Methods for ground target detection and recognition in 3-D laser data

The signal processing of three-dimensional laser data is a relatively new field of research, especially the high resolution applications. The laser based 3-D sensors give contrast where passive 2-D sensors in general have small or no contrast, as for instance in darkness. They give the possibility to separate objects at different distances. As long as you have some light passing through a covering material, such as for most cloth, vegetation, smoke, and Venetian blinds, it is possible to get a geometric view of the hidden objects. This geometric object data can be used for absolute measurements and is therefore also a strong basis for recognition. This report shows some of the studied methods to detect, segment and recognize objects in 3-D laser data and gives some examples. Only sensor systems placed on ground or close to ground in a fairly low angle of incidence are considered.

[1]  Fredrik Gustafsson,et al.  Ground Target Recognition Using Rectangle Estimation , 2006, IEEE Transactions on Image Processing.

[2]  Yonghuai Liu,et al.  Improving ICP with easy implementation for free-form surface matching , 2004, Pattern Recognit..

[3]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jonas Landgård.  Segmentering och klassificering av LiDAR-data , 2005 .

[5]  Z. Li,et al.  A fast expected time algorithm for the 2-D point pattern matching problem , 2004, Pattern Recognit..

[6]  Jitendra Malik,et al.  Recognizing Objects in Range Data Using Regional Point Descriptors , 2004, ECCV.

[7]  Christina Grönwall.  Ground Object Recognition using Laser Radar Data : Geometric Fitting, Performance Analysis, and Applications , 2006 .

[8]  G. Toussaint.  Solving geometric problems with the rotating calipers , 1983 .

[9]  Mille Millnert,et al.  Vehicle size and orientation estimation using geometric fitting , 2001 .

[10]  Qinfen Zheng,et al.  Model-based target recognition in pulsed ladar imagery , 2001, IEEE Trans. Image Process..

[11]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Stephane Ruel,et al.  Development of a practical 3D automatic target recognition and pose estimation algorithm , 2004, SPIE Defense + Commercial Sensing.

[13]  Richard M. Marino,et al.  Pose-independent automatic target detection and recognition using 3D LADAR data , 2004, SPIE Defense + Commercial Sensing.

[14]  Fredrik Gustafsson,et al.  Least Squares Fitting Articulated Objects , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[15]  Linda G. Shapiro,et al.  A new paradigm for recognizing 3-D objects from range data , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[16]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[17]  Harpreet S. Sawhney,et al.  Shapeme histogram projection and matching for partial object recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.