• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.88-95
• /
• 2011

An embedded mobile device mostly has lower computation power than a general purpose computer because of its relatively lower system specifications. Consequently, conventional face tracking and face detection methods, requiring complex algorithms for higher recognition rates, are unsuitable in a mobile environment aiming for real time detection. On the other hand, by applying a real-time tracking and detecting algorithm, we would be able to provide a two-way interactive multimedia service between an user and a mobile device thus providing a far better quality of service in comparison to a one-way service. Therefore it is necessary to develop a real-time face and eye tracking technique optimized to a mobile environment. For this reason, in this paper, we proposes a method of tracking horizontal face position of a user on a T-DMB device for enhancing the quality of 3D DMB content. The proposed method uses the orientation of edges to estimate the left and right boundary of the face, and by the color edge information, the horizontal position and size of face is determined finally to decide the horizontal face. The sobel gradient vector is projected vertically and candidates of face boundaries are selected, and we proposed a smoothing method and a peak-detection method for the precise decision. Because general face detection algorithms use multi-scale feature vectors, the detection time is too long on a mobile environment. However the proposed algorithm which uses the single-scale detection method can detect the face more faster than conventional face detection methods.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.764-781
• /
• 2013

In this paper, we propose a highly precise vehicle detection method with low false alarm using billboard sweep stereo matching and multi-stage hypothesis generation. First, we capture stereo images from cameras established in front of the vehicle and obtain the disparity map in which the regions of ground plane or background are removed using billboard sweep stereo matching algorithm. And then, we perform the vehicle detection and tracking on the labeled disparity map. The vehicle detection and tracking consists of three steps. In the learning step, the SVM(support vector machine) classifier is obtained using the features extracted from the gabor filter. The second step is the vehicle detection which performs the sobel edge detection in the image of the left camera and extracts candidates of the vehicle using edge image and billboard sweep stereo disparity map. The final step is the vehicle tracking using template matching in the next frame. Removal process of the tracking regions improves the system performance in the candidate region of the vehicle on the succeeding frames.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.4
• /
• pp.495-502
• /
• 2003

This paper focuses on the implementation of an efficient tracking method of a moving object using optimal representative blocks by way of a pan-tilt camera. The key idea is derived from the fact that when the image size of a moving object is shrunk in an image frame according to the distance between the mobile robot camera and the object in motion, the tracking performance of a moving object can be improved by reducing the size of representative blocks according to the object image size. Motion estimations using Edge Detection (ED) and Block-Matching Algorithm (BMA) are regularly employed to track objects by vision sensors. However, these methods often neglect the real-time vision data since these schemes suffer from heavy computational load. In this paper, a representative block able to significantly reduce the amount of data to be computed, is defined and optimized by changing the size of representative blocks according to the size of the object in the image frame in order to improve tracking performance. The proposed algorithm is verified experimentally by using a two degree-of- freedom active camera mounted on a mobile robot.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.633-637
• /
• 2001

In this paper, we proposed model creation algorithm for multiple moving objects tracking. The proposed algorithm is divided that the initial model creation step as moving objects are entered into background image and the model reformation step in the moving objects tracking step. In the initial model creation step, the initial model is created by AND operating division image, divided using difference image and clustering method, and edge image of the current image. In the model reformation step, a new model was reformed in the every frame to adapt appearance change of moving objects using Hausdorff Distance and 2D-Logarithmic searching algorithm. We simulated for driving cart in the road. In the result, model was created over 98% in case of irregular approach direction of cars and tracking objects number.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.127-136
• /
• 2003

In this paper, we propose a robust object tracking algorithm based on model and edge, using deformed template and Level-Set theory. The proposed algorithm can track objects in case of background variation, object flexibility and occlusions. First we design a new potential difference energy function(PDEF) composed of two terms including inter-region distance and edge values. This function is utilized to estimate and refine the object shape. The first step is to approximately estimate the shape and location of template object based on the assumption that the object changes its shape according to the affine transform. The second step is a refinement of the object shape to fit into the real object accurately, by using the potential energy map and the modified Level-Set speed function. The experimental results show that the proposed algorithm can track non-rigid objects under various environments, such as largely flexible objects, objects with large variation in the backgrounds, and occluded objects.

