| J. K. Aggarwal and Q. Cai, "Human motion analysis: A review," Computer Vision and Image Understanding 73(3), pp. 428--440, 1999. |
....and an outlier process, was discussed in [41] In a different approach, Ferrari et al. 26] presented an affine tracker based on planar regions and anchor points. Tracking people, which raises many challenges due to the presence of large 3D, nonrigid motion, was extensively analyzed in [36] [1], 30] 73] Explicit tracking approaches of people [69] are timeconsuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to introduce a new framework for efficient tracking of nonrigid objects. We show that by ....
J. Aggarwal and Q. Cai, "Human Motion Analysis: A Review," Computer Vision and Image Understanding, vol. 73, pp. 428-440, 1999.
....the human body, and solve the dynamical equations of motion with a fast recursive algorithm. We applied the same method to track a hand by creating forces directly between the model and a 3D reconstruction of the hand. For more detailed descriptions of past works in the human tracking domain, see [1] and [14] 1.4. A summary of our method In this article we suppose that we have a 3D geometric model of the human body without texture (because we have no idea of its appearance) and that several views are available. See a description of our model in the section 2.1. We study two cases: the ....
J. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Proc. Nonrigid and Articulated Motion Workshop, pages 90-102, June 1997.
.... II: Human Motion Capture Human motion capture plays an important role in a wide spectrum of applications such as visual surveillance, performance measurement for atheletes and patients with disabilities, human computer interfaces, figure animation, and video conference (see Aggarwal et al. [57] for a general review) Many human motion capture devices need to employ special markers or magnetic sensor attachements around the joints of a subject. Thus, they impose physical restrictions on the subject. Vision based body part localization is a way to enable mark free human motion capture. ....
J.K. Aggarwal and Q. Cai, "Human Motion Analysis: A Review," IEEE Nonrigid and Articulated Motion Workshop, June 1997.
....of states using stochastic model based approaches. For example, hidden Markov models (HMMs) have become very popular for recognizing gestures [2, 12] sign language [17, 13] and actions [10, 18, 4] for a detailed review of these and other significant efforts in this direction, please review [1, 7]) However, when it comes to recognizing activities with some predefined context or inherent semantics, purely probabilistic methods can be limiting unless they are augmented by additional structure. These activities include parking cars or dropping off people at the curb (a visual surveillance ....
J.K. Aggarwal and Q. Cai. Human motion analysis: A review. CVIU, 73(3):428-- 440, March 1999.
....events, we imply that both the number of meaningful events and their whereabout in the scene are automatically learned and detected rather than manually labelled or hypothesised as mostly reported in the literature. Numerous efforts have been made to model moving object behaviours in general [1, 7]. Most previous approaches for modelling behaviour heavily relied upon segmentation and tracking of object in the scene [5, 6, 11, 12] A visual event is commonly defined based on a moving object with constraints on its size, colour or shape. A sequence of events is represented by the tracked ....
J.K. Aggarwal and Q. Cai. Human motion analysis: a review. CVIU, 73(3):428--440, 1999.
....information and an outlier process, was discussed in [41] In a different approach, Ferrari et al. 26] presented an affine tracker based on planar regions and anchor points. Tracking people, which rises many challenges due to the presence of large 3D, non rigid motion, was extensively analyzed in [36, 1, 30, 73]. Explicit tracking approaches of people [69] are time consuming and often the simpler blob model [75] or adaptive mixture models [53] are also employed. The main contribution of the paper is to introduce a new framework for efficient tracking of non rigid objects. We show that by spatially ....
J. Aggarwal and Q. Cai, "Human motion analysis: A review," Computer Vision and Image Understanding, vol. 73, pp. 428--440, 1999.
....surveillance system to subsequently invoke object specific motion analysis methods to generate more detailed descriptions of object behavior. There has been considerable interest in the area of human motion tracking in recent years [2] 6] 38] 43] 60] 67] More references can be found in [68], 69] Many human motion tracking algorithms assume that the size of the person in the image is large enough to track individual limbs. On the other hand, many surveillance applications involve more distant observations and a subsequent smaller number of pixels on target. We have developed a ....
J. K. Aggarwal and Q. Cai, "Human motion analysis: A review," Comput. Vis. Image Understand., vol. 73, pp. 428--440, Mar. 1999.
