Object Tracking in Video Pictures based on Image Segmentation and Pattern Matching

Morimoto, Takashi; Kiriyama, Osamu; Harada, Yuji; Adachi, H.; Koide, Tetsushi; Mattausch, Hans Jürgen

doi:10.1109/iscas.2005.1465312

Cited by 22 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For robust tracking of an object it utilizes features available on the tracked object together with additional parameters obtained from tracking the extended features detected in an image. The additional parameters used in tracking range from velocity of features [2,5,31], path of features [8,9,31], deformable shape of region [1,32,33], region color [29,34] and region sizes [35][36][37].…”

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

“…Utilizes Mahalanobis Distance with color information for tracking Teknomo et al [36] Color Tracking based on feature such as area, perimeter box width and color. Moritomo et al [37] Color Tracking based on area, width and height of blob, position and color of blob. Zivkovic et al [49] Color Uses Bhatacharrya Distance as similarity index for tracking purpose.…”

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

“…In addition to the existing tracking methods, color information is also used in tracking [7,29,36,37]. For robust tracking in color, the typical tracking method uses color [3,7,10] and region properties such as color of head region, height of head region, area, width, length, perimeter, shape and position [6,29,33,36,37,47]. Although color information adds robustness to object tracking it is also susceptible to brightness variations [10].…”

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

See 2 more Smart Citations

Colour Space Effect on Tracking in Video Surveillance

Sebastian¹,

Voon²,

Comley³

2010

ijeei

View full text Add to dashboard Cite

Abstract:The utilization of video surveillance systems is becoming common and is expected to more widespread as societies become more complex and the population continues to grow. The implementation of these video surveillance systems has provided valuable information and assistance in monitoring large areas. These systems typically use human operators to determine human behavior and to manually track people or objects of interest over an array of cameras. With the application of computers with video surveillance, real time surveillance of large public areas, people and their activities has been made possible for monitoring and security. The main contribution of this paper is to show the effect of color space on tracking methods in video surveillance. Results from evaluations on different tracking methods have indicated that YCbCr and HSV color spaces have better tracking ability compared to grayscale and RGB color spaces. In addition, the results from evaluations have also indicated that data from selected layers in some color spaces can be used for the purpose of tracking namely the Cb and Cr layers from the YCbCr color space and the H layer from the HSV color space.Keywords: Video, Tracking, Video Surveillance, Tracking Metrics, Color space IntroductionThe utilization of video surveillance systems is becoming common and is expected to more widespread as societies become more complex and the population continues to grow. In utilizing video surveillance in a large scale environment, it leads to problems in recognizing human behavior and tracking people over an array of cameras. The task of recognizing human behavior is difficult by itself and in adding the task of tracking a particular person or persons over an array of cameras makes the task even more difficult for a human operator.The motivation of this paper is to show how different color spaces effects the tracking performance of a video surveillance system. The paper is divided into 6 sections. Section 2 covers the fundamental background information related to colour spaces of images. Section 3 covers recent and related research work in tracking methodologies. Section 4 covers the experimental setup for evaluating the effect on tracking performance on different colour spaces. Section 5 covers the results of the experiments done in determining tracking performance in different colour spaces.

show abstract

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

Section: Related Work On Tracking Methodologiesmentioning

confidence: 99%

See 1 more Smart Citation

Colour Space Effect on Tracking in Video Surveillance

Sebastian¹,

Voon²,

Comley³

2010

ijeei

View full text Add to dashboard Cite

show abstract

“…Tracking of targets are based on parameters or features which can range from specific features such as edges, line, corners [5], limbs [6] and heads [7] to parameters of blobs that are being tracked such as size [8], trajectory [4], velocity [9] and color [10]. Based on some of the features and parameters used for tracking targets, tracking of targets can range from simple target tracking methods to more complex target tracking methods [5].…”

Section: Introductionmentioning

confidence: 99%

Parametric tracking of multiple segmented regions

Sebastian

Voon

Comley

2012

2012 International Symposium on Computer Applications and Industrial Electronics (ISCAIE)

View full text Add to dashboard Cite

This paper proposes a tracking method based on parameters obtained from multiple blobs. The multiple blobs are derived or obtained from segmenting a single blob into multiple blobs or multiple regions that have the same color information where these regions generally remain the same as the target moves. The target being tracked is a person or human walking through the camera view field where the number of regions are dependent on the clothing worn and the general build of the person being tracked. This would indicate that the head, limbs and torso of a person would be segmented into regions of interest. The parameters used in tracking a multiple region or blob target are the vectors between the regions of interest and the mean values of the regions of interest. In this paper, the vector used is derived from the top most region to the lowest region of the multi region target. In addition, the difference between the mean values of the regions is used as a means of tracking in addition to the vector between the regions of interest. The results obtained showed that correct target tracking had consistently higher tracking rate compared to incorrect tracking. Correct tracking rates had higher than 0.9 Track Detection Rate (TDR) rates as compared to incorrect tracking that ranged from 0 to 0.6.

show abstract

“…As a preprocessing of object-oriented image analysis [1][2][3][4] such as object tracking and object recognition, real-time image segmentation with low power consumption, high segmentation quality, and large-scale-image segmentation capability is required. We have previously reported a onedimensional scanning method for realizing region-growingbased image segmentation [5] and its efficient LSI implementation [6].…”

Section: Introductionmentioning

confidence: 99%

Architecture and FPGA-Implementation of Scalable Picture Segmentation by 2D Scanning with Flexible Pixel-Block Size

Koide

Kimura

Sugahara

et al. 2010

2010 First International Conference on Networking and Computing

Self Cite

View full text Add to dashboard Cite

We report a two-dimensional (2D) pixel block scanning architecture for image segmentation by segment growing. This architecture can optimize processing speed, power consumption, and circuit area by modifying size and shape of the pixel block. Real-time processing can be maintained by using additional the two important techniques of (i) boundary-scan of the grown segment only, (ii) continued block-internal segment growing. We analyze and optimize the size and shape trade-offs for the pixel block, and evaluate the proposed architecture by an FPGA. Altogether, the investigated architecture concepts reduce the area-time product by 52.3 % in comparison to a previously reported one-dimensional (1D) scanning architecture.

show abstract

Object Tracking in Video Pictures based on Image Segmentation and Pattern Matching

Cited by 22 publications

References 3 publications

Colour Space Effect on Tracking in Video Surveillance

Colour Space Effect on Tracking in Video Surveillance

Parametric tracking of multiple segmented regions

Architecture and FPGA-Implementation of Scalable Picture Segmentation by 2D Scanning with Flexible Pixel-Block Size

Contact Info

Product

Resources

About