• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.461-463
• /
• 2023

본 연구는 실시간 MOT(Multiple-Object-Tracking)의 성능을 향상시키기 위해 다양한 기법을 적용한 MOT 모델을 설계한다. 연구에서 사용하는 Backbone 모델은 TBD(Tracking-by-Detection) 기반의 Tracking 모델을 사용한다. Heatmap Detection을 통해 객체를 검출하고 Transformer 기반의 Feature를 연결하여 Tracking 한다. 제안하는 방법은 Anchor 기반의 Detection의 장시간 문제와 추적 객체 정보 전달손실을 감소하여 실시간 객체 추적에 도움이 될 것으로 사료된다.

• Journal of Multimedia Information System
• /
• v.6 no.2
• /
• pp.91-98
• /
• 2019

Many researchers have attempted to recognize three-dimensional faces using feature points extracted from two-dimensional facial photographs. However, due to the limit of flat photographs, it is very difficult to recognize faces rotated more than 15 degrees from original feature points extracted from the photographs. As such, it is difficult to create an algorithm to recognize faces in multiple angles. In this paper, it is proposed a new algorithm to recognize three-dimensional face recognition based on feature points extracted from a flat photograph. This method divides into six feature point vector zones on the face. Then, the vector value is compressed and expanded according to the rotation angle of the face to recognize the feature points of the face in a three-dimensional form. For this purpose, the average of the compressibility and the expansion rate of the face data of 100 persons by angle and face zone were obtained, and the face angle was estimated by calculating the distance between the middle of the forehead and the tail of the eye. As a result, very improved recognition performance was obtained at 30 degrees of rotated face angle.

• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.255-264
• /
• 2011

In this paper, we propose a forward vehicle detection algorithm using column detection and bird's-eye view mapping based on stereo vision. The algorithm can detect forward vehicles robustly in real complex traffic situations. The algorithm consists of the three steps, namely road feature-based column detection, bird's-eye view mapping-based obstacle segmentation, obstacle area remerging and vehicle verification. First, we extract a road feature using maximum frequent values in v-disparity map. And we perform a column detection using the road feature as a new criterion. The road feature is more appropriate criterion than the median value because it is not affected by a road traffic situation, for example the changing of obstacle size or the number of obstacles. But there are still multiple obstacles in the obstacle areas. Thus, we perform a bird's-eye view mapping-based obstacle segmentation to divide obstacle accurately. We can segment obstacle easily because a bird's-eye view mapping can represent the position of obstacle on planar plane using depth map and camera information. Additionally, we perform obstacle area remerging processing because a segmented obstacle area may be same obstacle. Finally, we verify the obstacles whether those are vehicles or not using a depth map and gray image. We conduct experiments to prove the vehicle detection performance by applying our algorithm to real complex traffic situations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.293-297
• /
• 2007

This thesis suggests a new algorithm to detects multiple moving objects using a CMODE(Correct Multiple Object DEtection) method in the color images acquired in real-time and to track the interested pedestrian using motion and hue information. The multiple objects are detected, and then shaking trees or moving cars are removed using structural characteristics and shape information of the man , the interested pedestrian can be detected, The first similarity judgment for tracking an interested pedestrian is to use the distance between the previous interested pedestrian's centroid and the present pedestrian's centroid. For the area where the first similarity is detected, three feature points are calculated using k-mean algorithm, and the second similarity is judged and tracked using the average hue value for the $3{\times}3$ area of each feature point. The zooming of camera is adjusted to track an interested pedestrian at a long distance easily and the FOV(Field of View) of camera is adjusted in case the pedestrian is not situated in the fixed range of the screen. As a experiment results, comparing the suggested CMODE method with the labeling method, an average approach rate is one fourth of labeling method, and an average detecting time is faster three times than labeling method. Even in a complex background, such as the areas where trees are shaking or cars are moving, or the area of shadows, interested pedestrian detection is showed a high detection rate of average 96.5%. The tracking of an interested pedestrian is showed high tracking rate of average 95% using the information of situation and hue, and interested pedestrian can be tracked successively through a camera FOV and zooming adjustment.

• ETRI Journal
• /
• v.34 no.4
• /
• pp.503-510
• /
• 2012

We analyze the relationship between channel coherence bandwidth and two complexity-reduced lattice reduction aided detection (LRAD) algorithms for multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems in correlated fading channels. In both the adaptive LR algorithm and the fixed interval LR algorithm, we exploit the inherent feature of unimodular transformation matrix P that remains the same for the adjacent highly correlated subcarriers. Complexity simulations demonstrate that the adaptive LR algorithm could eliminate up to approximately 90 percent of the multiplications and 95 percent of the divisions of the brute-force LR algorithm with large coherence bandwidth. The results also show that the adaptive algorithm with both optimum and globally suboptimum initial interval settings could significantly reduce the LR complexity, compared with the brute-force LR and fixed interval LR algorithms, while maintaining the system performance.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.49-55
• /
• 2022

