教師著作
Permanent URI for this collectionhttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/31268
Browse
Item Area measurement system using a single camera(2006-11-11) C.-C. Chen; T.-H. Wang; M.-C. Lu; W.-Y. WangIn this paper, we propose a new method to measure area using only a single CCD camera in different distances. Two parallel laser beams are established to serve as the basis for horizontal length measurement. A single horizontal scanning line of the CCD image is only required for the area measurement. Based on the pixel numbers between two projected points within a CCD image, which represent the resolution of horizontal length, the actual area can be derived by counting the pixel numbers occupied by the image of the object to be measured on the CCD image. Our research results are merited with quick measurement speed, simple system structures and there will be no necessity to adopt image recognizing or signal analysis techniques to calculate the area from different photographing distances.Item A method of distance measurement by digital camera(2006-11-11) T.-H. Wang; C.-C. Hsu; C.-P. Tsai; M.-C. Lu; W.-Y. Wang; C.-C. ChenItem Nighttime Vehicle Distance Alarm System(2007-08-26) M.-C. Lu; W.-Y. Wang; C.-C. Chen; C.-P. TsaiKeeping safe distance between two cars is an important topic for car accident prevention. This paper presents a practical nighttime vehicle distance measuring method based on a single CCD image. The method combines the image-based distance measuring system (IBDMS) with nighttime vehicle distance alarm system. To solve the nighttime feature extraction problem, the proposed method uses two taillights as the feature. Based on the proportionality of similar triangles, distance between a CCD camera and taillight of the vehicle ahead can be measured. The method focuses on detecting taillight and differentiating the targeted vehicle from others on the basis of partial image analysis instead of whole image processing. As a result, high-speed processing and simple configuration of the proposed method have been achieved as demonstrated in this paper.Item Nonlinear system identification using delta learning-based gaussian-hopfield networks(2004-01-01) C.-C. Chen; W.-Y. Wang本論文針對非線性離散時間系統，提出一種以最徒負梯度法則為基礎之高斯-霍普菲爾類神經網路之新驗證方法。並藉由兩種不同的離散時間模型來描述此單輸入單輸出之非線性離散時間系統。而此等效非線性系統模型之非線性部份可用以相關聯之輸入及輸出組成的非線性函數來等效之。我們用高斯基組函數去代表? 一個非線性離散時間系統模型之非線性函數，以最徒負梯度法則去訓練一組高斯基組函數之係數並使其最佳化。最後以模擬結果來驗證此方法之逼近效能。