Real Time Speed Estimation of Moving Vehicles from Side View Images from an Uncalibrated Video Camera

Abstract

In order to estimate the speed of a moving vehicle with side view camera images, velocity vectors of a sufficient number of reference points identified on the vehicle must be found using frame images. This procedure involves two main steps. In the first step, a sufficient number of points from the vehicle is selected, and these points must be accurately tracked on at least two successive video frames. In the second step, by using the displacement vectors of the tracked points and passed time, the velocity vectors of those points are computed. Computed velocity vectors are defined in the video image coordinate system and displacement vectors are measured by the means of pixel units. Then the magnitudes of the computed vectors in image space should be transformed to the object space to find the absolute values of these magnitudes. This transformation requires an image to object space information in a mathematical sense that is achieved by means of the calibration and orientation parameters of the video frame images. This paper presents proposed solutions for the problems of using side view camera images mentioned here.

Parallel Implementation of a Video-based Vehicle Speed Measurement System for Municipal Roadways

“…After the tracking step, the vehicle's speed is calculated using a spherical projection that relates image movement with the vehicle's displacement. Authors in [15] used a frame differencing method for vehicle detection, which selects special points with large spatial gradients in two orthogonal directions within the vehicle's coverage area to track features. Therefore, the vehicle's speed was calculated by the means of velocity vectors obtained from the tracking step using an optical flow method.…”

Driver perception uncertainty in perceived relative speed and reaction time in car following – A quantum optical flow perspective

“…The perceived light mass of LV (i:e., m j D !i ðtÞÞ refers to the magnitude of m j D !i ðtÞ perceived by the FV driver (i:e., the participant). The magnitude of m j D !i ðtÞ at different relative speeds was transformed into input types using the Lucas-Kanade optical flow algorithm (Dogan et al, 2010) in OpenCV software in the experiment.…”

Performance of two low-cost GPS receivers for ground speed measurement under varying speed conditions

“…The front or fifth wheel-based sensors as well as the magnetic pickup sensors are affected by wheel slip requiring different calibration equations for different surfaces (Tompkins et al 1988). Some researchers used a video camera and image processing to estimate real time speed of moving vehicles from the images (Czajewski and Iwanowski 2010;Dogan et al 2010).…”