http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Sharpness-aware Evaluation Methodology for Haze-removal Processing in Automotive Systems
Seokha Hwang,Youngjoo Lee 대한전자공학회 2016 IEIE Transactions on Smart Processing & Computing Vol.5 No.6
This paper presents a new comparison method for haze-removal algorithms in nextgeneration automotive systems. Compared to previous peak signal-to-noise ratio–based comparisons, which measure similarity, the proposed modulation transfer function–based method checks sharpness to select a more suitable haze-removal algorithm for lane detection. Among the practical filtering schemes used for a haze-removal algorithm, experimental results show that Gaussian filtering effectively preserves the sharpness of road images, enhancing lane detection accuracy.
차량용 시스템의 안개제거 영상처리를 위한 선예도기반 성능평가 방법
황석하(Seokha Hwang),김수환(Suhwan Kim),김지훈(Jihoon Kim),어진(Jin Eo),우동현(Donghyun Woo),정세환(Sehwan Jung),이영주(Youngjoo Lee) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.6
This paper presents a new comparison method of haze-removal algorithms for the next generation automotive. Compared to the previous PSNR-based comparison, which measures the similarity, the proposed MTF-based method checks the sharpness for selecting more suitable haze-removal algorithm for the following lane detection problem. Among the practical filtering schemes used for haze-removal algorithm, experimental results show that Gaussian filtering effectively preserves the sharpness of road images, enhancing the lane detection accuracy.
황석해,윤종수 한국정보전략학회 2002 한국정보전략학회지 Vol.5 No.2
This study is to propose a customer segmentation model for managing the cancellation of car purchase contract in domestic automobile industry, and to suggest its applicability for many studies to be performed in the future. To accomplish these research purposes, this study performed the case study to identify which attributes of customer had an influence on the cancellation of a car purchase contract. This study developed a customer segmentation model that could estimate the possibilities of cancellation of car purchase contract, and then applied the model to the case to suggest its applicability in the future.
Approximate Radix-4 Booth Multiplication Circuit
김기범,Seokha Hwang,Youngjoo Lee,Sunggu Lee 대한전자공학회 2019 Journal of semiconductor technology and science Vol.19 No.5
Many modern applications, such as object recognition using deep neural networks, require extremely large numbers of multiplications, but can sacrifice accuracy in order to achieve lower power usage and faster operation. This paper proposes a new approximate multiplier design based on radix-4 Booth encoding. The key novel aspect of the proposed design is that approximate circuits are designed to create intermediate terms, which are then used as the common inputs to almost all of the logic within one entire row of a partial product array, resulting in a multi-level logic circuit implementation with extremely low delay and power usage characteristics. The proposed 8-bit (16-bit) design improves the power delay product by 17.1% to 30.3% (88.9% to 96.4%) over the previous best designs. By using accurate, approximated, and truncated regions, a wide range of approximate multiplier designs with different error characteristics are possible. Using normalized mean error distance and relative error distance metrics, simulations using synthesized circuits are used to show that the proposed designs have significantly improved power/accuracy tradeoffs over the previous best designs.