In the video analysis, the most important part in object detection and tracking is movement of object. The purpose is to detect the movement of object from the background image in video sequence and for the object tracking. This paper proposes a method to detect object based on background subtraction method. A reliable background updating model is established. Aoptimization threshold method is used to obtain behaviour of moving object and tracking. Motion of a moving object and tracking in a video stream is studied and detected. The centroid of object is computed to use in the analyses of the position of the moving human body. The experimental results show that the proposed method runs quickly, accurately and fits for the real-time detection.
Keywords |
Background subtraction, Object detection, Object tracking. |
INTRODUCTION |
A) Introduction |
The main aim of object tracking and detection is to establish a correspondence between object parts in consecutive
frames and to extract information about objects such as posture. Tracking detected objects frame by frame in video is a
significant and difficult task [1]. It is a crucial part of smart surveillance systems since without object tracking, the
system could not extract cohesive temporal information about objects and higher level behaviour analysis steps would
not be possible. Moving object detection is the first step in video analysis. Some of the applications are as follows [2]: |
(i) Visual surveillance: A human action recognition system process image sequences captured by video cameras
monitoring sensitive areas such as bank, departmental stores, parking lots and country border to determine whether one
or more humans engaged are suspicious or under criminal activity. |
(ii) Content based video retrieval: A human behavior understanding system scan an input video, and an action or event
specified in high-level language as output. This application will be very much useful for sportscasters to retrieve
quickly important events in particular games. |
(iii) Precise analysis of athletic performance: Video analysis of athlete action is becoming an importanttool for sports
training, since it has no intervention to the athletic. |
In all these applications fixed cameras are used with respect to static background and a common approach of
background subtraction is used to obtain an initial estimate of moving objects. First perform background modelling to
yield reference model. This reference model is used in background subtraction in which each video sequence is
compared against the reference model to determine possible variation. The variations between current video frames to
that of the reference frame in terms of pixels signify existence of moving objects. The variation which also represents
the foreground pixels are further processed for object localization and tracking. Ideally, background subtraction should
detect real moving objects with high accuracy and limiting false negatives (not detected) as much as possible. At the
same time, it should extract pixels of moving objects with maximum possible pixels, avoiding shadows, static objects
and noise [2]. |
The main objective of this paper is to develop an algorithm that can detect object motion and tracking. We carry out
various tasks such as motion detection, background modelling and subtraction, foreground detection, object tracking.
The rest of this paper is organized as follows. Section II describes the objectdetection using background subtraction
algorithm. Object tracking isperformed in Section III. Results are presented in sections IV, followed by conclusions on
section V. |
B) Literature Survey |
Visual surveillance is an active research topic in computer vision that tries to detect, recognize and track objects over a
sequence of images and it also makes an attempt to understand and describe object behavior by replacing the aging old
traditional method of monitoring cameras by human operators. A computer vision system, can monitor both immediate
unauthorized behavior and long term suspicious behavior, and hence alerts the human operator for deeper investigation
of the event [1]t. The video surveillance system can be manual, semi-automatic, or fully-automatic depending on the
human intervention. In manual video surveillance system, human operator responsible for monitoring does the entire
task while watching the visual information coming from the different cameras [7]. It’s a tedious and arduous job of an
operator to watch the multiple screens and at the same time to be vigilant from any unfortunate event. These systems
are proving to be ineffective for busy large places as the number of cameras exceeds the capability of human experts.
Such systems are in widespread across the world. The semi-automatic visual surveillance system takes the help of both
human operator and computer vision |
OBJECT DETECTION USING BACKGROUND SUBTRACTION |
To obtain background subtraction, the background has to model first. Then, the incoming frame is obtained, and
subtract out from the background model [5]. With the background model, a moving object can be detected. This
algorithm is called as “Background Subtraction” [10]. The efficiency of a background subtraction technique correlates
with three important steps: modelling, noise removal and data validation as shown in fig.1. |
Background modeling [3], is the backbone of the Background Subtraction algorithm. Background model defines the
type of model selected to represent the background, and the model representation can simply be a frame at time (t-1)
formula such as the median model. Model Adaption is the procedure used for adjusting the background changes that
may occur in a scene. Noise removal is a procedure that eliminates noise in the scene. Data validation is involved with
the collection of techniques to reduce the misclassification of pixels. In the recent papers, many background subtraction
algorithms are proposed, because no single algorithm is able to cope with all the challenges in the sports applications [10]. There are several problems that a good background subtraction algorithm must resolve. Therefore in this paper the
