Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance,HCI,object-based video compression,etc.One of the most successful moving objec...Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance,HCI,object-based video compression,etc.One of the most successful moving object detection algorithms is based on Adaptive Gaussian Mixture Model(AGMM).Although AGMM-based object detection shows very good performance with respect to object detection accuracy,AGMM is very complex model requiring lots of floating-point arithmetic so that it should pay for expensive computational cost.Thus,direct implementation of the AGMM-based object detection for embedded DSPs without floating-point arithmetic HW support cannot satisfy the real-time processing requirement.This paper presents a novel real-time implementation of adaptive Gaussian mixture model-based moving object detection algorithm for fixed-point DSPs.In the proposed implementation,in addition to changes of data types into fixed-point ones,magnification of the Gaussian distribution technique is introduced so that the integer and fixed-point arithmetic can be easily and consistently utilized instead of real number and floating-point arithmetic in processing of AGMM algorithm.Experimental results shows that the proposed implementation have a high potential in real-time applications.展开更多
For the measurement of X-ray energy spectrum with filter-fluorescer method,the high energy tail at the rearward of response function is the main source of background.There are,traditionally,two techniques for measurin...For the measurement of X-ray energy spectrum with filter-fluorescer method,the high energy tail at the rearward of response function is the main source of background.There are,traditionally,two techniques for measuring the background contributions:the same element Z for the fluorescer and filter,or the same element Z?1 for them.Using the formula of fluorescence intensity,and the elemental combinations of cobalt and iron,the backgrounds which the two techniques provide and the real one for measuring black-body radiation at equilibrium temperature of 7×106 K,were calculated.The results show that the Co-Co combination for the filter-fluorescer spectrometer can achieve better effect.A semi-quantitative analysis for the calculation results is discussed.展开更多
基金supported by Soongsil University Research Fund and BK 21 of Korea
文摘Foreground moving object detection is an important process in various computer vision applications such as intelligent visual surveillance,HCI,object-based video compression,etc.One of the most successful moving object detection algorithms is based on Adaptive Gaussian Mixture Model(AGMM).Although AGMM-based object detection shows very good performance with respect to object detection accuracy,AGMM is very complex model requiring lots of floating-point arithmetic so that it should pay for expensive computational cost.Thus,direct implementation of the AGMM-based object detection for embedded DSPs without floating-point arithmetic HW support cannot satisfy the real-time processing requirement.This paper presents a novel real-time implementation of adaptive Gaussian mixture model-based moving object detection algorithm for fixed-point DSPs.In the proposed implementation,in addition to changes of data types into fixed-point ones,magnification of the Gaussian distribution technique is introduced so that the integer and fixed-point arithmetic can be easily and consistently utilized instead of real number and floating-point arithmetic in processing of AGMM algorithm.Experimental results shows that the proposed implementation have a high potential in real-time applications.
文摘For the measurement of X-ray energy spectrum with filter-fluorescer method,the high energy tail at the rearward of response function is the main source of background.There are,traditionally,two techniques for measuring the background contributions:the same element Z for the fluorescer and filter,or the same element Z?1 for them.Using the formula of fluorescence intensity,and the elemental combinations of cobalt and iron,the backgrounds which the two techniques provide and the real one for measuring black-body radiation at equilibrium temperature of 7×106 K,were calculated.The results show that the Co-Co combination for the filter-fluorescer spectrometer can achieve better effect.A semi-quantitative analysis for the calculation results is discussed.