....at different tournaments with different players. 1 Introduction Analysis of human motion is a challenging problem mainly because of complexity of the motion. Many researchers work in the field of computer vision based human motion analysis. This is reflected in several surveys on this topic [1, 5, 4, 11], covering various areas of the field. The field of human motion analysis can be roughly divided into two areas: human motion acquisition (tracking) and classification, recognition and detection of human activity. Although most of the algorithms that deal with human activity classification work on ....
....concluding the paper, we will present results, which show that our findings are consistent over the large database of human motion data. 2 Human motion scale Classification of video based human motion analysis techniques is not uniform and largerly depends on interests of a particlular author [1, 5, 4]. There are some common points, for example the division to two large areas of motion analysis (analysis of whole body motion vs. analysis of motion of the body parts) since these two problems are seen as fundamentally different. Such classification forms a basis for definition of human motion ....
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. In Dimitris. Metaxas and Irfan. Essa, editors, IEEE Nonrigid and Articulated Motion Workshop, pages 90--102. IEEE Computer Society Press, 1997.
....projection by marking the body segments in an initial frame. For the special complexity of human motion, the existing research methods laid much limitation on human, such as a uniform and quiescent background, parallelism of human motion direction to the image plane, and skintight clothing of human[ 1 ]. From the view of motion analysis, our approach removes many restrictions as in the previous approaches. For example, it does not aim at a given human motion mode. Rather, it analyzes large motion from frame to frame in complex, variational background, and finally sets up a 3D human skeleton ....
Aggarwal, J. K. and Cai, Q. Human Motion Analysis: A Review. In Proceedings of the IEEE Nonrigid and Articulated Motion Workshop 1997. IEEE, Piscataway, NJ, USA.
....sequence into a static shape pattern. The most commonly used features for this technique are 2D meshes [8] Furthermore, these approaches also comprise motion energy images (MEI) and motion history images (MHI) which are presented in [4] A detailed review of human motion analysis can be found in [1]. The outline of this paper is given as follows. In the next section we introduce the tracking approach which is based on the Condensation algorithm [5] to trace an arbitrary, changing number of objects. In Section 3 we propose a self learning clustering method using the tracking results to build ....
J. K. Aggarwal and Q. Cai. Human Motion Analysis: A Review. Journal of Computer Vision and Image Understanding, Vol. 73, No. 3, March, pp. 428-440, 1999.
....over the past several decades. This has led to much interesting research performed in the areas of vision [5, 10] active vision [6] object recognition[7] and motion analysis [8, 11] to name just a few. Excellent surveys on methods for tracking human participants in virtual environments [24, 25] have appeared recently. So, to avoid unnecessary duplication, we simply ask interested readers to refer them. In this paper, we briefly mention the most recent efforts in this area. Narayanan et al. 23] use depth (range) images to create visible surface models but have Au: OK as in refs ....
....and in some cases mapped onto a synthetic, human like actor to represent an avatar of the participant. These approximations can add preciseness and robustness problems, as estimation of correspondences may not be reliable. Recently, a second research direction has been emerging as mentioned in [24, 25]. Basically, combinations of several tracking methods are suggested for resolving the correspondence problem. Some methods have already been implemented, for example, the Constellation system in [21] and the multisensor fusion approach in [22] We are pursuing a third alternative toward ....
J. Aggarwal and Q. Cai. Human motion analysis: A review, Comput. Vision Image Understand. 73, 1999, 428--440.
.... The extraction and characterization of human movement from video spans several research areas of computer vision, such as gesture recognition, action activity recognition, lipreading and person identification from gait (or gait recognition) Good comprehensive surveys on this topic are in [9, 1, 17]. Existing methods can be grouped into: i) structural methods, which recover a structural model of the human body and use this structure for motion recognition [23, 24, 2, 45, 18, 7, 36, 46] and (ii) non structural methods, which directly model, extract and recognize the motion patterns ....
J. K. Aggarwal and Q. Cai, "Human Motion Analysis: a Review," in Proc. of IEEE Computer Society Workshop on Motion of Non-Rigid and Articulated Objects, 1997.
....that best agrees with the location of the head, feet and hands found in the images. Hogg developed a system in which the geometric error between the projection of a model and edges detected in the image is minimized using hierarchical search. A survey of early results in the field can be found in [1]. A direct search of the model parameters in order to match the model projection with the images was presented in [12] In [19] three cameras are used for tracking in the presence of self occlusion and an extended Kalman filter is employed for motion prediction. The technique of exponential maps ....
