Detecting objects of interest from a video sequence is a fundamental and critical task in automated visual surveillance. Most current approaches only focus on discriminating moving objects by background subtraction wh...Detecting objects of interest from a video sequence is a fundamental and critical task in automated visual surveillance. Most current approaches only focus on discriminating moving objects by background subtraction whether or not the objects of interest can be moving or stationary. In this paper, we propose layers segmentation to detect both moving and stationary target objects from surveillance video. We extend the Maximum Entropy (ME) statistical model to segment layers with features, which are collected by constructing a codebook with a set of codewords for each pixel. We also indicate how the training models are used for the discrimination of target objects in surveillance video. Our experimental results are presented in terms of the success rate and the segmenting precision.展开更多
Selecting new program projects plays an important role for TV companies. Balanced scorecard （BSC） which links financial and non-financial, tangible and intangible, inward and outward factors can provide an integrate...Selecting new program projects plays an important role for TV companies. Balanced scorecard （BSC） which links financial and non-financial, tangible and intangible, inward and outward factors can provide an integrated viewpoint for decision makers to select optimal new program projects. This study combines BSC with analytic hierarchy process （AHP） to help Taiwan Residents TV company managers make better decisions in new program projects selection. Moreover, the practical application of the proposed approach is generic and also suitable to be exploited for Taiwan Residents TV companies.展开更多
Due to the substantial role of bridges in transportation networks and in accordance with the limited funding for bridge management, remediation strategies have to be prioritised. A conservative bridge assessment will ...Due to the substantial role of bridges in transportation networks and in accordance with the limited funding for bridge management, remediation strategies have to be prioritised. A conservative bridge assessment will result in unnecessary actions, such as costly bridge strengthening or repairs. On the other hand, any bridge maintenance negligence and delayed actions may lead to heavy future costs or degraded assets. The accuracy of decisions developed by any manager or bridge engineer relies on the accuracy of the bridge condition assessment which emanates from visual inspection. Many bridge rating systems are based on a very subjective procedure and are associated with uncertainty and personal bias. The developing condition rating method described herein is an important step in adding more holism and objectivity to the current approaches. Structural importance and material vulnerability are the two main factors that should be considered in the evaluation of element structural index and the causal factor as the representative of age, environment, road class and inspection is implemented as a coefficient to the OSCI （overall structural condition index）. The AHP （analytical hierarchy process） has been applied to evaluate the priority vector of the causal parameters.展开更多
基金Project supported by the National Natural Science Foundation of China (No. 60272031), and Technology Plan Program of ZhejiangProvince (No. 2003C21010), and Zhejiang Provincial Natural Sci-ence Foundation of China (No. M603202)
文摘Detecting objects of interest from a video sequence is a fundamental and critical task in automated visual surveillance. Most current approaches only focus on discriminating moving objects by background subtraction whether or not the objects of interest can be moving or stationary. In this paper, we propose layers segmentation to detect both moving and stationary target objects from surveillance video. We extend the Maximum Entropy (ME) statistical model to segment layers with features, which are collected by constructing a codebook with a set of codewords for each pixel. We also indicate how the training models are used for the discrimination of target objects in surveillance video. Our experimental results are presented in terms of the success rate and the segmenting precision.
文摘Selecting new program projects plays an important role for TV companies. Balanced scorecard （BSC） which links financial and non-financial, tangible and intangible, inward and outward factors can provide an integrated viewpoint for decision makers to select optimal new program projects. This study combines BSC with analytic hierarchy process （AHP） to help Taiwan Residents TV company managers make better decisions in new program projects selection. Moreover, the practical application of the proposed approach is generic and also suitable to be exploited for Taiwan Residents TV companies.
文摘Due to the substantial role of bridges in transportation networks and in accordance with the limited funding for bridge management, remediation strategies have to be prioritised. A conservative bridge assessment will result in unnecessary actions, such as costly bridge strengthening or repairs. On the other hand, any bridge maintenance negligence and delayed actions may lead to heavy future costs or degraded assets. The accuracy of decisions developed by any manager or bridge engineer relies on the accuracy of the bridge condition assessment which emanates from visual inspection. Many bridge rating systems are based on a very subjective procedure and are associated with uncertainty and personal bias. The developing condition rating method described herein is an important step in adding more holism and objectivity to the current approaches. Structural importance and material vulnerability are the two main factors that should be considered in the evaluation of element structural index and the causal factor as the representative of age, environment, road class and inspection is implemented as a coefficient to the OSCI （overall structural condition index）. The AHP （analytical hierarchy process） has been applied to evaluate the priority vector of the causal parameters.
