• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.6
• /
• pp.107-116
• /
• 2015

In compliance with digital device growth, the proliferation of high-tech computers, the availability of high quality and inexpensive video cameras, the demands for automated video analysis is increasing, especially in field of intelligent monitor system, video compression and robot vision. That is why object tracking of computer vision comes into the spotlight. Tracking is the process of locating a moving object over time using a camera. The consideration of object's scale, rotation and shape deformation is the most important thing in robust object tracking. In this paper, we propose a robust object tracking scheme using Random Forest. Specifically, an object detection scheme based on region covariance and ZNCC(zeros mean normalized cross correlation) is adopted for estimating accurate object location. Next, the detected region will be divided into five regions for random forest-based learning. The five regions are verified by random forest. The verified regions are put into the model pool. Finally, the input model is updated for the object location correction when the region does not contain the object. The experiments shows that the proposed method produces better accurate performance with respect to object location than the existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.27-38
• /
• 2006

The main purpose of rate control is to achieve the highest video quality when bandwidth or storage capacity is limited. For this purpose, we need a rate control algorithm which is adaptively controlled by the motion information of sequences, scene change, buffer capacity and time-varing bandwitdh channels. A rate-control method in the encoder requires the accurate estimation of target bit for each frame and the low end-to-end delay for transmitting video data by intelligent selection of encoding parameters. In this paper, we suggest three kinds of linear relation in the encoder to satisfy the characteristics of rate control. The first relation is that between the percentage of zero quantized transformed coefficients(p) and coded bits. Second relation is that between the PSNR of encoded frame and its Quantization parameter(QP). Finally, we can find out a linear approximation between QP and p. According to the experimental analysis, the proposed method results in an efficient rate control in terms of the bit estimation, the buffer capacity, and PSNR compared with the existing rate control in the H.264 JM 9.3.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.208-221
• /
• 2020

The objective of this study is to estimate and analyze the traffic density of continuous flow using the trajectory of individual vehicles and the headway of sample probe vehicles-front vehicles obtained from ADAS (Advanced Driver Assitance System) installed in sample probe vehicles. In the past, traffic density of continuous traffic flow was mainly estimated by processing data such as traffic volume, speed, and share collected from Vehicle Detection System, or by counting the number of vehicles directly using video information such as CCTV. This method showed the limitation of spatial limitations in estimating traffic density, and low reliability of estimation in the event of traffic congestion. To overcome the limitations of prior research, In this study, individual vehicle trajectory data and vehicle headway information collected from ADAS are used to detect the space on the road and to estimate the spatiotemporal traffic density using the Generalized Density formula. As a result, an analysis of the accuracy of the traffic density estimates according to the sampling rate of ADAS vehicles showed that the expected sampling rate of 30% was approximately 90% consistent with the actual traffic density. This study contribute to efficient traffic operation management by estimating reliable traffic density in road situations where ADAS and autonomous vehicles are mixed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.74-91
• /
• 2023

Several that analyzed the effectiveness of traffic safety facilities a method of comparing changes in the number of accidents, accident severity, speed through traffic accident data before and after installation or speed data collected from vehicle detection systems (VDS). , when traffic accident data is used, it takes a long time to collect because must be collected for at least one year before and after installation. , the road environment may change during this period, such as the addition of other traffic safety facilities in addition to the facilities to be analyzed. , the location of the VDSs for speed data is often different from the location where analysis is required, and there is a problem in that the investigators are exposed to the risk of traffic accident during on-site investigation. Therefore, this study a case study by establishing a methodology to determine effectiveness video images with a drone, extracting data using a program, and comparing vehicle driving speeds before and after speed reduction facilities. Vehicle speed surveys using drones are much safer than observational surveys conducted on highways and have the advantage of tracking speed changes along the vehicle, it is expected that they will be used for various traffic surveys in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.4
• /
• pp.87-98
• /
• 2011

Detecting a moving object from videos and tracking it are basic and necessary preprocessing steps in many video systems like object recognition, context aware, and intelligent visual surveillance. In this paper, we propose a method that is able to detect a moving object quickly and accurately in a condition that background and light change in a real time. Furthermore, our system detects strongly an object in a condition that the target object is covered with other objects. For effective detection, effective Eigen-space and FCM are combined and employed, and a CONDENSATION algorithm is used to trace a detected object strongly. First, training data collected from a background image are linear-transformed using Principal Component Analysis (PCA). Second, an Eigen-background is organized from selected principal components having excellent discrimination ability on an object and a background. Next, an object is detected with FCM that uses a convolution result of the Eigen-vector of previous steps and the input image. Finally, an object is tracked by using coordinates of an detected object as an input value of condensation algorithm. Images including various moving objects in a same time are collected and used as training data to realize our system that is able to be adapted to change of light and background in a fixed camera. The result of test shows that the proposed method detects an object strongly in a condition having a change of light and a background, and partial movement of an object.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.147-161
• /
• 2010

