Q. Cai, A. Mitiche, and J. K. Aggarwal, "Tracking human motion in an indoor environment," in Proc. IEEE Int. Conf. Image Processing, Oct. 1995, pp. 215--218.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....While these works present a wide range of di#erent methods, they can be classified into three main categories of increasing complexity: 1. Methods using region or blob based tracking, sometimes with additional classification schemes based on colour, texture or other local image properties [2 4, 6, 7]. 2. Methods using 2D appearance models of human beings [1, 5] 3. Methods using full 3D modelling of human beings [8, 9] Fig. 1. View from Surveillance Camera with Tracked Outline Shapes The more detailed the models for people detection and tracking, the better the system can handle the ....

Q. Cai, A. Mitiche, and J. K. Aggarwal, "Tracking human motion in an indoor environment," in Proceedings of the 2nd International Conference on Image Processing (ICIP'95), pp. 215--218, 1995.

....moving object, including persons, is to use some form of image subtraction to find motion regions. These motion regions are then classified as either noise or a person. Researchers such as [2] use the difference between consecutive video images to find the regions of motion. Others such as [3] and [4] use a background known to be empty of any moving objects (a reference image ) which is then subtracted from current or foreground images to find the motion regions. It should be noted that this use of a reference image is limited to fixed field of view cameras whereas the consecutive image ....

Q. Cai, A. Mitiche, and J. K. Aggarwal. "Tracking human motion in an indoor environment", 2nd Intl. Conf. on Image Processing, pages 215-218, Washington D.C., October 1995.

....Related Work Much work in the field of person detection and tracking is based on vision systems using stationary cameras [10] Most of them originate from virtual reality applications where one person moves in front of a stationary background. Moving objects are detected by subtracting two frames [9, 4]. These approaches often require that the tracked person is never occluded by other objects [1] Therefore they are typically not suitable for person following on a mobile robot since at the same time the robot tracks the person it has to move into the person s direction to stay close enough. ....

Q. Cai, A. Mitchie, and J.K. Aggarwal. Tracking human motion in an indoor environment. In 2nd International Conference on Image Processing, Oct. 1995.

.... International Conference on Pattern Recognition Type: Paper Key words: Multiple human tracking, multiple cameras, human model, double difference method, Mahalanobis distance and window slicing Summary: This paper is about tracking humans using multiple cameras and is based on previous work [18]. The human head is modeled by an ellipse having height width ratio of 1 to 1.5. the trunk is modeled as a rectangle with different ratios depending on the viewing angle. A human 14 is segmented from the background using the double difference method described in [18] Different non background ....

....and is based on previous work [18] The human head is modeled by an ellipse having height width ratio of 1 to 1.5. the trunk is modeled as a rectangle with different ratios depending on the viewing angle. A human 14 is segmented from the background using the double difference method described in [18]. Different non background objects are found in the following way. The horizontal and vertical profiles of the binary image is found. Then the valleys of the smoothed profiles defines the boundaries of the rectangle boxes containing non background objects. In each box a search for, first the head ....

[Article contains additional citation context not shown here]

Q. Cai, A. Mitiche, and J.K. Aggarwal. Tracking Human Motion in an Indoor Environment. In International Conference on Image Processing, 1995.

....1994 Guo et al. 61] 1994 Niyogi and Adelson [117] 1994 Polana and Nelson [126] 1994 Rossi and Bozzoli [129] 1994 Schneider and Bekker [130] Table 3.1: Publication before 1995. 19 Year Initialization Tracking Pose Estimation Recognition 1995 Cai et al. [28] 1995 Campbell and Bobick [29] 1995 Campbell and Bobick [30] 1995 Cedras and Shah [32] 1995 Freeman et al. 50] 1995 Goncalves et al. 58] 1995 Kakadiaris and Metaxas [81] 1995 Kameda et al. 85] 1995 Leung and Yang [98] 1995 ....

....In the work by Haritaoglu et al. 63] the aspect ration between the head, torso and legs are used to find, after a box representation, a blob representation of the hands, head, feet and torso. The same type of idea can be seen in e.g. Leung and Yang [96] Tesei et al. 136] and Cai and Aggarwal [28]. In the work by Leung and Yang [98] the same idea is expanded by the use of higher level of knowledge. The user s movements are assumed to be known and are used to label the different body parts and thereby finding the pose of the user. This idea of having key frames beforehand has also been ....

Q. Cai, A. Mitiche, and J.K. Aggarwal. Tracking Human Motion in an Indoor Environment. In International Conference on Image Processing, 1995.

....about subjects. The estimated pose of systems in this class is generally not very detailed. Typically positions of the head, hands, and feet or a rough description of the entire human body is used to represent the pose. A simple human model is the aspect ratios between the various limbs [20][53] which may be used to guide the pose estimation. In the work by Leung and Yang [89] the outline of the subject is estimated as edge regions described using 2D ribbons which are U shaped edge segments. A 2D ribbon model guides the labelling of the image data by searching for structures similar ....

