Crossing obstacle detection with a vehicle-mounted camera

Abstract

We propose a computer vision algorithm that detects obstacles crossing a vehicle's path with a monocular camera mounted on the vehicle. False positives are strongly suppressed even for low-resolution images by imposing constraints on feature-based optical flows. The constraints are derived from a model of crossing obstacle motion under perspective projection. A key concept in this model is “Relative Incoming Angle”, which is an angle between the camera's translational direction and relative velocity of a crossing obstacle with respect to the camera. We show a ROC curve that has been obtained by varying the Relative Incoming Angle using our dataset consisting of 18 scenes, 1456 frames. A representative point on the curve yields the detection rate of 59.7% and false positive rate of 2.6% (per-image).