As broadcasting and communication are converged recently, communication is jointed to TV. TV viewing has brought about many changes. The IPTV (Internet Protocol Television) provides information service, movie contents, broadcast, etc. through internet with live programs + VOD (Video on demand) jointed. Using communication network, it becomes an issue of new business. In addition, new technical issues have been created by imaging technology for the service, networking technology without video cuts, security technologies to protect copyright, etc. Through this IPTV network, users can watch their desired programs when they want. However, IPTV has difficulties in search approach, menu approach, or finding programs. Menu approach spends a lot of time in approaching programs desired. Search approach can't be found when title, genre, name of actors, etc. are not known. In addition, inserting letters through remote control have problems. However, the bigger problem is that many times users are not usually ware of the services they use. Thus, to resolve difficulties when selecting VOD service in IPTV, a personalized service is recommended, which enhance users' satisfaction and use your time, efficiently. This paper provides appropriate programs which are fit to individuals not to save time in order to solve IPTV's shortcomings through filtering and recommendation-related system. The proposed recommendation system collects TV program information, the user's preferred program genres and detailed genre, channel, watching program, and information on viewing time based on individual records of watching IPTV. To look for these kinds of similarities, similarities can be compared by using ontology for TV programs. The reason to use these is because the distance of program can be measured by the similarity comparison. TV program ontology we are using is one extracted from TV-Anytime metadata which represents semantic nature. Also, ontology expresses the contents and features in figures. Through world net, vocabulary similarity is determined. All the words described on the programs are expanded into upper and lower classes for word similarity decision. The average of described key words was measured. The criterion of distance calculated ties similar programs through K-medoids dividing method. K-medoids dividing method is a dividing way to divide classified groups into ones with similar characteristics. This K-medoids method sets K-unit representative objects. Here, distance from representative object sets temporary distance and colonize it. Through algorithm, when the initial n-unit objects are tried to be divided into K-units. The optimal object must be found through repeated trials after selecting representative object temporarily. Through this course, similar programs must be colonized. Selecting programs through group analysis, weight should be given to the recommendation. The way to provide weight with recommendation is as the follows. When each group recommends programs, similar programs near representative objects will be recommended to users. The formula to calculate the distance is same as measure similar distance. It will be a basic figure which determines the rankings of recommended programs. Weight is used to calculate the number of watching lists. As the more programs are, the higher weight will be loaded. This is defined as cluster weight. Through this, sub-TV programs which are representative of the groups must be selected. The final TV programs ranks must be determined. However, the group-representative TV programs include errors. Therefore, weights must be added to TV program viewing preference. They must determine the finalranks.Based on this, our customers prefer proposed to recommend contents. So, based on the proposed method this paper suggested, experiment was carried out in controlled environment. Through experiment, the superiority of the proposed method is shown, compared to existing ways.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.19-36
• /
• 2015

