Vision-based adaptive and recursive tracking of unpaved roads

Jeong, Hong; Oh, Yong─Geun; Park, J. H.; Koo, Bonkon; Lee, S. W.

doi:10.1016/s0167-8655(01)00120-9

Cited by 19 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 shows the road detection results of these two method classified by SVM. Overall, these two methods classified by SVM both have better detecting results than H. Jeong's method [2] , but the TM&FSVM method has fewer points classified into wrong area and obtains better road boundaries than the method only using SVM. The road boundaries using our method are relatively straighter and close to real road boundaries.…”

Section: Resultsmentioning

confidence: 92%

“…5 shows the road detection results of three different methods, in which Fig. 5(a) uses H. Jeong's method [2] , Fig. 5(b) uses the method based on trapezoidal model and SVM [3] and Fig.…”

Section: Resultsmentioning

confidence: 99%

“…The model in TM&FSVM method is the trapezoidal model [2] , which can describe the shape of the road briefly.…”

Section: Trapezoidal Model In Tmandfsvm Methodsmentioning

confidence: 99%

“…The noise variances, 11 22 , , q q and r are unknown, which can be updated using EM algorithm in order to adapt unstructured roads [2] .…”

Section: Trapezoidal Model In Tmandfsvm Methodsmentioning

confidence: 99%

“…We proposed a method of model-oriented and fuzzy Support Vector Machine (SVM)-calling TM&FSVM method in this paper, based on the trapezoidal [2] model and SVM [3] . The frames of the video are preprocessed by Pulse-Coupled Neural Network (PCNN).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A model-oriented road detection approach using fuzzy SVM

Zhang

Wang

2010

J. Electron.(China)

View full text Add to dashboard Cite

This paper presents an approach of model-oriented road detection based on trapezoidal model proposed by H. Jeong, et al and fuzzy Support Vector Machine (SVM). Firstly, the frames extracted from the video are preprocessed by Pulse Coupled Neural Network (PCNN), and then handled by Kalman filter and Expectation Maximization (EM) algorithms. Next, according to the road's different feathers, using fuzzy algorithm chooses a corresponding SVM for further lane detection, and then using morphological filters obtains the final detecting result. For different types of roads, this method uses fuzzy algorithm to choose different SVMs. Furthermore, in preprocessing using PCNN removes the shadow in the road to reduce the effect of illumination variations. Experimental results show that our method can receive better lane detecting results than the trapezoidal model and BP proposed by H. Jeong, et al..

show abstract

Section: Resultsmentioning

confidence: 92%

“…5 shows the road detection results of three different methods, in which Fig. 5(a) uses H. Jeong's method [2] , Fig. 5(b) uses the method based on trapezoidal model and SVM [3] and Fig.…”

Section: Resultsmentioning

confidence: 99%

“…The model in TM&FSVM method is the trapezoidal model [2] , which can describe the shape of the road briefly.…”

Section: Trapezoidal Model In Tmandfsvm Methodsmentioning

confidence: 99%

“…The noise variances, 11 22 , , q q and r are unknown, which can be updated using EM algorithm in order to adapt unstructured roads [2] .…”

Section: Trapezoidal Model In Tmandfsvm Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations