• Journal of Broadcast Engineering
• /
• v.6 no.1
• /
• pp.13-20
• /
• 2001

In this paper, we propose a new digital audio watermarking scheme In the cepstrum domain. We insert a digital watermark signal Into the cepstral components of the audio signal using a technique analogous to spread spectrum Communications, hiding a narrow band signal in a wade band channel. In our proposed method, we use pseudo-random sequences to watermark the audio signal. The watermark Is then weighted in the cepstrum domain according to the distribution of cepstral coefficients and the frequency masking characteristics of the human auditory system. The proposed watermark embedding scheme minimizes audibility of the watermark signal. and the embedded watermark is robust to mu1tip1e watermarks, MPEG audio ceding and additive noose.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.383-383
• /
• 2015

하천의 하상고 측량은 하상변동 분석, 서식처 구조 등을 이해하는데 매우 중요한 정보를 제공한다. 하지만, 현재까지 대부분의 하상고 측량은 일정한 간격의 하천 단면 측량에 의해서 행해져 왔다. 최근 GPS와 다중 빔 측심기를 이용하여 하상의 3차원적 형상을 조밀하게 측량하고 있으나 비용이 많이 들기 때문에 긴 하천 구간을 전부 측량하지는 못하고 특정한 부분에 대해서만 집중하고 있다. 항공 LiDAR의 경우 넓은 지역에 대해 신속하고 고해상도로 지형을 측량할 수 있으나 수중 투과 장비가 고가이며, 일반 적색 레이져 기반 LiDAR는 수중을 측정하지 못하여 하상 측량에 한계가 있다. 이에 대한 대안으로 활용할 수 있는 방법은 광학 기반의 원격 탐사에 의한 수심 측량 방법이다. 이 방법은 얕은 수심의 하천에 대한 활용되었는데, 광학 센서 이미지나 항공사진 등을 이용한다. 본 연구에서는 저고도에서 촬영한 고해상도 디지털 항공사진을 이용하여 모래하천의 수심을 추정하였다. 이 방법은 항공사진의 적색 및 녹색 색상값과 현장에서 정밀한 측위 하에 측량한 수심값 사이의 관계를 이용한다. 이를 통해 보정식을 수립하고 검사 자료를 이용하여 검증한 후 항공사진의 해당 지역에 대해 수심 부분을 마스킹 처리하여 하상고를 구축하였다. 검사 자료에 대한 RMSE는 약 12 cm로 나타났다. 이를 활용하여 대상 구간의 3차원적 지형 형상을 구축하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.120-128
• /
• 2012

In this paper, we propose a modified iterative pre-whitening projection statistics (MIPPS) scheme for improving multi-target detection performance in non-homogeneous clutter environments. As a non-homogeneity detection (NHD) technique of space-time adaptive processing algorithm for airborne radar, the MIPPS scheme improves the average detection probability of weak target when multiple targets with different reflection signal intensities are located in close range. Numerical results show that the conventional NHD schemes suffers from the masking effect by strong targets and clutters and the proposed MIPPS scheme outperforms the conventional schemes with respect to the average detection probability of the weak target at low signal-to-clutter ratio.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.77-84
• /
• 2022

In this paper, we propose a Label Reassignment Strategy to improve the performance of an object detection algorithm. Our approach involves two stages: an inference stage and an assignment stage. In the inference stage, we perform multi-scale inference with predefined scale sizes on a trained model and re-infer masked images to obtain robust classification results. In the assignment stage, we calculate the IoU between bounding boxes to remove duplicates. We also check box and class occurrence between the detection result and annotation label to re-assign the dominant class type. We trained the YOLOX-L model with the re-annotated dataset to validate our strategy. The model achieved a 3.9% improvement in mAP and 3x better performance on AP_S compared to the model trained with the original dataset. Our results demonstrate that the proposed Label Reassignment Strategy can effectively improve the performance of an object detection model.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.