• 방송공학회논문지
• /
• 제20권2호
• /
• pp.204-214
• /
• 2015

업샘플링 깊이맵은 깊이 카메라로부터 획득된 깊이맵의 공간 해상도를 증가시키는 방법이다. 깊이맵의 성능은 입체영상, 멀티뷰의 3D 입체감과 밀접한 관계가 있다. PSNR 등의 객관적 메트릭으로 깊이맵의 업샘플링 성능을 평가하고, 생성된 입체영상은 주관적 평가를 통해서 입체감 및 시각적 피로도를 조사한다. 후자의 주관적 평가는 인적 물적 자원을 필요로 하는 반면에, 전자의 객관적 메트릭은 수학적 표현으로 정량적 수치값을 알려준다. 따라서 주관적 평가와 높은 상관관계를 가지는 객관적 메트릭이 주관적 평가를 대체할 수 있다면 많이 시간을 필요로 하는 주관적 평가가 불필요하다. 이를 위해 본 논문에서는 다양한 객관적 메트릭과 3D 주관적 평가 사이의 관계를 조사한 후에, 이용한 메트릭에 기반한 주관평가와 상관관계가 높은 객관적 메트릭을 제안한다. 업샘플링된 깊이맵의 성능을 측정하기 위해 다양한 참조영상 및 무참조영상 평가 메트릭들을 이용하였다. 주관적 평가는 DSCQS 입체영상 테스트로 수행되었다. 세 종류의 상관관계의 활용 및 분석을 통해서, SSIM과 Edge-PSNR이 주관적 평가를 대체할 수 있는 적합한 객관적 메트릭임을 실험을 통해서 검증하였다.

• 한국소음진동공학회논문집
• /
• 제16권9호
• /
• pp.897-903
• /
• 2006

The reduction of the vehicle interior noise has been the main interest of noise and vibration harshness (NVH) engineers. The driver's perception on the vehicle noise is affected largely by psychoacoustic characteristic of the noise as well as the SPL. In particular, the heating, ventilation and air conditioning (HVAC) system sound among the vehicle interior noise has been reflected sensitively in psychoacoustics view point. Even though the HVAC noise is not louder than overall noise level, it clearly affects subjective perception to drivers in the way of making to be nervous or annoyed. Therefore, these days a vehicle engineer takes aim at developing sound quality as well as reduction of noise. In this paper, we acquired noises in the HVAC from many vehicles. Through the objective and subjective sound quality (SQ) evaluation with acquiring noises recorded by the vehicle HVAC system, the simple and multiple regression models were obtained for the subjective evaluation 'Pleasant' using the semantic differential method (SDM). The regression procedure also allows you to produce diagnostic statistics to evaluate the regression estimates including appropriation and accuracy. Furthermore, the neural network (NN) model were obtained using three inputs(loudness, sharpness and roughness) of the SQ metrics and one output(subjective 'Pleasant'). Because human's perception is very complex and hard to estimate their pattern, we used NN model. The estimated models were compared with correlations between output indexes of SQ and hearing test results for verification data 'Pleasant'. As a result of application of the SQ indexes, the NN model was shown with the largest correlation of SQ indexes and we found possibilities to predict the SQ metrics.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 춘계학술대회논문집
• /
• pp.1443-1448
• /
• 2006

The reduction of the vehicle interior noise has been the main interest of NVH engineers. The driver's perception on the vehicle noise is affected largely by psychoacoustic characteristic of the noise as well as the SPL. In particular, the HVAC sound among the vehicle interior noise has been reflected sensitively in the side of psychology. Even though the HVAC noise is not louder than overall noise level, it clearly affects subjective perception in the way of making a diver become nervous or annoyed. Therefore, these days a vehicle engineer takes aim at developing sound quality as well as reduction of noise. In this paper, we acquired noises in the HVAC from many vehicles. Through the objective and subjective sound quality evaluation with acquiring noises caused by the vehicle HVAC system, the simple and multiple regression models were obtained for the subjective evaluation 'Pleasant' using the sound quality metrics. The regression procedure also allows you to produce diagnostic statistics to evaluate the regression estimates including appropriation and accuracy. Furthermore, the neural network model were obtained using three inputs(loudness, sharpness and roughness) of the sound quality metrics and one output(subjective 'Pleasant'). And then the models were compared with correlations between sound quality index outputs and hearing test results for 'Pleasant'. As a result of application of the sound quality index, the neural network was verified with the largest correlation of the sound quality index.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.318-321
• /
• 2007

Since human listening is very sensitive to sound, a subjective index of a sound quality is required. Therefore, in the analysis for each situation, the sound evaluation is composed with sound quality factor. Many researchers spends their effort to make a more reliable and more accurate of sound in term of sound quality index for various system noise. The previous methods to evaluation of the SQ about vehicle interior noise are linear regression analysis of subjective SQ metrics by statistics and the estimation of the subjective SQ values by neural network. But these are so depended on jury test very much that they result in many difficulties. So, to reduce jury test weight, we suggested a new method using Mahalanobis distance for SQ evaluation. Threrefore, in this study Mahalanobis distance for the vehicle interior noise was derived using the objective SQ except jury test. Finnaly, the results of the SQ evaluation was analyzed discrimination between reference and abnormal group.

• 한국소음진동공학회논문집
• /
• 제18권1호
• /
• pp.57-60
• /
• 2008

Since human listening is very sensitive to sound, for evaluating of a sound quality is required. Therefore, in the analysis for each situation, the sound evaluation is composed with sound quality factor. My researchers spends their effort to make a more reliable and more accurate of sound in term of sound quality index for various system noise. The previous methods to evaluation of the SQ about vehicle interior noise are linear regression analysis of subjective SQ metrics by statistics and the estimation of the subjective SQ values by neural network. But these are highly dependent on jury test and have many difficulties due to various environmental factors. So, to reduce jury test weight. we suggested a new method using Mahalanobis distance for SQ evaluation. Threrefore, in this study Mahalanobis distance for the vehicle interior noise was derived using the objective SQ except jury test. Finnaly, the results of the SQ evaluation was analyzed discrimination between reference and abnormal group.

• 한국전자통신학회논문지
• /
• 제9권6호
• /
• pp.719-726
• /
• 2014

본 논문은 사용자 체감 품질에 관한 것으로서 특히 주관적인 측면을 포함하는 사용자 체감 품질을 어떻게 객관적인 방법으로 평가할 수 있는지에 관한 것이다. 본 논문은 현재 상용화되어 사용되고 있는 와이브로 무선 접속 인터페이스를 통해서 음성 서비스가 제공되는 경우에 다양한 품질 지표들의 값의 변화를 실제 측정하고 이들 간의 상관관계를 분석하여 음성 서비스의 사용자 체감 품질을 객관적으로 평가하고자 한다. 분석결과 와이브로를 통한 음성 서비스의 사용자 품질은 네트워크 계층에서 측정되는 전송 지연과 높은 상관관계를 보였고 다시 전송 지연은 무선 채널의 RSSI와 높은 상관관계를 가진다는 점을 확인할 수 있었다.