http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Accelerating Distance Transform Image based Hand Detection using CPU-GPU Heterogeneous Computing
Zhaohua Yi,Xiaoqi Hu,Eung Kyeu Kim,Kyung Ki Kim,Byunghyun Jang 대한전자공학회 2016 Journal of semiconductor technology and science Vol.16 No.5
Most of the existing hand detection methods rely on the contour shape of hand after skin color segmentation. Such contour shape based computations, however, are not only susceptible to noise and other skin color segments but also inherently sequential and difficult to efficiently parallelize. In this paper, we implement and accelerate our in-house distance image based approach using CPU-GPU heterogeneous computing. Using emerging CPU-GPU heterogeneous computing technology, we achieved 5.0 times speed-up for 320x240 images, and 17.5 times for 640x480 images and our experiment demonstrates that our proposed distance image based hand detection is robust and fast, reaching up to 97.32% palm detection rate, 80.4% of which have more than 3 fingers detected on commodity processors.
Accelerating Distance Transform Image based Hand Detection using CPU-GPU Heterogeneous Computing
Yi, Zhaohua,Hu, Xiaoqi,Kim, Eung Kyeu,Kim, Kyung Ki,Jang, Byunghyun The Institute of Electronics and Information Engin 2016 Journal of semiconductor technology and science Vol.16 No.5
Most of the existing hand detection methods rely on the contour shape of hand after skin color segmentation. Such contour shape based computations, however, are not only susceptible to noise and other skin color segments but also inherently sequential and difficult to efficiently parallelize. In this paper, we implement and accelerate our in-house distance image based approach using CPU-GPU heterogeneous computing. Using emerging CPU-GPU heterogeneous computing technology, we achieved 5.0 times speed-up for $320{\times}240$ images, and 17.5 times for $640{\times}480$ images and our experiment demonstrates that our proposed distance image based hand detection is robust and fast, reaching up to 97.32% palm detection rate, 80.4% of which have more than 3 fingers detected on commodity processors.
Hui Tang,Qiu Sun,Tiezhu Xin,Chuangui Yi,Zhaohua Jiang,Fuping Wang 한국물리학회 2012 Current Applied Physics Vol.12 No.1
Ceramic thermal protection coatings on Ti6Al4V alloy were achieved by micro-arc oxidation (MAO) in the presence of Co(CH3COO)2. The morphology, crystallographic structure and chemical composition of the coating were characterized by various techniques. The thermal emission of the coating was measured by Fourier transform spectrometer apparatus. The bonding strength between the coating and substrate was studied, together with the thermal shock resistance of the coating. The results indicate that the content of Co in the coating layer significantly affects its thermal emissivity. Higher concentration of Co(CH3-COO)2 in electrolytes leads to more Co ions into the coating, which enhances the emissivity of the coating. All the coatings show bonding strength higher than 10 MPa. In addition, the coating remains stable over 40 cycles of thermal shocking. The coating formed at 4 g/L Co(CH3COO)2 displays an average spectral emissivity value more than 0.9 and bonding strength about 10.4 MPa.