Browsing by Author "Lee, Hsia"

Now showing 1 - 3 of 3

A new vehicle detection approach in traffic jam conditions
(2007)
Wu, Bing-Fei
;
Juang, Jhy-Hong
;
Tsai, Ping-Tsung
;
Chang, Ming-Wei
;
Fan, Chung-Jui
The well-known vehicle detectors utilize the background extraction methods to segment the moving objects. The back-ground updating concept is applied to overcome the luminance variation which results in the error detection. These systems will meet a challenge when detecting the vehicles in the traffic jam conditions at sunset. The vehicles will cover the road surface so that the background information cannot be smoothly updated. Once the traffic is released, the existing background is not suitable for the moving segmentation. The main contribution of this paper is that an efficient vehicle detection approach is proposed to improve the detection accuracy in traffic jam conditions. The land mask decision gives the land information and the merged boundary box rule is presented to realize vehicle detection. The signed square normalized correlation coefficient calculation is addressed, and it is applied to vehicle tracking. The experimental results show that this approach works well in highway and urban area with high accuracy.
Signal recognition by nonparametric discrimination of functional data for vehicle transportation system
(2007)
Jou, Yow-Jen
;
Lu, Yung-Tsai
;
Lan, Chien-Lun
;
Lee, Hsia
;
資訊管理與財務金融系註：原資管所+財金所
Traffic congestion is a serious and general problem in our daily life. Real time vehicle information is essential to the advanced traffic management. The recognition and statistics of traffic flow among different types of vehicles would be contributive to improve traffic block. This paper considers the dataset recorded by the radar microwave detector with the intensity of reflecting waves and the types of vehicles. The data is treated as functional data and then classification would be proposed to be performed by nonparametfic discrimination of functional data with three forms of Proximity. The proximity with lower misclassification rate would be adopted for the data. The results show that the misclassification rate is pretty satisfactory if the number of groups is two and as the number of group increases the misclassification rate increases as expected.
Vehicle Classification using Support Vector Machines and k-means Clustering
(2009)
Cho, Hsun-Jung
;
Li, Rih-Jin
;
Lee, Hsia
;
Wu, Jennifer Yuh-Jen
;
運輸與物流管理系註：原交通所+運管所
This investigation involves the combination of support vector machines (SVM) and k-means clustering implemented on radar signal. SVM classifier based on k-means algorithm has an advance for classifying unlabeled data. To classify the vehicle types automatically, the combined method is implemented with radar signals. This paper proposed a classifier training algorithm based on SVM and k-means clustering as follows (i) using the k-means algorithm to label the input feature data extracted from radar signal into two subsets, (ii) train SVM with labeled data, and (iii) classify unidentified radar signal into large vehicle or small vehicle with the trained classifier. Training features of radar signal includes (i) signal volume and (ii) sum of signal variations, both in frequency domain. These features are taken as system input, while vehicle types as system output. The proposed algorithm is implemented and demonstrated with real FMCW radar signals. With the numerical experiment, satisfying result is obtained.