• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1128-1141
• /
• 2010

This paper proposes a method of moving object detection in crowded scene using clustered trajectory. Unlike previous appearance based approaches, the proposed method employes motion information only to isolate moving objects. In the proposed method, feature points are extracted from input frames first and then feature tracking is followed to create feature trajectories. Based on an assumption that feature points originated from the same objects shows similar motion as the object moves, the proposed method detects moving objects by clustering trajectories of similar motions. For this purpose an energy function based on spatial proximity, motion coherence, and temporal continuity is defined to measure the similarity between two trajectories and the clustering is achieved by minimizing the energy function in CRFs (conditional random fields). Compared to previous methods, which are unable to separate falsely merged trajectories during the clustering process, the proposed method is able to rearrange the falsely merged trajectories during iteration because the clustering is solved my energy minimization in CRFs. Experiment results with three different crowded scenes show about 94% detection rate with 7% false alarm rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.2
• /
• pp.120-133
• /
• 2008

This paper presents a novel approach for facial motion tracking and facial expression cloning to create a realistic facial animation of a 3D avatar. The exact head pose estimation and facial expression tracking are critical issues that must be solved when developing vision-based computer animation. In this paper, we deal with these two problems. The proposed approach consists of two phases: dynamic head pose estimation and facial expression cloning. The dynamic head pose estimation can robustly estimate a 3D head pose from input video images. Given an initial reference template of a face image and the corresponding 3D head pose, the full head motion is recovered by projecting a cylindrical head model onto the face image. It is possible to recover the head pose regardless of light variations and self-occlusion by updating the template dynamically. In the phase of synthesizing the facial expression, the variations of the major facial feature points of the face images are tracked by using optical flow and the variations are retargeted to the 3D face model. At the same time, we exploit the RBF (Radial Basis Function) to deform the local area of the face model around the major feature points. Consequently, facial expression synthesis is done by directly tracking the variations of the major feature points and indirectly estimating the variations of the regional feature points. From the experiments, we can prove that the proposed vision-based facial expression cloning method automatically estimates the 3D head pose and produces realistic 3D facial expressions in real time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.3
• /
• pp.123-128
• /
• 2007

This Paper Presents new transient signal classification algorithms for underwater transient signals. In general. the ambient noise has small spectral deviation and energy variation. while a transient signal has large fluctuation. Hence to detect the transient signal, we use the spectral deviation and power variation. To classify the detected transient signal. the feature Parameters are obtained by using the Wigner-Ville distribution based eigenvalue decomposition. The correlation is then calculated between the feature vector of the detected signal and all the feature vectors of the reference templates frame-by-frame basis, and the detected transient signal is classified by the frame mapping rate among the class database.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.6
• /
• pp.1010-1019
• /
• 1994

It is shown that there exists a nonlinear mapping which transforms image features and their changes to the desired camera motion without measuring of the relative distance between the camera and the object. This nonlinear mapping can eliminate several difficulties occurring in computing the inverse of the feature Jacobian as in the usual feature-based visual feedback control methods. Instead of analytically deriving the closed form of this mapping, a Fuzzy Membership Function-based Neural Network (FMFNN) incorporating a Fuzzy-Neural Interpolating Network is used to approximate the nonlinear mapping. Several FMFNN's are trained to be capable of tracking a moving object in the whole workspace along the line of sight. For an effective implementation of the proposed FMF network, an image feature selection process is investigated. Finally, several numerical examples are presented to show the validity of the proposed visual servoing method.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.2
• /
• pp.71-79
• /
• 1998

In this paper, we propose a new mART(modified ART) neural network by combining the winner neuron definition method of SOM(self-organizing map) and the real-time adaptive clustering function of ART(adaptive resonance theory) and construct it in a modular structure, for the purpose of organizing the feature maps of three dimensional targets. Being constructed in a modular structure, the proposed modular mART can effectively prevent the clusters from representing multiple classes and can be trained to organze two dimensional distortion invariant feature maps so as to recognize targets with three dimensional distortion. We also present the recognition result and self-organization perfdormance of the proposed modular mART neural network after carried out some experiments with 14 tank and fighter target models.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.67-75
• /
• 1997

A design for a system to perform rapid recognition of three dimensional objects is presented, focusing on efficient indexing. In order to retrieve the best matched models without exploring all possible object matches, we have employed a bayesian framework. A decision-theoretic measure of the discriminatory power of a feature for a model object is defined in terms of posterior probability. Detectability of a featrue defined as a function of the feature itselt, viewpoint, sensor charcteristics, nd the feature detection algorithm(s) is also considered in the computation of discribminatory power. In order to speed up the indexing or selection of correct objects, we generate and verify the object hypotheses for rfeatures detected in a scene in the order of the discriminatory power of these features for model objects.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1994.04a
• /
• pp.703-712
• /
• 1994

This paper presents an automatic conversion of machining data from the orthographic views of press mold by feature recognition rule. The system includes following 6 modules : separation of views, function support, dimension text recognition, feature recognition, dimension text check and feature processing modules. The characteristic of this system is that with minimum user intervention, it recognizes basic features such as holes, slots, pockets and clamping parts and thus automatically converts CAD drawing details of press mold into machining data using 2D CAD system instead of using an expensive 3D Modeler. The system is developed by using IBM-PC in the environment of AutoCAD R12, AutoLISP and MetaWare High C. Performance of the system is verified as a good interfacing of CAD and CAM when applied to a lot of sample drawings.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1053-1056
• /
• 1999

In this paper we propose a facial feature extraction method by using a genetic algorithm. The method uses a facial feature template to model the location of eyes and a mouth, and genetic algorithm is employed to find the optimal solution from the fitness function consisting of invariant moments. The simulation results show that the proposed algorithm can effectively extract facial features from face images with variations in position, size, rotation and expression.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.525-526
• /
• 2016

machine learning 기법 중 하나인 logistic regression을 이용하여 benign sample과 breast cancer sample을 구분할 수 있는데, 이 연구를 통해 classification의 정확도를 높이고 false positive와 false negative의 비율을 줄이려고 했다. 그래서 logistic regression의 parameter 값을 바탕으로 regression function에 영향을 많이 주는 feature 들을 선택하고, 영향력 있는 feature 들을 더한 새로운 feature를 추가했다. 그 결과 정확도와 F-score가 증가했으며, false positive, false negative의 비율이 감소했다.