Simultaneous estimation of 3D shape and motion of objects by computer vision

Schick, J.; Dickmanns, Ernst D.

doi:10.1109/wvm.1991.212799

Cited by 17 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work is closely related to prior work on model based tracking in computer vision [11,5,21,4,7,24,17,16]. However, the notion of a dynamic model in the tracking literature is different from the one presented here.…”

Section: Related Workmentioning

confidence: 95%

See 1 more Smart Citation

Computing the Physical Parameters of Rigid-Body Motion from Video

Bhat

Seitz

Popović

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents an optimization framework for estimating the motion and underlying physical parameters of a rigid body in free flight from video. The algorithm takes a video clip of a tumbling rigid body of known shape and generates a physical simulation of the object observed in the video clip. This solution is found by optimizing the simulation parameters to best match the motion observed in the video sequence. These simulation parameters include initial positions and velocities, environment parameters like gravity direction and parameters of the camera. A global objective function computes the sum squared difference between the silhouette of the object in simulation and the silhouette obtained from video at each frame. Applications include creating interesting rigid body animations, tracking complex rigid body motions in video and estimating camera parameters from video.

show abstract

Section: Related Workmentioning

confidence: 95%

“…In many instances, the dynamic model that relates the current and previous states is extremely simple [11,5]. However, they are sufficient for tracking rigid-body motions [11] or for navigation [5,21]. Kalman filters have also been successfully applied to track articulated [24] and non-rigid motion [16,17] in video.…”

Section: Related Workmentioning

confidence: 99%

Computing the Physical Parameters of Rigid-Body Motion from Video

Bhat

Seitz

Popović

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Polyhedral 3-D shape models with 12 independent shape parameters (see Figure 2.15 for four orthonormal projections as frequently used in engineering) have been investigated for road vehicle recognition [Schick 1992]. By specializing these parameters within certain ranges, different types of road vehicles such as cars, trucks, buses, vans, pickups, coupes, and sedans may be approximated sufficiently well for recognition [Schick, Dickmanns 1991;Schick 1992;Schmid 1993]. With these models, edge measurements should be confined to vehicle regions with small curvatures, avoiding the idealized sharp 3-D edges and corners of the generic model.…”

Section: Coarse-to-fine 3-d Shape Modelsmentioning

confidence: 99%

Dynamic Vision for Perception and Control of Motion

Dickmanns¹

2007

View full text Add to dashboard Cite

“…a) An autonomous vehicle can rapidly and accurately follow the markers on a road; it need not analyse the entire road scene, but need only detect and track the marker edges (Dickmanns & Graefe 1988a, b). By using additional domain-specific knowledge about the types of vehicles, their possible motions etc., significant improvements in 3-D object and motion estimation have been reported in Schick & Dickmanns (1991). b) An active observer, by shifting its line of sight so that the focus of expansion due to its motion occupies a sequence of positions, can robustly detect independent motion anywhere in the region surrounded by these foci (Sharma & Aloimonos 1991).…”

Section: Pick Your Problemmentioning

confidence: 99%

Current issues in computer vision

Chellappa

Rosenfeld

1993

Sadhana

View full text Add to dashboard Cite

The goal of computer vision is to derive descriptive information about a scene by computer analysis of images of the scene. Vision algorithms can often serve as computational models for biological visual processes, and they also have many practical uses; but this paper treats computer vision as a subject in its own right. Vision problems are often ill-defined, ill-posed, or computationally intractable; nevertheless, successes have been achieved in many specific areas-document processing and industrial inspection, for example. We suggest that by limiting the domain of application, carefully choosing the task, using redundant data (multi-sensor, multi-frame), and applying adequate computing power, useful solutions to many vision problems can be ob.tained. Methods of designing such solutions are the subject of the emerging discipline of vision engineering. With projected advances in sensor and computing technologies, the domains of applicability and ranges of problems that can be solved will gradually expand.

show abstract

Simultaneous estimation of 3D shape and motion of objects by computer vision

Cited by 17 publications

References 4 publications

Computing the Physical Parameters of Rigid-Body Motion from Video

Computing the Physical Parameters of Rigid-Body Motion from Video

Dynamic Vision for Perception and Control of Motion

Current issues in computer vision

Contact Info

Product

Resources

About