• The Korean Journal of Physiology and Pharmacology
• /
• v.14 no.6
• /
• pp.413-417
• /
• 2010

To understand the function of edges in perception of moving objects, we defined four questions to answer. Is the focus point in visual motion detection of a moving object: (1) the body or the edge of the object, (2) the leading edge or trailing edge of the object, (3) different in scotopic, mesopic and photopic luminance levels, or (4) different for colored objects? We measured the Optomotor Response (OMR) and Edge Triggering Response (ETR) of goldfish. We used a square and sine wave patterns with black and red stripes and a square wave pattern with black and grey stripes to generate OMR's and ETR's in the goldfish. When we used black and red stripes, the black leading edges stimulated an ETR under scotopic conditions, red leading edges stimulated an ETR under photopic conditions, and both black and red leading edges stimulated an ETR under mesopic luminance levels. For black and gray stripes, only black leading edges stimulated an ETR in all three light illumination levels. We observed less OMR and ETR results using the sine wave pattern compared to using the square wave pattern. From these results, we deduced that the goldfish tend to prefer tracking the leading edge of the pattern. The goldfish can also detect the color of the moving pattern under photopic luminance conditions. We decided that ETR is an intriguing factor in OMR, and is suitable as a method of behavioral measurement in visual system research.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.10
• /
• pp.64-74
• /
• 2007

Because of the size and environment in the shipbuilding process, the portable type robot is required for the automatic seam tracking. For this reason, the structure of laser sensor should be considered in the initial design step and the coordinate transformation between welding robot and laser sensor, which is joint finder, must be identified exactly and the real time tracking algorithm based on these consideration could be developed. In this research, laser displacement sensor in which its structure is laser beam's vertical projection, is developed to recognize the location of weld joint. In practical applications, however, images of weld joints are often degraded because of the surface specularity or spatter. To overcome the problem, the constrained joint finding algorithm is proposed. In the approach of coordinate conversion rule for the visual feedback control among welding torch, robot body and laser sensor is applied by the same reference point method. In the real time seam tracking algorithms we propose constrained sampling method which uses look ahead distance. The RLS(Recursive Least Square) filter is applied to obtain the smooth tracking path from the sensitive edge data. From the experimental results, we could see the possibility that the developed laser sensor with proposed processing algorithm and real time seam tracking method can be used as a welding under the shipbuilding condition.

• Progress in Medical Physics
• /
• v.23 no.1
• /
• pp.8-14
• /
• 2012

In order to develop a Patient respiratory management system includinga biofeedback function for4-dimentional radiation therapy, this study investigated anoptimal tracking algorithmfor moving target using IR (Infra-red) camera as well as commercial camera. A tracking system was developed by LabVIEW 2010. Motion phantom images were acquired using a camera (IR or commercial). After image process were conducted to convert acquired image to binary image by applying a threshold values, several edge enhance methods such as Sobel, Prewitt, Differentiation, Sigma, Gradient, Roberts, were applied. The targetpattern was defined in the images, and acquired image from a moving targetwas tracked by matching pre-defined tracking pattern. During the matching of imagee, thecoordinateof tracking point was recorded. In order to assess the performance of tracking algorithm, the value of score which represents theaccuracy of pattern matching was defined. To compare the algorithm objectively, we repeat experiments 3 times for 5 minuts for each algorithm. Average valueand standard deviations (SD) of score were automatically calculatedsaved as ASCII format. Score of threshold only was 706, and standard deviation was 84. The value of average and SD for other algorithms which combined edge detection method and thresholdwere 794, 64 in Sobel, 770, 101 in Differentiation, 754, 85 in Gradient, 763, 75 in Prewitt, 777, 93 in Roberts, and 822, 62 in Sigma, respectively. According to score analysis, the most efficient tracking algorithm is the Sigma method. Therefore, 4-dimentional radiation threapy is expected tobemore efficient if threshold and Sigma edge detection method are used together in target tracking.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2605-2625
• /
• 2024

Siamese-based segmentation and tracking algorithms improve accuracy and stability for video object segmentation and tracking tasks simultaneously. Although effective, variability in target appearance and background clutter can still affect segmentation accuracy and further influence the performance of tracking. In this paper, we present a memory propagation-based target-aware and mask-attention decision network for robust object segmentation and tracking. Firstly, a mask propagation-based attention module (MPAM) is constructed to explore the inherent correlation among image frames, which can mine mask information of the historical frames. By retrieving a memory bank (MB) that stores features and binary masks of historical frames, target attention maps are generated to highlight the target region on backbone features, thus suppressing the adverse effects of background clutter. Secondly, an attention refinement pathway (ARP) is designed to further refine the segmentation profile in the process of mask generation. A lightweight attention mechanism is introduced to calculate the weight of low-level features, paying more attention to low-level features sensitive to edge detail so as to obtain segmentation results. Finally, a mask fusion mechanism (MFM) is proposed to enhance the accuracy of the mask. By utilizing a mask quality assessment decision network, the corresponding quality scores of the "initial mask" and the "previous mask" can be obtained adaptively, thus achieving the assignment of weights and the fusion of masks. Therefore, the final mask enjoys higher accuracy and stability. Experimental results on multiple benchmarks demonstrate that our algorithm performs outstanding performance in a variety of challenging tracking tasks.