• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.17 no.1
• /
• pp.47-54
• /
• 2013

This work deals with automatic motion detection for with surveillance tracking that aims to provide high-lighting movable objects which is discriminated from moving backgrounds such as moving trees, etc. For this aim, we perform a false background region detection together with an initial foreground detection. The false background detection detects the moving backgrounds, which become eliminated from the initial foreground detection. This false background detection is done by performing the bimodal segmentation on a deformed image, which is constructed using the information of the dominant colors in the background.

• International Journal of Aeronautical and Space Sciences
• /
• v.6 no.1
• /
• pp.8-16
• /
• 2005

This paper describes target detection performance of millimeter wave radar that exits on non-stationary target detection schemes in the ground clutter conditions. The comparison of various CFAR process schemes such as CA(Cell-Average)-CFAR, GO(Greatest Of)/SO(Smallest Of)-CFAR, and OS(Order Statistics)-CFAR performance are applied. Using matlab software, we show the performance and loss between target detection probability and signal to noise ratio. This paper concludes the OS-CFAR process performance is better than any others and satisfies the optimal detection probability without loss of detection in the homogeneous clutter, When range bins increase.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.12
• /
• pp.21-28
• /
• 2015

In this paper, we propose a method of glasses detection in facial image. we develop a detection method of glasses with a weighted sum of the results that detected by facial element detection and glasses frame candidate region. Component of the face detection method detects the glasses, by defining the detection probability of the glasses according to the detection of a face component. Method using the candidate region of the glasses frame detects the glasses, by defining feature of the glasses frame in the candidate region. finally, The results of the combined weight of both methods are obtained. The proposed method in this paper is expected to increase security system's recognition on facial accessories by raising detection performance of glasses or sunglasses for using ATM.

• ETRI Journal
• /
• v.24 no.2
• /
• pp.161-171
• /
• 2002

This paper proposes a novel decision feedback differential phase detection (DF-DPD) for M-ary DPSK. A conventional differential phase detection method for M-ary Differential Phase Shift Keying (DPSK) can simplify the receiver architecture. However, it possesses a poorer bit error rate (BER) performance than coherent detection because of the prior noisy phase sample. Multiple-symbol differential detection methods, such as maximum likelihood differential phase detection, Viterbi-DPD, and DF-DPD using L-1 previous detected symbols, have attempted to improve BER performance. As the detection length, L, increases, the BER performance of the DF-DPD improves but the complexity of the architecture increases dramatically. This paper proposes a simplified DF-DPD architecture replacing the conventional delay and additional architecture with an accumulator. The proposed architecture also improves BER performance by minimizing the current differential phase noise through the accumulation of previous differential phase noise samples. The simulation results show that the BER performance of the proposed architecture approaches that of a coherent detection with differential decoding.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.303-304
• /
• 2006

This paper proposes detection method of vehicles using camera for auto-vehicle-system. Detection method is based on shadow detection and symmetric feature of vehicle. This method consists of three part. First is lane detection. By lane detection, we can reduce the area for vehicle detection. Second part is shadow detection. Shadow has information of vehicle width and position. Third part is symmetry. This feature is helpful for confirming the vehicle.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.2
• /
• pp.110-114
• /
• 2015

This paper reports a novel object-detection technique in video sequences. The proposed algorithm consists of detection of objects in illuminated and occluded videos by using object features and a neural network technique. It consists of two functional modules: region-based object feature extraction and continuous detection of objects in video sequences with region features. This scheme is proposed as an enhancement of the Lowe's scale-invariant feature transform (SIFT) object detection method. This technique solved the high computation time problem of feature generation in the SIFT method. The improvement is achieved by region-based feature classification in the objects to be detected; optimal neural network-based feature reduction is presented in order to reduce the object region feature dataset with winner pixel estimation between the video frames of the video sequence. Simulation results show that the proposed scheme achieves better overall performance than other object detection techniques, and region-based feature detection is faster in comparison to other recent techniques.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.133-138
• /
• 2008

In this paper, we propose a novel anchor shot detection system, named to MASD (Multi-phase Anchor Shot Detection), which is a core step of the preprocessing process for the news video analysis. The proposed system is composed of four modules and operates sequentially: 1) skin color detection module for reducing the candidate face regions; 2) face detection module for finding the key-frames with a facial data; 3) vector representation module for the key-frame images using a non-negative matrix factorization; 4) one class SVM module for determining the anchor shots using a support vector data description. Besides the qualitative analysis, our experiments validate that the proposed system shows not only the comparable accuracy to the recently developed methods, but also more faster detection rate than those of others.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.652-661
• /
• 2017

A mention has a noun or noun phrase as its head and constructs a chunk that defines any meaning, including a modifier. Mention detection refers to the extraction of mentions from a document. In mentions, coreference resolution refers to determining any mentions that have the same meaning. Pointer networks, which are models based on a recurrent neural network encoder-decoder, outputs a list of elements corresponding to an input sequence. In this paper, we propose mention detection using pointer networks. This approach can solve the problem of overlapped mention detection, which cannot be solved by a sequence labeling approach. The experimental results show that the performance of the proposed mention detection approach is F1 of 80.75%, which is 8% higher than rule-based mention detection, and the performance of the coreference resolution has a CoNLL F1 of 56.67% (mention boundary), which is 7.68% higher than coreference resolution using rule-based mention detection.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.419-428
• /
• 2011

This paper suggests a judgement method for an inclined plane before entrance of it and the detection of obstacle position. Main idea is started from the assumption that obstacle is always on the bottom plane, and corner appears at this position. The process to detect the obstacle consists of three steps. First the 3D data using stereo matching is acquired to detect an obstacle. Second a bottom plane is extracted by using limit condition. Last the obstacle position is found by using Harris corner detection. Obstacle position detection on an inclined plane was verified by outdoor and indoor experiment. In error analysis, it is confirmed that an average error of obstacle detection in outdoor was larger than the error in indoor but the error are within about 0.030 m. This method will be applied to unmanned vehicles to navigate under various environment.

• The Journal of Information Systems
• /
• v.15 no.4
• /
• pp.211-224
• /
• 2006

This study investigates the application of data mining techniques such as artificial neural networks, rough sets, and induction teaming to the intrusion detection systems. To maximize the effectiveness of data mining for intrusion detection systems, we introduced the asymmetric costs with false positive errors and false negative errors. And we present a method for intrusion detection systems to utilize the asymmetric costs of errors in data mining. The results of our empirical experiment show our intrusion detection model provides high accuracy in intrusion detection. In addition the approach using the asymmetric costs of errors in rough sets and neural networks is effective according to the change of threshold value. We found the threshold has most important role of intrusion detection model for decreasing the costs, which result from false negative errors.