Statistical approach for distance estimation using Inverse Perspective Mapping on embedded platform

Abstract

The paper presents a real time image processing algorithm for distance estimation on Beagleboard. The system uses a single camera fixed at a stationary position to capture the real time image of target object and determine its distance in contrast to existing and most common vision algorithms of stereo vision.The image captured from a single forward facing camera suffers from high degree of uncertainty in object distance estimation due to the nonlinear relation between object height and its actual distance from camera. This uncertainty is eliminated by using Inverse Perspective Mapping to translate the front view captured by the photosensitive sensor to a bird's eye view. The focus of the paper is to present a statistical approach to scale the position of object in pixel to the real world physical distance. The proposed algorithm offers high efficiency in determining the distance of target object in a short time and thus aids the autonomous vehicle in intelligent navigation and feedback. The implementation is done using Intel OpenCV image processing libraries to reduce system overhead and is intended to work at least at 30 fps with VGA resolution.

Robust Inter-Vehicle Distance Estimation Method Based on Monocular Vision

“…In recent years, research on the methods for estimating the distance of monocular vision vehicles based on geometric models, which are largely divided into the inverse perspective mapping transformation method [3], projection geometric relationship method [5], and fitting modeling method [16], has achieved considerable results. In [4], [17], [18], [20], a distance estimation method based on IPM was proposed. The difference among these studies is the object detection method, such as the road removal algorithm [4], [17], threshold adjustment [18], and hue, saturation, and value (HSV) color mapping [20].…”

“…In [4], [17], [18], [20], a distance estimation method based on IPM was proposed. The difference among these studies is the object detection method, such as the road removal algorithm [4], [17], threshold adjustment [18], and hue, saturation, and value (HSV) color mapping [20]. The overall idea is to convert the original image into a bird s eye view, which approximates the image obtained from the top-down observation scene.…”

The effect of illumination compensation methods with histogram back projection for camshift application

“…The system had been tested in various situations and was found to be efficient in distance estimation and object detection. However, it is extremely perceptive to changes in the environmental conditions [6]. It was also found that its tolerance to changes in light intensity can be improved by observing its effect on predicted distance value.…”

“…Another method evaluated was Inverse Perspective Mapping. This method utilized inverse perspective mapping for distance estimation [5][6]. To predict the distance of the tracked object under various conditions, regression analysis was employed to derive the equation needed [6].…”

“…This method utilized inverse perspective mapping for distance estimation [5][6]. To predict the distance of the tracked object under various conditions, regression analysis was employed to derive the equation needed [6]. Linear regression models are straightforward and require minimum memory to be implemented, so they perform well on embedded controllers that have limited memory space [7].…”