Monocular Rear-View Obstacle Detection Using Residual Flow

We present a system for automatically detecting obstacles from a moving vehicle using a monocular wide angle camera. Our system was developed in the context of finding obstacles and particularly children when backing up. Camera viewpoint is transformed to a virtual bird-eye view. We developed a novel image registration algorithm to obtain ego-motion that in combination with variational dense optical flow outputs a residual motion map with respect to the ground. The residual motion map is used to identify and segment 3D and moving objects. Our main contribution is the feature-based image registration algorithm that is able to separate and obtain ground layer ego-motion accurately even in cases of ground covering only 20% of the image, outperforming RANSAC.

[1]  Dan Levi,et al.  Part-Based Feature Synthesis for Human Detection , 2010, ECCV.

[2]  Kurt Konolige,et al.  Large-Scale Visual Odometry for Rough Terrain , 2007, ISRR.

[3]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Remy Bendahan,et al.  Real-Time Monocular 3D Vision System , 2009 .

[5]  Chong Sun,et al.  A real-time rear view camera based obstacle detection , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[6]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[7]  Takeo Kanade,et al.  Transforming camera geometry to a virtual downward-looking camera: robust ego-motion estimation and ground-layer detection , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[8]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[9]  Bernard Chazelle,et al.  A minimum spanning tree algorithm with inverse-Ackermann type complexity , 2000, JACM.

[10]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[11]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[12]  Alberto Broggi,et al.  StereoBox: A Robust and Efficient Solution for Automotive Short-Range Obstacle Detection , 2007, EURASIP J. Embed. Syst..

[13]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[14]  Timo Kohlberger,et al.  Universität Des Saarlandes Fachrichtung 6.1 – Mathematik Variational Optic Flow Computation in Real-time Variational Optic Flow Computation in Real-time , 2022 .

[15]  Baoxin Li,et al.  Homography-based ground detection for a mobile robot platform using a single camera , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[16]  Norman Weyrich,et al.  A single camera based rear obstacle detection system , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[17]  Dennis A. Guenther,et al.  Perception/Reaction Time Values for Accident Reconstruction , 1989 .

[18]  Yuri Owechko,et al.  Parts-based object recognition seeded by frequency-tuned saliency for child detection in active safety , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.