Motion Tracking with an Active Camera

2014

Video surveillance systems have known significant growth because of the increased insecurity in these recent years. In order to reduce threats such as assaults, many cameras have invaded the public squares. The manual monitoring of these screens is tedious because of the large amount of information. So it is very interesting to automate this process from image processing systems able to extract the useful information from video sequences and interpret it. One of the most important tasks is the motion detection and estimation. This article aims to provide the status of art of the different techniques of motion detection estimation and segmentation based on movement. Many studies have been conducted on the subject and the literature is very abundant in this province, we are not trying to list all the existing methods. The idea is to give an overview of the most commonly used methods and to distinguish different types and approaches.

SMPTE Motion Imaging Journal, 2007

In order to insert a virtual object into a TV image, the graphics system needs to know precisely how the camera is moving, so that the virtual object can be rendered in the correct place in every frame. Nowadays this can be achieved relatively easily in postproduction, or in a studio equipped with a special tracking system. However, for live shooting on location, or in a studio that is not specially equipped, installing such a system can be difficult or uneconomic. To overcome these limitations, the MATRIS project is developing a real-time system for measuring the movement of a camera. The system uses image analysis to track naturally occurring features in the scene, and data from an inertial sensor. No additional sensors, special markers, or camera mounts are required. This paper gives an overview of the system and presents some results.

In this paper, we propose a real-time video-surveillance system for image sequences acquired by a moving camera. The system is able to compensate the background motion and to detect mobile objects in the scene. Background compensation is obtained by assuming a simple translation of the whole background from the previous to the actual frame. Dominant translation is computed on the basis of the tracker proposed by Shi-Tomasi and Tomasi-Kanade. Features to be tracked are selected according to a new intrinsic optimality criterion. Badly tracked features are rejected on the basis of a statistical test. The current frame and the related background, after compensation, are processed by a change detection method in order to obtain a binary image of moving points.Results are presented in the contest of a visual-based system for outdoor environments.

site.iugaza.edu.ps

The rapid development in the field of digital image processing made motion detection and tracking an attractive research topic. Until recent years, real-time video applications were inapplicable due to the expense computational time. An intelligent method to analyze the motion in a stream video line using the methods of background subtraction, temporal differencing, and optical flow, methods are proposed. The new method solves the computational time problem by using a reliable technique that is called Fast Pixels Selection. A low cost tracking system is proposed. This tracking system consist of camera, PC, motor and data acquisition card. This system is designed to detect and track any moving target automatically.

2017

Moving object recognition and detection is very crucial for video surveillance. In this paper, we present a comparative analysis between the various motion detection algorithms like background subtraction, Kalman filter, Mean Shift and Optical flow. The accumulative optical flow method is employed in order to obtain and retain a stable background image and cope with changes in environmental conditions. The performance of optical flow in terms of tracking and detection is much improved and accurate as compared to rest of the other algorithms.From the comparison it has been noted that the optical flow algorithm have outperformed the kalman and the mean shift algorithm .

Nowadays, video surveillance is indispensable in security-sensitive areas. Hence, a significant amount of work has been done in this field. This paper proposes a hybrid framework for motion region detection and an appearance-based real-time motion tracking system. Initially, a foreground map is extracted through a process of subtraction from a background model, applying a temporal differencing method. Then, shadow elimination and morphological operations are used to remove noise. Finally, models are initiated for each detected motion region by extracting features such as center of mass and a color correlogram, which are then used for tracking purposes. As the similarity in distances within a certain radius is measured, the probability of confusing objects is reduced considerably, and therefore, performance is optimized significantly. The proposed framework also uses a robust technique to label people within a group. This framework has the capability to work in indoor, semi-outdoor, and even outdoor environments that generate a penumbra shadow, and it handles the groups formed due to occlusion effectively. The framework takes good care of false foreground pixels due to penumbra shadow. Hence, the proposed framework will play a pivotal role in providing security in highly confidential areas.

