• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.871-891
• /
• 2019

Visual tracking is a challenging task that needs learning an effective model to handle the changes of target appearance caused by factors such as pose variation, illumination change, occlusion and motion blur. In this paper, a novel tracking algorithm based on weighted local sub-space reconstruction error is presented. First, accounting for the appearance changes in the tracking process, a generative weight calculation method based on structural reconstruction error is proposed. Furthermore, a template update scheme of occlusion-aware is introduced, in which we reconstruct a new template instead of simply exploiting the best observation for template update. The effectiveness and feasibility of the proposed algorithm are verified by comparing it with some state-of-the-art algorithms quantitatively and qualitatively.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.1
• /
• pp.39-46
• /
• 2006

We propose an global color model based method for tracking motions of multiple human using a networked multiple-camera system in intelligent space as a human-robot coexistent system. An intelligent space is a space where many intelligent devices, such as computers and sensors(color CCD cameras for example), are distributed. Human beings can be a part of intelligent space as well. One of the main goals of intelligent space is to assist humans and to do different services for them. In order to be capable of doing that, intelligent space must be able to do different human related tasks. One of them is to identify and track multiple objects seamlessly. In the environment where many camera modules are distributed on network, it is important to identify object in order to track it, because different cameras may be needed as object moves throughout the space and intelligent space should determine the appropriate one. This paper describes appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.178-181
• /
• 2011

With the development of mobile devices and intelligent surveillance system loaded with pan/tilt cameras, object tracking with non-stationary cameras has become a topic with increasing importancy. Since it is difficult to model a background image in a non-stationary camera environment, colors and texture are the most important features in the tracking algorithm. However, colors in the background similar to those in the target arise instability in the tracking. Recently, we proposed a robust color based tracking algorithm that uses an area weighted centroid shift. In this letter, we update the model such that it becomes more stable against background colors. The proposed algorithm also incorporates time filtering by adding an additional energy term to the energy functional.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2120-2123
• /
• 2003

This paper presents the moving object detection and tracking algorithm using edge information base on human perceptual system The human visual system recognizes shapes and objects easily and rapidly. It's believed that perceptual organization plays on important role in human perception. It presents edge model(GCS) base on extracted feature by perceptual organization principal and extract edge information by definition of the edge model. Through such human perception system I have introduced the technique in which the computers would recognize the moving object from the edge information just like humans would recognize the moving object precisely.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.34-42
• /
• 1999

Multi-target tracking system is defined as tracking several targets simultaneously. Kalman filter is widely used for target tracking problems. Kalman filter is known to be extremely useful as an optimal estimator but has a shortcoming of computational complexity. So a simplified estimator model which had less computational burden is proposed for a real-time implementation of multi-target tracking systems. In this paper, Kalman filter is applied to implement a real-time tracking system with a simplified target model. The proposed Kalman filter model is simpler compared with those of conventional ones, greatly reducing computation time, yet keeping the tracking abilities of the optimal Kalman filter. Through both simulations and experiments with real environments, it is demonstrated that the proposed simplified model works good in real situation with multiple to be tracked.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.186-196
• /
• 2018

In this paper, we propose an on-line tracking method using convolutional neural network (CNN) for tracking object. It is well known that a large number of training samples are needed to train the model offline. To solve this problem, we use an untrained model and update the model by collecting training samples online directly from the test sequences. While conventional methods have been used to learn models by training samples offline, we demonstrate that a small group of samples are sufficient for online object tracking. In addition, we define a loss function containing color information, and prevent the model from being trained by wrong training samples. Experiments validate that tracking performance is equivalent to four comparative methods or outperforms them.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.2
• /
• pp.103-112
• /
• 2007

This study was designed to validate Spreading Activation Theory (SAT) for an evaluation methodology for menu structure through Eye-Tracking approach. When a visual search is on the way, more eye fixations and time are necessary to visually process complex and vague area. From the aspect of recognition, well-designed menu structures were hypothesized to have fewer numbers of fixations and shorter duration because well-designed menu structures reflecting the users' mental model would be well matched with the product's menu structure, resulting in reducing the number of fixations and duration time. The results show that the shorter reaction times for SAT had significantly fewer numbers of fixation and shorter duration time as the hypothesis for this study stated. In conclusion, SAT was proved to be an effective evaluation methodology for menu structure with the eye tracking equipment. In addition, using SAT instead of the real performance experiment would be useful for designing user-centered systems and convenient information structures because SAT was proven to be the theoretical background for design and evaluation of menu structures.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1411-1414
• /
• 2003

In this paper, vehicle tracking is implemented using parametric active contour. Extract objects from the background area is the essential step in vehicle tracking. We focus our algorithm on the situations such that the camera is fixed. However, if a simple and ordinary algorithm is adapted to achieve real-time processing, it produces much noise and the vehicle tracking results is poor. For this reason, in this paper, we propose a parametric active contour model algorithm to achieve better vehicle tracking. Experimental results show that the performance of the proposed algorithm is satisfactory.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.93-100
• /
• 2003

Accuracy in maneuvering target tracking using multiple models relies upon the suit-ability of each target motion model to be used. To construct multiple models, the interacting multiple model (IMM) algorithm and the adaptive IMM (AIMM) algorithm require predefined sub-models and predetermined acceleration intervals, respectively, in consideration of the properties of maneuvers. To solve these problems, this paper proposes the GA-based IMM method as an intelligent tracking method for a maneuvering target. In the proposed method, the acceleration input is regarded as an additive process noise, a sub-model is represented as a fuzzy system to compute the time-varying variance of the overall process noise, and, to optimize the employed fuzzy system, the genetic algorithm (GA) is utilized. The simulation results show that the proposed method has a better tracking performance than the AIMM algorithm.