Road surface estimation robust against vehicles' existence for stereo-based vehicle detection

Aizawa, Tatsuhiko; Tanaka, Atsuko; Higashikage, H.; Asokawa, Y.; Kimachi, Masatoshi; Ogata, Shiro

doi:10.1109/itsc.2002.1041186

Cited by 9 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For other methods using motion information [4], [29] or range data [12], [13], [30] to detect vehicles, we did not compare them in this paper. Table III lists the accuracy comparisons of vehicle detection among these three methods.…”

Section: Resultsmentioning

confidence: 99%

“…Then, the distance transform of a pixel in is defined as (12) where is the Euclidian distance between and . In order to enhance the strength of distance changes, (12) is further modified as follows: (13) where . Fig.…”

Section: A Contour Featurementioning

confidence: 99%

“…5(a). Thus, according to (13), a set of contour features can be extracted from . If we scan all pixels of in a row major order, can be then represented as a vector, i.e., (14) where all belong to and is the scanning index.…”

Section: A Contour Featurementioning

confidence: 99%

“…In [11], Ratan et al developed a scheme to detect vehicles' wheels as features to find possible vehicle positions and then used a method called Diverse Density to verify each vehicle candidate. In addition, Bensrhari [12] and Aizawa [13] used stereo-vision methods and 3-D vehicle models to detect vehicles and obstacles. The major drawback of the above methods to search vehicles is the need of a fully time-consuming search to scan all pixels of the whole image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Vehicle Detection Using Normalized Color and Edge Map

Tsai

Hsieh

Fan

2007

IEEE Trans. on Image Process.

237

108

View full text Add to dashboard Cite

This paper presents a novel vehicle detection approach for detecting vehicles from static images using color and edges. Different from traditional methods, which use motion features to detect vehicles, this method introduces a new color transform model to find important "vehicle color" for quickly locating possible vehicle candidates. Since vehicles have various colors under different weather and lighting conditions, seldom works were proposed for the detection of vehicles using colors. The proposed new color transform model has excellent capabilities to identify vehicle pixels from background, even though the pixels are lighted under varying illuminations. After finding possible vehicle candidates, three important features, including corners, edge maps, and coefficients of wavelet transforms, are used for constructing a cascade multichannel classifier. According to this classifier, an effective scanning can be performed to verify all possible candidates quickly. The scanning process can be quickly achieved because most background pixels are eliminated in advance by the color feature. Experimental results show that the integration of global color features and local edge features is powerful in the detection of vehicles. The average accuracy rate of vehicle detection is 94.9%.

show abstract