In this paper, we propose an obstacle detection method that can operate robustly even in external environmental factors such as weather. In particular, we propose an obstacle detection system that can accurately inform dangerous situations in AR through DB-based feature matching and RANSAC-based multiplane method. Since the approach to detecting obstacles based on images obtained by RGB cameras relies on images, the feature detection according to lighting is inaccurate, and it becomes difficult to detect obstacles because they are affected by lighting, natural light, or weather. In addition, it causes a large error in detecting obstacles on a number of planes generated due to complex terrain. To alleviate this problem, this paper efficiently and accurately detects obstacles regardless of lighting through DB-based feature matching. In addition, a criterion for classifying feature points is newly calculated by normalizing multiple planes to a single plane through RANSAC. As a result, the proposed method can efficiently detect obstacles regardless of lighting, natural light, and weather, and it is expected that it can be used to secure user safety because it can reliably detect surfaces in high and low or other terrains. In the proposed method, most of the experimental results on mobile devices reliably recognized indoor/outdoor obstacles.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.31-38
• /
• 2021

It is hard to predict when and where a fall accident will happen. Also, if rapid follow-up measures on it are not performed, a fall accident leads to a threat of life, so studies that can automatically detect a fall accident have become necessary. Among automatic fall-accident detection techniques, a fall detection scheme using an IMU (inertial measurement unit) sensor attached to a wrist is difficult to detect a fall accident due to its movement, but it is recognized as a technique that is easy to wear and has excellent accessibility. To overcome the difficulty in obtaining fall data, this study proposes an algorithm that efficiently learns less data through machine learning such as KNN (k-nearest neighbors) and SVM (support vector machine). In addition, to improve the performance of these mathematical classifiers, this study utilized feature data aquired in the frequency space. The proposed algorithm analyzed the effect by diversifying the parameters of the model and the parameters of the frequency feature extractor through experiments using standard datasets. The proposed algorithm could adequately cope with a realistic problem that fall data are difficult to obtain. Because it is lighter than other classifiers, this algorithm was also easy to implement in small embedded systems where SIMD (single instruction multiple data) processing devices were difficult to mount.

• IE interfaces
• /
• v.22 no.2
• /
• pp.126-134
• /
• 2009

As product quality and yield are essential factors in semiconductor manufacturing, monitoring the main manufacturing steps is a critical task. For the purpose, FDC(Fault detection and classification) is used for diagnosing fault states in the processes by monitoring data stream collected by equipment sensors. This paper proposes an FDC model based on decision tree which provides if-then classification rules for causal analysis of the processing results. Unlike previous decision tree approaches, we reflect the structural aspect of the data stream to FDC. For this, we segment the data stream into multiple subregions, define structural features for each subregion, and select the features which have high relevance to results of the process and low redundancy to other features. As the result, we can construct simple, but highly accurate FDC model. Experiments using the data stream collected from etching process show that the proposed method is able to classify normal/abnormal states with high accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.4
• /
• pp.812-820
• /
• 2012

In this paper, multiple pedestrians tracking system using Histogram of Oriented Gradient and occlusion detection is proposed. The proposed system is applicable to Intelligent Surveillance System. First, we detect pedestrian in a image sequence using pedestrian's feature. To get pedestrian's feature, we make block-histogram using gradient's direction histogram based on HOG(Histogram of Oriented Gradient), after that a pedestrian region is classified by using Linear-SVM(Support Vector Machine) training. Next, moving objects are tracked by using position information of the classified pedestrians. And we create motion trajectory descriptor which is used for content based event retrieval. The experimental results show that the proposed method is more fast, accurate and effective than conventional methods.

• Smart Structures and Systems
• /
• v.13 no.6
• /
• pp.975-991
• /
• 2014

The objective of this study is to develop a reliable method for locating cracks in a beam using data fusion of fractal dimension features of operating deflection shapes. The Katz's fractal dimension curve of an operating deflection shape is used as a basic feature of damage. Like most available damage features, the Katz's fractal dimension curve has a notable limitation in characterizing damage: it is unresponsive to damage near the nodes of structural deformation responses, e.g., operating deflection shapes. To address this limitation, data fusion of Katz's fractal dimension curves of various operating deflection shapes is used to create a sophisticated fractal damage feature, the 'overall Katz's fractal dimension curve'. This overall Katz's fractal dimension curve has the distinctive capability of overcoming the nodal effect of operating deflection shapes so that it maximizes responsiveness to damage and reliability of damage localization. The method is applied to the detection of damage in numerical and experimental cases of cantilever beams with single/multiple cracks, with high-resolution operating deflection shapes acquired by a scanning laser vibrometer. Results show that the overall Katz's fractal dimension curve can locate single/multiple cracks in beams with significantly improved accuracy and reliability in comparison to the existing method. Data fusion of fractal dimension features of operating deflection shapes provides a viable strategy for identifying damage in beam-type structures, with robustness against node effects.