• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.173-181
• /
• 2002

Generally the one of serious problems in Voice Activity Detection (VAD) is speech region detection in noise environment. Therefore, this paper propose the new method using energy, lsp varation. As a result of processing time and speech quality of the proposed algorithm, the processing time is reduced due to the accurate detection of inactive period, and there is almot no difference in the subjective quality test. As a result of bit rate, proposed algorithm measures the number of VAD=1 and the result shows predominant reduction of bit rate as SNR of noisy speech is low (about 5∼10 dB).

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.17 no.4
• /
• pp.524-533
• /
• 2017

This paper presents a novel reset scheme for mm-scale sensing systems with stringent volume and area constraints. In such systems, multi-layer structure is required to maximize the silicon area per volume and minimize the system size. The multi-layer structure requires wirebonding connections for power delivery and communication among layers, but the area overhead for wirebonding pads can be significant. The proposed reset scheme exploits already existing power wires and thus does not require additional wires for system-wide reset operation. To implement the proposed reset scheme, a power management unit is designed to impose reset condition, and a reset detector is designed to interpret the reset condition indicated by the power wires. The reset detector uses a coupling capacitor for the initial power-up and a feedback path to hold the developed supply voltage. The prototype reset detector is fabricated in a $180-{\mu}m$ CMOS process, and the measurement results with the prototype mm-scale system confirmed robust reset operation over a wide range of temperatures and voltages.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.119-128
• /
• 2014

The appearance of retinal blood vessels is an important diagnostic indicator of serious disease, such as hypertension, diabetes, cardiovascular disease, and stroke. Automatic segmentation of the retinal vasculature is a primary step towards automatic assessment of the retinal blood vessel features. This paper presents an automated method for the enhancement and segmentation of blood vessels in fundus images. To decrease the influence of the optic disk, and emphasize the vessels for each retinal image, a multidirectional morphological top-hat transform with rotating structuring elements is first applied to the background homogenized retinal image. Then, an improved multiscale line detector is presented to produce a vessel response image, and yield the retinal blood vessel tree for each retinal image. Since different line detectors at varying scales have different line responses in the multiscale detector, the line detectors with longer length produce more vessel responses than the ones with shorter length; the improved multiscale detector combines all the responses at different scales by setting different weights for each scale. The methodology is evaluated on two publicly available databases, DRIVE and STARE. Experimental results demonstrate an excellent performance that approximates the average accuracy of a human observer. Moreover, the method is simple, fast, and robust to noise, so it is suitable for being integrated into a computer-assisted diagnostic system for ophthalmic disorders.

• Transactions on Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.17-20
• /
• 2024

This paper presents a novel lightweight object detection model tailored for low-powered edge devices, addressing the limitations of traditional resource-intensive computer vision models. Our proposed detector, inspired by the Single Shot Detector (SSD), employs a compact yet robust network design. Crucially, it integrates an 'enhancer block' that significantly boosts its efficiency in detecting smaller objects. The model comprises two primary components: the Light_Block for efficient feature extraction using Depth-wise and Pointwise Convolution layers, and the Enhancer_Block for enhanced detection of tiny objects. Trained from scratch on the Udacity Annotated Dataset with image dimensions of 300x480, our model eschews the need for pre-trained classification weights. Weighing only 5.5MB with approximately 0.43M parameters, our detector achieved a mean average precision (mAP) of 27.7% and processed at 140 FPS, outperforming conventional models in both precision and efficiency. This research underscores the potential of lightweight designs in advancing object detection for edge devices without compromising accuracy.

• ETRI Journal
• /
• v.30 no.2
• /
• pp.338-340
• /
• 2008

In this letter, we propose a novel approach to detecting and tracking apartment buildings for the development of a video-based navigation system that provides augmented reality representation of guidance information on live video sequences. For this, we propose a building detector and tracker. The detector is based on the AdaBoost classifier followed by hierarchical clustering. The classifier uses modified Haar-like features as the primitives. The tracker is a motion-adjusted tracker based on pyramid implementation of the Lukas-Kanade tracker, which periodically confirms and consistently adjusts the tracking region. Experiments show that the proposed approach yields robust and reliable results and is far superior to conventional approaches.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.253-257
• /
• 2004

Neural networks are works are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division(corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.1 s.94
• /
• pp.61-67
• /
• 1999

A laser Doppler vibrometer based on the laser heterodyne interferometry is employed to measure the vibration velocity of vibrating objects. In this paper, we propose a real time analog signal processor of a laser Doppler vibrometer to reduce the degradation of Doppler signals mainly caused by environmental noises. In the proposed real time signal processor of an laser Doppler vibrometer, a pre-processor and a logical motion direction detector are designed to reduce the detection errors of the object motion direction. Also, a noise detection and rejection circuit is designed to reject the unfiltered noises.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.285-288
• /
• 2017

In this paper, we propose a vision-based object detection and tracking system using online learning. The proposed system adopts a feature point-based method for tracking a series of inter-frame movement of a newly detected object, to estimate rapidly and toughness. At the same time, it trains the detector for the object being tracked online. Temporarily using the result of the failure detector to the object, it initializes the tracker back tracks to enable the robust tracking. In particular, it reduced the processing time by improving the method of updating the appearance models of the objects to increase the tracking performance of the system. Using a data set obtained in a variety of settings, we evaluate the performance of the proposed system in terms of processing time.

• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.2
• /
• pp.167-172
• /
• 2004

Neural networks are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division (Corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.699-702
• /
• 2015

다중의 영상을 이용하여 하나의 파노라마 영상을 제작하는 기법은 컴퓨터 비전, 컴퓨터 그래픽스 등과 같은 여러 분야에서 널리 연구되고 있다. 파노라마 영상은 하나의 카메라에서 얻을 수 있는 영상의 한계, 즉 예를 들어 화각, 화질, 정보량 등의 한계를 극복할 수 있는 좋은 방법으로서 가상현실, 로봇비전 등과 같이 광각의 영상이 요구되는 다양한 분야에서 응용될 수 있다. 파노라마 영상은 단일 영상과 비교하여 보다 큰 몰입감을 제공한다는 점에서 큰 의미를 갖는다. 현재 다양한 파노라마 영상 제작 기법들이 존재하지만, 대부분의 기법들이 공통적으로 파노라마 영상을 구성할 때 각 영상에 존재하는 특징점 및 대응점을 검출하는 방식을 사용하고 있다. 본 논문에서 사용한 SURF(Speeded Up Robust Features) 알고리즘은 영상의 특징점을 검출할 때 영상의 흑백정보와 지역 공간 정보를 활용하는데, 영상의 크기 변화와 시점 검출에 강하며 SIFT(Scale Invariant Features Transform) 알고리즘에 비해 속도가 빠르다는 장점이 있어서 널리 사용되고 있다. 본 논문에서는 두 영상 사이 또는 하나의 영상과 여러 영상 사이에 대응되는 매칭을 계산하여 파노라마영상을 생성하는 처리 방법을 구현하고 기술하였다.