Advanced driver assistance systems (ADAS) are designed to improve driving safety and reduce driving stress in roads. These systems are applied to maintain safe distance from the car in front, alert driver to objects in their path, alert driver of an unintended departure from the lane or even automatic intervention. According to National Highway Traffic Safety Administration (NHTSA), 94 percent of the immediate reason for the critical pre-crash and often the last failure in the causal chain of events leading up to the crash is assigned to the driver. ADAS testing and rating are a development trend in NHTSA’s New Car Assessment Program (NCAP), which increases the manufactures investment in such solutions. Camera based ADAS solutions for Lane Departure Warning (LDW) requires extensive use of mathematical operations in image processing. Edge detection methods are frequently used in such applications, however noise and outlier reduction are still challenging tasks. The Canny edge detector is one of the most popular edge detection algorithm due to its superior performance, though it is not restricted to a shape or an orientation. The gradient of an image provides the information about how the image intensity level changes in both, x and y-axis, thus it is the base of several edge detection algorithms. First derivatives in image processing are implemented using the magnitude of the gradient. It is also possible to use specific operators like Sobel to smooth the differentiation operation. Image gradient direction is obtained using the trigonometric relationship between its magnitude in vertical and horizontal paths. For an edge detection algorithm based on a single monocular camera it is a valuable information, since the lane orientation in the camera perspective is predictable, therefore image points with a gradient direction out of the specified boundaries can be ignored. To prove it, this paper presents an approach using the direction of image gradient to delimit the feature extraction for vehicle nearest lanes, reducing thus the presence of outliers in the edge detection stage output. As lanes orientation are not constant in the road, due to curves or slope changing, vehicle Controller Area Network (CAN) signals are used in the strategy to adaptively correct the angle range of the lines to detect.