most commonly used, background subtraction algorithms are discussed. |
A Gaussian mixture model (GMM) was proposed for the background subtraction in Friedman and Russell, [6] and
efficient update equations are given in Stauffer and Grimson, [7]. In Power and Schoonees, [8] the GMM is extended
with a hysteresis threshold. This method uses a Gaussian probability density function to evaluate the pixel intensity
value. It finds the difference of the current pixel‟s intensity value and cumulative average of the previous values. So it
keeps a cumulative average (μ) of the recent pixel values. If the difference of the current image‟s pixel value and the
cumulative pixel value is greater than the product of a constant value and standard deviation then it is classified as
foreground [11]. That is, at each t frame time, the Ipixel‟s value can then be classified as foreground pixel if the
inequality: |It -μt| > k σ holds; otherwise, it can be considered as background, where k is a constant and σ is standard
deviation. Here background is updated as the running average: |
The proposed background subtraction method, we capture frames from camera. Then we model the (t-1) frame as a
background model which we are referring for the object detection & extraction from the current frame. |
OBJECT TRACKING BASED ON COLOURED OBJECT |
Object tracking means identifying & following same object in sequences of video frames. Camera is used as input
sensors to acquire frames to form the video. The acquired video may have some noise due to bad (light, wind, etc. or
due to problems in sensors). To remove noise from captured frames noise reduction technic is used to improve the
image quality, to detect moving object, based on colour of the moving object in frame. Extraction of objects from frame
using the different features is known as object detection. Every object has a specific feature based on its shape. |
Applying background extraction algorithm, the object in each frame can be extracted out. The camera is capturing
30fps. The implementation is initially performed on matlab and various methods for object tracking are tested. The
process of indicating the moving object in sequence of frames is known as tracking. This tracking can be performed by
using the feature extraction of objects and detecting the objects in sequence of frames. We are tracking the object are on
basic colour RGB, to be detected object in frame we differentiate gray scale input image frame with coloured image
frame to indicate coloured objet in video |
A. Rectangular Bounding Box |
A rectangular coloured bounding box is plotted around the foreground objects detected from GMM based Background
subtraction. By using the dimensions of rectangular bounding box, a centroid is plotted. The position of the centroid is
stored & object is bounded in box. |
RESULTS |
The proposed work has been developed using MATLAB on Intel dual core processor, 4GB RAM and Windows XP
SP2. The real time video sequences are acquired at the rate of 30 frames/second with the frame size of 640×360 pixels
resolution. |
CONCLUSION |
In this paper, a real-time video of moving object detection and tracking is proposed, based on background subtraction.
For object detection, we propose reliable background model, uses thresholding method to detect moving object and
update the background in real time. At last the moving object is tracked by finding colour. This method is beneficial for
time efficient, and it works well for small numbers of moving objects. Target detection and process is realized on the
video image. Video image data of the human body is processed, and its geometrical centroid is obtained in different
time intervals depending upon colour it are getting tracked. |
Figures at a glance |
![Click Here Figure](IJAREEIE-1748/IJAREEIE-1748-g001.gif) |
![Click Here Figure](IJAREEIE-1748/IJAREEIE-1748-g002.gif) |
![Click Here Figure](IJAREEIE-1748/IJAREEIE-1748-g003.gif) |
![Click Here Figure](IJAREEIE-1748/IJAREEIE-1748-g004.gif) |
Figure 1 |
Figure 2 |
Figure 3 |
Figure 4 |
|
References |
- Shih-Chia Huang,” An Advanced Motion Detection Algorithm with Video Quality Analysis for Video Surveillance Systems” IEEETRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 21, NO. 1, JANUARY 2011.
- PritiP.Kuralkar, Prof.V.T.Gaikwad,” Human Object Tracking using Background Subtraction and Shadow Removal Techniques,” in International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, No. 3, 2012.
- M. Hedayati, Wan Mimi Diyana Wan Zaki ,AiniHussain, “A Qualitative and Quantitative Comparison of Real-time Background Subtraction Algorithms for Video Surveillance Applications” Journal of Computational Information Systems “, pp 493 – 505, 2012.
- L. KoteswaraRao, K. Sivanagi Reddy, K. PradeepVinaik,” Implementation of Object Tracking and Velocity Determination”,in International Journal of Information Technology and Knowledge Management, Vol. 5, No. 1, 2012.
- A.McIvor, “Background subtraction techniques,” in Proceedings of Image and Vision Computing , Auckland, New Zealand, 2000.
- Friedman N., Russell, S, “Image segmentation in video sequences: a probabilistic approach”, In: Proc. 13th Conf. on Uncertainty in Artificial Intelligence, 1997.
- C.Stauffer, E.Grimson, “Adaptive background mixture models for real-time tracking”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2:246-252, 1999.
- Power, P.W., Schoonees, J.A., “Understanding background mixture models for foreground segmentation”, In: Proc. of the Image and Vision Computing New Zealand, 2002.
- Y. Benezeth, P.-M. Jodoin, B. Emile, H. Laurent, C. Rosenberger “Comparative study of background subtraction algorithms” Journal of Electronic Imaging, SPIE, vol. 19, 2010.
- M. Hedayati, Wan Mimi Diyana Wan Zaki ,AiniHussain, “A Qualitative and Quantitative Comparison of Real-time Background Subtraction Algorithms for Video Surveillance Applications” Journal of Computational Information Systems “, pp 493 – 505, 2012.
- Z.Zivkovic,”Improved adaptive Gausian mixture model for background subtraction”, IEEE International Conference on Pattern Recognition (ICPR), pp 28-31, 2004.
|