Real-time detection of moving objects is vital for video surveillance. Background subtraction serves as a basic method typically used to segment the moving objects in image sequences taken from a camera. Some existing algorithms cannot fine-tune changing circumstances and they need manual calibration in relation to specification of parameters or some hypotheses for dynamic changing background. An adaptive motion segmentation and detection strategy is developed by using motion variation and chromatic characteristics, which eliminates undesired corruption of the background model and it doesn't look on the adaptation coefficient. In this particular proposed work, a novel real-time motion detection algorithm is proposed for dynamic changing background features. The algorithm integrates the temporal differencing along with optical flow method, double background filtering method and morphological processing techniques to achieve better detection performance. Temporal differencing is designed to detect initial motion areas for the optical-flow calculation to produce realtime and accurate object motion vectors detection. The double background filtering method is obtain and keep a reliable background image to handle variations on environmental changing conditions that is designed to get rid of the background interference and separate the moving objects from it. The morphological processing methods are adopted and mixed with the double background filtering to obtain improved results. The most attractive benefit for this algorithm is that the algorithm does not require to figure out the background model from hundreds of images and can handle quick image variations without prior understanding of the object size and shape.

Journal of Real-Time Image Processing, 2013

We propose a novel method for real-time camera motion tracking in planar view scenarios. This method relies on the geometry of a tripod, an initial estimation of camera pose for the first video frame, and a primitive tracking procedure. This process uses lines and circles as primitives, which are extracted applying CART (Classification and Regression Tree). We have applied the proposed method to HD (High Definition) videos of soccer matches. Experimental results prove that our proposal can be applied to processing high definition video in real time. We validate the procedure by inserting virtual content in the video sequence.

2003

In this paper we present a complete chain of algorithms for detection and tracking of moving objects using a static camera. The system is based on robust difference of images for motion detection. However, the difference of images does not take place directly over the image frames, but over two robust frames which are continuously constructed by temporal median filtering on a set of last grabbed images, which allows working with slow illumination changes. The system also includes a Kalman filter for tracking objects, which is also employed in two ways: assisting to the process of object detection and providing the object state that models its behaviour. These algorithms have given us a more robust method of detection, making possible the handling of occlusions as can be seen in the experimentation made with outdoor traffic scenes.

International Journal of Latest Trends in Engineering and Technology, 2018

Video surveillance system used to monitor areas sensitive to long safety. Finding videos, and providing useful information can be obtained in advance. Detection and tracking forms a most important usage in computer vision such as video observation, vision depends control, human-computer interfaces, medical picturing, augmented reality, and robotics. About moving object detection from an object control is a big step forward. Segmentation of objects, in a static environment is not complicated. In relation to dynamic changes in environmental conditions: wind, segmentation of objects, light, shade and branches of whispering trees should be treated as a powerful monitoring system is a difficult and important problem. Object tracking is to track an object (or multiple objects) over a order of picture. The segmentation of the object of interest of a video of the object and its movement, orientation, etc. The occlusion is defined as the course of the track in order to obtain useful information. Against the motion the problems that arise with the track of sharp objects, the object is changing, too, and the event is not to act against a hard object structures, object-to-scene Occlusions and movement of the camera. Tracking is usually performed in the context of higher-level applications that need the position and/or shape of the object in every frame. The analysis of objects in real time monitoring important exposure in the field of development and is more and more recently. Motion detection and object tracking method for the prevention of threats against the video surveillance system can also be used. Each tracking method or an object in each frame requires a mechanism to determine the formation of the first film or object. As part of an object in order to determine the general approach is the use of the data. However, some object detection, count a number of methods to reduce the number of false detections of the temporary use of information. Figure1: Object tracking method This temporal information is normally in the form of frame changing, which highlights changing area in successive frames. Tracking includes registering the actions of the segmented thing from starting frame to the end frame in a video.