Wide-angle vision for road views

Abstract

The field-of-view of a wide-angle image is greater than (say) 90 degrees, and so contains more information than available in a standard image. A wide field-of-view is more advantageous than standard input for understanding the geometry of 3D scenes, and for estimating the poses of panoramic sensors within such scenes. Thus, wide-angle imaging sensors and methodologies are commonly used in various road-safety, street surveillance, street virtual touring, or street 3D modelling applications. The paper reviews related wide-angle vision technologies by focusing on mathematical issues rather than on hardware.

Moving Object Detection based on Reverse Projection Error Model

“…Compared with ordinary plane cameras, fish-eye camera enlarges the viewing Angle range through multiple refraction of light. Its mapping relationship can be expressed as equation (1).…”

“…Moving object detection is an important research topic in the field of vehicle auxiliary driving and automatic driving. Due to the advantages of rich information, low cost, convenient installation, the monocular fish-eye camera has a broad application prospect in the on-board field [1,2]. Compared with moving object detection in static environment [3][4][5], in the vehicle-mounted environment, the camera moves along with the car, making the originally stationary background points in the image also move, which makes moving object detection more difficult.…”

Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function

“…[23,[25][26][27]] to train a neural network which by the regression method can make an adjustment of our measure− ments and theoretically approximated to the real value. To obtain the minimum error during the training [28], the mean square error function was used…”