• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.4
• /
• pp.219-225
• /
• 2016

Visual object tracking is one of the key tasks in computer vision. Robust trackers should address challenging issues such as fast motion, deformation, occlusion and so on. In this paper, we therefore propose a visual object tracking method that exploits inter-frame correlations of convolutional feature maps in Convolutional Neural Net (ConvNet). The proposed method predicts the location of a target by considering inter-frame spatial correlation between target location proposals in the present frame and its location in the previous frame. The experimental results show that the proposed algorithm outperforms the state-of-the-art work especially in hard-to-track sequences.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.311-315
• /
• 2009

The ubiquitous smart home is the home of future that takes advantage of context information from user and home environment and provides automatic home services for the user. User's location and motion are the most important contexts in the ubiquitous smart home. This paper presents a method positioning user's location using four cameras and some home context parameter together with user preferences provided. Some geometry math problems would be raised to figure out approximately which area is monitored by cameras. The moving object is detected within the image frames and then simulated in a 2D window to present visually where user is located and show his moving. The moving ways are statistically recorded and used for predicting user's future moving.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.8
• /
• pp.766-772
• /
• 2015

This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.138-143
• /
• 2002

This paper describes a framework for extending GIS databases to support moving object data type and query language. The rapid progress of wireless communications, positioning systems, and mobile computing devices have led location-aware applications to be essential components for commercial and industrial systems. Location-aware applications require GIS databases system to represent moving objects and to support querying on the motion properties of objects. For example, fleet management applications may require storage of information about moving vehicles. Also, advanced CRM(Customer Relationship Management) applications may require to store and query the trajectories of mobile phone users. In this trend, maintaining consistent information about the location of continuously moving objects and processing motion-specific queries is challenging problem. We formally define a data model and query language for mobile objects that includes complex evolving spatial structure, and propose core algebra to process the moving object query language. Main profit of proposed moving objects query language and algebra is that proposed model can be constructed on the top of GIS databases.

• Journal of Advanced Navigation Technology
• /
• v.2 no.2
• /
• pp.107-115
• /
• 1998

In this paper, we propose a robust moving object tracking(MOT) method based on motion energy and prediction. MOT consists of two steps: moving object extraction step(MOES) and moving object tracking step(MOTS). For MOES, we use improved motion energy method. For MOTS, we predict the next location of moving object based on distance and direction information among previous instances, so that we can reduce the search space for correspondence. We apply the method to both synthetic and real world sequences and find that the method works well even in the presence of occlusion and disocclusion.

• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.336-344
• /
• 2012

As an important part of the Computer Vision, the object recognition and tracking function has infinite possibilities range from motion recognition to aerospace applications. One of methods to improve accuracy of the object recognition, are uses colors which have robustness of orientation, scale and occlusion. Computational cost for extracting features can be reduced by using color. Also, for fast object recognition, predicting the location of the object recognition in a smaller area is more effective than lowering accuracy of the algorithm. In this paper, we propose a method that uses SURF descriptors which applied with color model for improving recognition accuracy and combines with Kalman filter which is Motion estimation algorithm for fast object tracking. As a result, the proposed method classified objects which have same patterns with different colors and showed fast tracking results by performing recognition in ROI which estimates future motion of an object.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.1015-1017
• /
• 2013

Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns of both the object and the scene, non-rigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher-level applications that require the location or the shape of the object in every frame. This paper describes an object tracking system based on active vision with two cameras, into algorithm of single camera tracking system an object active visual tracking and object locked system based on Extend Kalman Filter (EKF) is introduced, by analyzing data from which the next running state of the object can be figured out and after the tracking is performed at each of the cameras, the individual tracks are to be fused (combined) to obtain the final system object track.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1405-1416
• /
• 1995

An effective algorithm for implementation of unmanned surveillance system which detects moving object from image sequences, predicts the direction of it, and drives the camera in real time is proposed. Outputs of proposed algorithm are coordinates of location of moving object, and they are converted to the values according to camera model. As a pre- processing, extraction of moving object and shape discrimination are performed. Existence of the moving object or scene change is detected by computing the temporal derivatives of consecutive two or more images in a sequence, and this result of derivatives is combined with the edge map from one original gray level image to obtain the position of moving object. Shape discri-mination(Target identification) is performed by analysis of distribution of projection profiles in x and y directions. To reduce the prediction error due to the fact that the motion cha- racteristic of walking man may have an abrupt change of moving direction, an order adaptive lattice structured linear predictor is proposed.

• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.1
• /
• pp.92-99
• /
• 2002

To obtain visual information of a target object, a camera should be placed within the visibility region. As the visibility region is dependent on the relative position of the target object and the surrounding object, the position change of the surrounding object during a task requires recalculation of the visibility region. For a fast computation of the visibility region so as to modify the camera position to be located within the visibility region, we propose a spherical projection method. After being projected onto the sphere the visibility region is represented in $\theta$-$\psi$ spaces of the spherical coordinates. The reduction of calculation space enables a fast modification of the camera location according to the motion of the surrounding objects so that the continuous observation of the target object during the task is possible.