This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Multi-Modal Image Segmentation for Obstacle Detection and Masking
Technical Paper
2014-01-0164
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
A novel multi-modal scene segmentation algorithm for obstacle identification and masking is presented in this work. A co-registered data set is generated from monocular camera and light detection and ranging (LIDAR) sensors. This calibrated data enables 3D scene information to be mapped to time-synchronized 2D camera images, where discontinuities in the ranging data indicate the increased likelihood of obstacle edges. Applications include Advanced Driver Assistance Systems (ADAS) which address lane-departure, pedestrian protection and collision avoidance and require both high-quality image segmentation and computational efficiency. Simulated and experimental results that demonstrate system performance are presented.
Recommended Content
Authors
Citation
Lee, C., Zhang, H., Nguyen, H., Wu, Y. et al., "Multi-Modal Image Segmentation for Obstacle Detection and Masking," SAE Technical Paper 2014-01-0164, 2014, https://doi.org/10.4271/2014-01-0164.Also In
References
- Heikkila J. and Silven O. A four-step camera calibration procedure with implicit image correction the Computer Vision and Pattern Recognition 1106 1112 1997 Proceedings., 1997 IEEE Computer Society Conference on 1997
- Hartley Richard and Zisserman Andrew Multiple View Geometry in Computer Vision Cambridge University Press 155 157 0-521-54051-8 2003
- He Qiang , Chu Chee-Hung Henry Lane Detection and Tracking through Affine Rectification Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2007) Tokyo Japan May 16 18 2007
- Liebowitz D. and Zisserman A. Metric rectification for perspective images of planes the Computer Vision and Pattern Recognition 482 488 1998 Proceedings. 1998 IEEE Computer Society Conference on 1998