Reconstructing Images of Bar Codes for Construction Site Object Recognition

Abstract

This paper discusses a general approach to reconstructing ground truth intensity images of bar codes that have been distorted by LADAR optics. The first part of this paper describes the experimental data collection of several bar code images along with experimental estimates of the LADAR beam size and configuration at various distances from the source. Mathematical models of the beam size and configuration were developed and were applied through a convolution process to a simulated set of bar code images similar to the original experiment. This was done in order to estimate beam spread models (beam spread models are unique to each specific LADAR) to be used in a deconvolution process to reconstruct the original bar code images from the distorted images. In the convolution process a distorted image in vector form g is associated with a ground truth image f and each element of g is computed as a weighted average of neighboring elements of f to that associated element. The deconvolution process involves a least squares procedure that approximately solves a matrix equation of the form Hf = g where H is a large sparse matrix that is made up of elements from the beam spread function.

Pose Estimation of Construction Materials Using Multiple ID Devices for Parts and Packets Unification

“…Distance measurement systems (e.g., stereo vision systems) and light detection and ranging systems (e.g., laser range finders) are used for three‐dimensional object‐pose estimation (Gilsinn et al, 2002; Shih, 2002). These systems are useful because they can measure the distance directly and can also accurately measure the three‐dimensional object pose; however, in a cloudy environment, such as construction sites, there are occlusion problems in the ID and pose estimation of objects.…”

Deconvolving LADAR images of bar codes for construction site object recognition

“…Values are in meters % Bars are numbered as follows: % First index is the bar number % Lowest row, left to right: 1,2,3 % Middle row: 4,5,6 % Top row: 7,8,9 % Second index is comer number on bar (clockwise): % Comer 1 is lower left, Comer 2 is upper left, % Comer 3 is upper right, Comer 4 is lower right. % % Offset downwards by the ground truth overlap % bar_x (7,2) bar_x (7,3) bar_x (8,2) bar_x (8,3) bar_x (9,2) bar_x (9,3) bar_x (7,l) bar_x (7,4) 0.1952 + ((ma(i)-l)/2)*delta; x is a vector representing the ground truth image stored by columns of length nf*nf. b is the filtered image stored by columns of length ng*ng.…”

“…In either case read the matrix into the array a for %easier handling. bar_x (8,l) bar_x (8,4) bar_x (9,l) bar_x (9,4) bar_x (4,2) bar_x (4,3) bar_x (5,2) bar_x (5,3) bar_x (6,2) bar_x (6,3) bar_x (4,l) bar_x ( for j = l:nf y = (j-l)*delta; for k = l:nf %go down rows first then colums…”

Identification Recovery Scheme using Quick Response (QR) Code and Watermarking Technique

“…Currently, two-dimensional barcodes [1,2,3,4,5,6] are used to increase encoding space. Such two-dimensional barcodes as QR code, GS1 DataBar, Data Matrix, PDF417, and MaxiCode are widely implemented in daily life.…”