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, San Juan, Puerto Rico, June 1997.
....food. We will use some terminology in this paper reflecting this motivation, such as referring to the human subject of the video clips as an employee. 2. Related Work There is a large body of work on the analysis of human motion reported in the literature. Please see two excellent surveys [1] and [3] for a detailed treatment of this subject. For a sample of recent work refer to the special section of IEEE PAMI on Video Surveillance [2] In the following, we briefly describe some sample work in this area, which is in no way exhaustive and complete. Bobick and Davis [9] describe a ....
Aggarwal, J. K. and Q. Cai, "Human Motion Analysis: A Review" Computer Vision Image Understanding, Vol.73, No.3, March, pp. 428-440, 1999.
....space one the different summaries. But, as can be seen in the following, large variations between the length of the different summaries can be observed. This is mainly due to the length of the papers, but also due to my interest in the individual papers. 4 Title: Human Motion Analysis: A Review [1] Author(s) J.K. Aggarwal and Q. Cai Location: Computer and Vision Research Center, University of Texas at Austin Year: 1997 Published: Workshop on Motion of Non Rigid and Articulated Objects, Puerto Rico, USA Type: Paper (Review) Key words: Overview and human motion Summary: This is an ....
J.K. Aggarwal and Q. Cai. Human Motion Analysis: A Review. In Workshop on Motion of Non-Rigid and Articulated Objects, Puerto Rico, USA, 1997.
....The last area is recognition of human movements. Here the input from e.g. a precise human motion tracking system is used to e.g. recognize whether a human is walking or running [126] or to recognize different dance steps [29] For a more general and thorough survey of body analysis see [32] [1] and [54] or read on : 7 1.4 Motion Capture The above three mentioned subclasses of the Looking at People domain all contain aspects where the motion of the human, or a part of him, needs to be obtained. This process is known as human motion capture. Even though the term covers all aspects ....
....An overview of work done within the area of human motion estimation and recognition with special focus on optical flow techniques is given in Ju [77] 1996) The overall taxonomy is motion estimation and motion recognition which again is divided into subclasses. In the survey by Aggarwal and Cai [1] (1997) the same taxonomy as in Cedras and Shah [32] is used even though they use different labels for the three classes. The three classes are each divided into subclasses yielding a rather comprehensive taxonomy. Recently a survey was done by Gavrila [54] 1999) He gives a good general ....
[Article contains additional citation context not shown here]
J.K. Aggarwal and Q. Cai. Human Motion Analysis: A Review. In Workshop on Motion of Non-Rigid and Articulated Objects, Puerto Rico, USA, 1997.
.... detection and tracking of h uman faces is a key component of video surveillance and monitoring systems [7] It pro vides input to high level processing such as recognition [21] access control, or re identification, or is used to initialize the analysis and classification of human activities [1, 13]. The head is one of the most easily recognizable human parts, ha ving a relatively constant color composition in certain color sub spaces [6, 27] a projection of elliptical shape in theimage frame, and distinct local features. Although the illumination conditions can thoroughly affect the face ....
J.K. Aggarwal, Q. Cai, "Human Motion Analysis: A Review," Computer Vision and Image Understanding, 73:428--440, 1999.
.... machine human interaction for identifying gestures, body movements, facial expressions and other characteristics of human motion and interactive behaviour is generally a highly difficult task that requires usually extensive computational resources and development time [Crowley 1997] Essa 1999] [Aggarwal and Cai 1999]. Also, most vision systems in robot human interaction highly constrain the position of the human with respect to the robot. Often the human is required to sit or stand in from of the robot cameras at a certain distance, cf. Breazeal et al. 2000] Different from such approaches (high computational ....
Aggarwal, J. K. and Cai, Q. (1999) Human motion analysis: a review, Computer Vision and Image Understanding 73(3): 428-440
No context found.
J. K. Aggarwal and Q. Cai, "Human motion analysis: A review," Computer Vision and Image Understanding 73(3), pp. 428--440, 1999.
No context found.
J. K. Aggarwal and Q. Cai "Human Motion Analysis: A Review " Computer Vision and Image Understanding,1999
No context found.
J.K. Aggarwal and Q. Cai. Human motion analysis: A review. CVIU, 73(3):428--440, 1999.
No context found.
J. Aggarwal and Q. Cai. Human Motion Analysis: A Review. CVIU, 73(3):428--440, 1999.
No context found.
J. K. Aggarval and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, Puerto Rico, June 17-19 1997.
No context found.
Aggarval, J. K. and Cai, Q. (1997), "Human Motion Analysis: A review", IEEE Nonrigid and Articulated Motion Workshop, pp. 90-102.
No context found.
J. K. Aggarval and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90-- 02, Puerto Rico, June 7- 9 997.
No context found.
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, Puerto Rico, June 17-19 1997.
No context found.
Aggarwal, J. K., Cai, Q., (1999), "Human Motion Analysis: A Review", Computer Vision and Image Understanding, Vol. 73, No. 3, pp. 428 - 440.
No context found.
Aggarwal , J.K., Cai, Q. (1999). Human motion analysis: A Review, Computer Vision and Image Understanding 73(3), p428--440.
No context found.
J. K. Aggarwal and Q. Cai, "Human motion analysis: A review," Computer Vision and Image Understanding 73(3), pp. 428--440, 1999.
No context found.
J.K. Aggarwal and Q. Cai, "Human motion analysis: a review", CVIU Journal, vol.73, no.3, pp.428-440, Mar. 1999
No context found.
Aggarwal J, Cai Q. (1997). Human Motion Analysis: A Review. Proceedings Nonrigid and Articulated Motion Workshop, Austin, Texas, IEEE
No context found.
J.K. Aggarwal and Q. Cai, "Human Motion Analysis: A Review ", in IEEE Nonrigid and Articulated Motion Workshop 1997.
No context found.
J. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Workshop on Non-Rigid and Articulated Motion, pages 90---102, 1997.
No context found.
J.K.Aggarwal and Q. Cai. Human motion analysis: A review. In Proc. of IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, 1997.
No context found.
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, San Juan, Puerto Rico, June 1997.
No context found.
Aggarwal, J. K., and Cai, Q. "Human Motion Analysis: A Review". Computer Vision & Image Under.: CVIU. 1999.
No context found.
Q. Cai and J. K. Aggarwal. Human motion analysis: a review. In Proc. of IEEE Computer Society Workshop on Motion of Non-Rigid and Articulated Objects, 1997.
No context found.
J.K. Aggarwal and Q. Cai, "Human motion analysis: a review", CVIU Journal, vol.73, no.3, pp.428-440, Mar. 1999
No context found.
J. K. Aggarwal and Q. Cai. "Human Motion Analysis: A Review", Journal of Computer Vision and Image Understanding, Vol. 73, No. 3, March, pp. 428-440, 1999.
No context found.
J. Aggarwal and Q. Cai, "Human motion analysis: A review," in Proc. of IEEE Nonrigid and Articulated Motion Workshop, 1997, pp. 90--102.
No context found.
J.K., Aggarwal and Q. Cai, "Human motion analysis: a review", Nonrigid and Articulated Motion Workshop, 1997.
No context found.
J. K. Aggarwal and Q. Cai. "Human Motion Analysis: A Review", Journal of Computer Vision and Image Understanding, Vol. 73, No. 3, March, pp. 428-440, 1999.
No context found.
J. K. Aggarwal and Q. Cai, "Human motion analysis: a review, " in Proc. of IEEE Computer Society Workshop on Motion of Non-Rigid and Articulated Objects, 1997.
No context found.
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. In IEEE Nonrigid and Articulated Motion Workshop, pages 90--102, San Juan, Puerto Rico, June 1997.
No context found.
Aggarwal J, Cai Q., "Human Motion Analysis: A Review", Proceedings Nonrigid and Articulated Motion Workshop, Austin, Texas, IEEE, 1997.
No context found.
J.K. Aggarwal and Q. Cai, "Human Motion Analysis: A Review," IEEE Nonrigid and Articulated Motion Workshop, June 1997.
No context found.
J. K. Aggarwal and Q. Cai. Human Motion Analysis: A Review. CVIU, 73(3):428--440, March 1999.
No context found.
J. K. Aggarwal and Q. Cai. Human motion analysis: A review. CVIU, 73(3):428--440, March 1999.
No context found.
J. K. Aggarwal, Q. Cai, "Human Motion Analysis: A Review," Computer Vision and Image Understanding, Vol. 73, pp. 428-440, 1999.
No context found.
J. Aggarwal and Q. Cai, "Human motion analysis: A review," Computer Vision and Image Understanding, vol. 73, pp. 428--440, 1999.
First 50 documents Next 50
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