Social media is an emerging issue in content services and in current business environment. YouTube is the most representative social media service in the world. YouTube is different from other conventional content services in its open user participation and contents creation methods. To promote a content in YouTube, it is important to understand the diffusion phenomena of contents and the network structural characteristics. Most previous studies analyzed impact factors of contents diffusion from the view point of general behavioral factors. Currently some researchers use network structure factors. However, these two approaches have been used separately. However this study tries to analyze the general impact factors on the view count and content based network structures all together. In addition, when building a content based network, this study forms the network structure by analyzing user comments on 22,370 contents of YouTube not based on the individual user based network. From this study, we re-proved statistically the causal relations between view count and not only general factors but also network factors. Moreover by analyzing this integrated research model, we found that these factors affect the view count of YouTube according to the following order; Uploader Followers, Video Age, Betweenness Centrality, Comments, Closeness Centrality, Clustering Coefficient and Rating. However Degree Centrality and Eigenvector Centrality affect the view count negatively. From this research some strategic points for the utilizing of contents diffusion are as followings. First, it is needed to manage general factors such as the number of uploader followers or subscribers, the video age, the number of comments, average rating points, and etc. The impact of average rating points is not so much important as we thought before. However, it is needed to increase the number of uploader followers strategically and sustain the contents in the service as long as possible. Second, we need to pay attention to the impacts of betweenness centrality and closeness centrality among other network factors. Users seems to search the related subject or similar contents after watching a content. It is needed to shorten the distance between other popular contents in the service. Namely, this study showed that it is beneficial for increasing view counts by decreasing the number of search attempts and increasing similarity with many other contents. This is consistent with the result of the clustering coefficient impact analysis. Third, it is important to notice the negative impact of degree centrality and eigenvector centrality on the view count. If the number of connections with other contents is too much increased it means there are many similar contents and eventually it might distribute the view counts. Moreover, too high eigenvector centrality means that there are connections with popular contents around the content, and it might lose the view count because of the impact of the popular contents. It would be better to avoid connections with too powerful popular contents. From this study we analyzed the phenomenon and verified diffusion factors of Youtube contents by using an integrated model consisting of general factors and network structure factors. From the viewpoints of social contribution, this study might provide useful information to music or movie industry or other contents vendors for their effective contents services. This research provides basic schemes that can be applied strategically in online contents marketing. One of the limitations of this study is that this study formed a contents based network for the network structure analysis. It might be an indirect method to see the content network structure. We can use more various methods to establish direct content network. Further researches include more detailed researches like an analysis according to the types of contents or domains or characteristics of the contents or users, and etc.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.3 s.8
• /
• pp.33-43
• /
• 2005

Traffic condition monitoring system serves as the foundation for all intelligent transportation system operation. Loop detectors and Video Image Processing are the most widely common technology approach to condition monitoring in korea Highways. Lane Usage is defined as the proportion of total link volume served by each lane. In this research, the lane Usage(LU) of two lane link for one day. Interval is 56% : 44%. The LU of three lane link is 39% : 37% : 24%. The LU of four lane link is 25% : 29% : 26% : 21%. These analysis reveal that each lane distributions of link are not same. This research investigates the general concept of lane usage by using collected loop detector data and the investigated that lane distribution is different by traffic lane and lane usage is consistent by time of day.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.133-148
• /
• 2014

Recently, with the advent of various information channels, the number of has continued to grow. The main cause of this phenomenon can be found in the significant increase of unstructured data, as the use of smart devices enables users to create data in the form of text, audio, images, and video. In various types of unstructured data, the user's opinion and a variety of information is clearly expressed in text data such as news, reports, papers, and various articles. Thus, active attempts have been made to create new value by analyzing these texts. The representative techniques used in text analysis are text mining and opinion mining. These share certain important characteristics; for example, they not only use text documents as input data, but also use many natural language processing techniques such as filtering and parsing. Therefore, opinion mining is usually recognized as a sub-concept of text mining, or, in many cases, the two terms are used interchangeably in the literature. Suppose that the purpose of a certain classification analysis is to predict a positive or negative opinion contained in some documents. If we focus on the classification process, the analysis can be regarded as a traditional text mining case. However, if we observe that the target of the analysis is a positive or negative opinion, the analysis can be regarded as a typical example of opinion mining. In other words, two methods (i.e., text mining and opinion mining) are available for opinion classification. Thus, in order to distinguish between the two, a precise definition of each method is needed. In this paper, we found that it is very difficult to distinguish between the two methods clearly with respect to the purpose of analysis and the type of results. We conclude that the most definitive criterion to distinguish text mining from opinion mining is whether an analysis utilizes any kind of sentiment lexicon. We first established two prediction models, one based on opinion mining and the other on text mining. Next, we compared the main processes used by the two prediction models. Finally, we compared their prediction accuracy. We then analyzed 2,000 movie reviews. The results revealed that the prediction model based on opinion mining showed higher average prediction accuracy compared to the text mining model. Moreover, in the lift chart generated by the opinion mining based model, the prediction accuracy for the documents with strong certainty was higher than that for the documents with weak certainty. Most of all, opinion mining has a meaningful advantage in that it can reduce learning time dramatically, because a sentiment lexicon generated once can be reused in a similar application domain. Additionally, the classification results can be clearly explained by using a sentiment lexicon. This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of movie reviews. Additionally, various parameters in the parsing and filtering steps of the text mining may have affected the accuracy of the prediction models. However, this research contributes a performance and comparison of text mining analysis and opinion mining analysis for opinion classification. In future research, a more precise evaluation of the two methods should be made through intensive experiments.