Q. Cai, A. Mitiche, and J.K. Aggarwal. Tracking Human Motion in an Indoor Environment. In International Conference on Image Processing, 1995.

....back This research was supported in part by the Army Research Office under contracts DAAH04 95 I 0494 and DAAG55 98 1 0230 and by the Texas Higher Education Coordinating Board Advanced Research Project 97 ARP 275. ground, in which case the moving regions are used to identify and track objects [4]. Or, visual motion may imply a moving camera depicting a still background. 7] The combination of a moving camera and moving objects is the multiple motion problem, in which segmentation and egomotion estimation have to be solved at the same time. Existing approaches for the analysis of multiple ....

Q. Cai, A. Mitiche, and J. K. Aggarwal. Tracking human motion in an indoor environment. In Proceedings of the Second IEEE Conference on Image Processing, pages 215--218, Washington D.C., 1995.

....different types of information and this physical diversity aids in a better classification of the indoor environment into regions containing humans and those that are background. Detection and recognition of humans in such a scene is a challenging problem that has applications in various domains [2, 7]. As an interesting aside, it is worthy of note that snakes have infrared sensitive organs and use a combination of visual and thermal sensing while preying on other creatures. It has been hypothesized that a fusion center exists in the reptilian brain and that the input from different sensors are ....

Q. Cai, A. Mitiche, and J. K. Aggarwal. Tracking human motion in an indoor environment. In Proceedings of the Second IEEE Conference on Image Processing, pages 215--218, Washington D.C., 1995.

....of the bounding box was used as the feature to track. Positions of the center point in the previous frames were used to estimate the current position. Therefore, correct tracking was resolved even when the two subjects were occluded to each other in the middle of the image sequence. Cai et al. [10] also focused on tracking the movements of the whole human body using a viewing system with 2D translational movement. They focused on dynamic recovery of still or changing background images. The image motion of the viewing camera was estimated by matching the line segments of the background ....

Q. Cai, A. Mitiche, and J. K. Aggarwal. Tracking human motion in an indoor environment. In Proc. of 2nd Intl. Conf. on Image Processing, volume 1, pages 215--218, Washington, D.C., October 1995.

....buildings. This requires that the viewing system be able to image the tracked subject in a broad area over a long period of time. In pursuit of this goal, our work has evolved from studying human walking using a fixed camera [1, 2] to tracking non background objects in a single moving camera [3]. The studies in tracking using a fixed single camera [4, 2, 5] are limited to a very narrow area due to the restricted viewing angle of the system. A moving camera with a substantial degree of rotational freedom [3] increases the viewing angle to certain degree, however, it complicates the ....

....a fixed camera [1, 2] to tracking non background objects in a single moving camera [3] The studies in tracking using a fixed single camera [4, 2, 5] are limited to a very narrow area due to the restricted viewing angle of the system. A moving camera with a substantial degree of rotational freedom [3] increases the viewing angle to certain degree, however, it complicates the implementation by adding the motion estimation of both the viewing system and the subject of interest, and is still limited in the amount of viewing area. In this work, we chose to use multiple fixed cameras mounted in the ....

[Article contains additional citation context not shown here]

Q. Cai, A. Mitiche, and J. K. Aggarwal. Tracking human motion in an indoor environment. In 2nd Intl. Conf. on Image Processing, pages 215--218, Washinton, D.C., October 1995.

No context found.

Q. Cai, A. Mitiche, and J. K. Aggarwal, "Tracking human motion in an indoor environment," in Proc. IEEE Int. Conf. Image Processing, Oct. 1995, pp. 215--218.

No context found.

Cai, Q., Mitchie, A. and Aggarwal, J. K.: Tracking human motion in an indoor environment, in: Proc. of Internat. Conf. on Image Processing.

No context found.

Q. Cai, A. Mitiche and J. K. Aggarwal, "Tracking human motion in an indoor environment", ICIP Conference, vol.1, pp.215-218, Washington D.C., 1995.

No context found.

Cai, Q., Mitchie, A. and Aggarwal, J. K.: Tracking human motion in an indoor environment, in: Proc. of Internat. Conf. on Image Processing.

No context found.

Cai, Q., Mitchie, A. and Aggarwal, J. K.: Tracking human motion in an indoor environment, in: Proc. of Internat. Conf. on Image Processing.

No context found.

Q. Cai, A. Mitiche and J. K. Aggarwal, "Tracking human motion in an indoor environment", ICIP Conference, vol.1, pp.215-218, Washington D.C., 1995.

No context found.

Q. Cai, A. Mitchie, and J. K. Aggarwal. Tracking human motion in an indoor environment. In 2nd International Conference on Image Processing, October 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