick and Davis [5, 6] describe another non structural approach that ....

A. M. Baumberg and D. C. Hogg. Learning spatiotemporal models from training examples. Technical Report 95.9, University of Leeds School of Computer Studies, March 1995.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC