• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1351-1355
• /
• 2016

The number of CCTV units is rapidly increasing annually, and the demand for intelligent video-analytics system is also increasing continuously for the effective monitoring of them. The existing analytics engines, however, require considerable computing resources and cannot provide a sufficient detection accuracy. For this paper, a light analytics engine was employed to analyze video and we collected metadata, such as an object's location and size, and the dwell time from the engine. A further data analysis was then performed to filter out the target of interest; as a result, it was possible to verify that a light engine and the heavy data analytics of the metadata from that engine can reject an enormous amount of environmental noise to extract the target of interest effectively. The result of this research is expected to contribute to the development of active intelligent-monitoring systems for the future.

• Journal of Korea Multimedia Society
• /
• v.13 no.1
• /
• pp.47-57
• /
• 2010

The object detection is essential for identifying objects, location information, and user context-aware in the image. In this paper, we propose a robust object detection system. The System linearly transforms learning data obtained from the background images to Principal components. It organizes the Eigen-background with the selected Principal components which are able to discriminate between foreground and background. The Fuzzy-C-means (FCM) carries out clustering for images with inputs from the Eigen-background information and classifies them into objects and backgrounds. It used various patterns of backgrounds as learning data in order to implement a system applicable even to the changing environments, Our system was able to effectively detect partial movements of a human body, as well as to discriminate between objects and backgrounds removing noises and shadows without anyone frame image for fixed background.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2179-2184
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper described 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• Journal of Digital Contents Society
• /
• v.9 no.1
• /
• pp.77-86
• /
• 2008

False sharing is a result of co-location of unrelated data in the same unit of memory coherency, and is one source of unnecessary overhead being of no help to keep the memory coherency in multiprocessor systems. Moreover, the damage caused by false sharing becomes large in proportion to the granularity of memory coherency. To reduce false sharing in page-based DSM systems, it is necessary to allocate unrelated data objects that have different access patterns into the separate shared pages. In this paper we propose sized and call-site tracing-based shared memory allocator, shortly SCSTallocator. SCSTallocator places each data object requested from the different call-sites into the separate shared pages, and at the same time places each data object that has different size into different shared pages. Consequently data objects that have the different call-site and different object size prohibited from being allocated to the same shared page. Our observations show that our SCSTallocator outperforms the existing dynamic shared memory allocators. By combining the two existing allocation technique, we can reduce a considerable amount of false sharing misses.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.8
• /
• pp.1535-1543
• /
• 2007

Recently, there are many researches for P2P network. P2P network technologies are a good solution about making a wide spread distributed computing in the internet environment. The recent algorithms developed by several research groups for the lookup problem present a simple and general interface, a distributed hash table (DHT). In this paper, we also introduce new schemes that enhance the available rate of an object in the MagicSquare network. Replication scheme is to replicate an object with many replicas and save them to several nodes. Fragmentation scheme is to divide an object into several fragments and save them to several nodes. Replicated Fragmentation scheme is to mix replication scheme and fragmentation scheme. We will show result of simulation for our the proposed scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.33-43
• /
• 2011

Recently, advances in mobile communication and location identifying technology of the moving object is evolving. Therefore, the location-based services based on request for service have increased and a variety of the indexing for the position management of moving objects has been studied. Because the index based on Euclidean space are no restriction of movement, it is difficult to apply to the real world. Also, there is additional cost to find adjacent road segments in road networks-based indexing. Existing studies of fixed static objects such as buildings or hospitals are not considered. In this paper, we propose an efficient road networks-based indexing for management of current positions. The proposed indexing partitions road networks by grids and has integrated road connection informations and manage separated extra indexing for fixed static objects. Through the experiment, we show that the proposed indexing based on road networks improves the performance of operation for search or update than existing indexing.

• The KIPS Transactions:PartD
• /
• v.16D no.2
• /
• pp.237-248
• /
• 2009

Recently, based on dynamic location or mobility of moving object, many researches on pattern mining methods actively progress to extract more available patterns from various moving patterns for development of location based services. The performance of moving pattern mining depend on how analyze and process the huge set of spatio-temporal data. Some of traditional spatio-temporal pattern mining methods[1-6,8-11]have proposed to solve these problem, but they did not solve properly to reduce mining execution time and minimize required memory space. Therefore, in this paper, we propose new spatio-temporal pattern mining method which extract the sequential and periodic frequent moving patterns efficiently from the huge set of spatio-temporal moving data. The proposed method reduces mining execution time of $83%{\sim}93%$ rate on frequent moving patterns mining using the moving sequence tree which generated from historical data of moving objects based on hash tree. And also, for minimizing the required memory space, it generalize the detained historical data including spatio-temporal attributes into the real world scope of space and time using spatio-temporal concept hierarchy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.