Vehicle Detection Using Normalized Color and Edge Map

Abstract

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%.

Counting Cars in Traffic Using Cascade Haar with KLP

“…If object point lie in Detection. Window [1] Delete all points of that object from PointBeingTrackedList [2] Add the list PT as feature of this object [3] The detection results can be further improved by training the classifier on largerset of positives and negatives. The direction of flow can be further used to improve tracking results as sudden changes in flow can be classified as cases of occlusion and such points can be ignored in the trackingalgorithm.…”

“…Luo-Wei Tsai et al [1] present vehicle detection approach for detecting vehicles for static images based on color and edge. Based on color of vehicle important vehicle is extracted from background.…”

Adaptive centre extraction method for structured light stripes

“…The centre extraction methods are aimed at obtaining the centre positions of light stripes. They include the methods of extreme value [13,14], threshold [15][16][17], directional template [18][19][20], grey centroid [21,22], curve fitting [23,24] and Hessian matrix [25][26][27]. Below we discuss in brief these methods and point to their advantages and shortcomings.…”

“…The method is fast and accurate when the light stripe obeys ideal Gaussian distribution and the other areas of image are dark, but it is susceptible to noise and contrast conditions. The threshold method [15][16][17] sets a boundary threshold to obtain two borders in the transverse section of the light stripe, and the centres of the light stripe are regarded as centres of the two borders. This method is affected by the noise and the image contrast conditions, too.…”

Vision-based parking lot occupancy evaluation system using 2D separable discrete wavelet transform

“…Segmentation by thresholding together with Sobel edge detection to eliminate shadows is shown in the paper of Bong et al [5]. Tsai et al [6] propose a color-based model to detect vehicle candidates and a Bayesian classifier to verify the detection of vehicles based on corners, edges, and wavelet features. A Bayesian hierarchical framework integrating the 3-D scene knowledge is presented in [7], utilizing the pixel-based car model and parking space model with the estimate of the lighting condition.…”