A pattern framework driven by the Hamming distance for structured light-based reconstruction with a single image

Abstract

Structured light based patterns provide a means to capture the state of an object shape. However it may be inefficient when the object is freely moving, when its surface contains high curvature parts or in out of depth of field situations. For image-based robotic guidance in unstructured and dynamic environment, only one shot is required for capturing the shape of a moving region-of-interest. Then robust patterns and real-time capabilities must be targeted. To this end, we have developed a novel technique for the generation of coded patterns directly driven by the Hamming distance. The counterpart is the big amount of codes the coding/decoding algorithms have to face with a high desired Hamming distance. We show that the mean Hamming distance is a useful criterion for driving the patterns generation process and we give a way to predict its value. Furthermore, to ensure local uniqueness of codewords with consideration of many incomplete ones, the Perfect Map theory is involved. Then, we describe a pseudorandom/exhaustive algorithm to build patterns with more than 200×200 features, in a very short time, thanks to a splitting strategy which performs the Hamming tests in the codeword space instead of the pattern array. This leads to a significant reduction of the computational complexity and it may be applied to other purposes. Finally, real-time reconstructions from single images are reported and results are compared to the best known which are outperformed in many cases.

Three-dimensional surface reconstruction via a robust binary shape-coded structured light method

“…Reiss and Tommaselli 21 improved the coding volume with five different shapes; each shape owned four or six points for surface reconstruction. Maurice et al 22,23 presented a perfect submap generation with large Hamming distance. However, the coding window size of 3 × 3 decreased the code-correction ability for the scenes with depth discontinuities.…”

“…The binary shapes can be circle, disc, stripe, 19 thickened cuneiform, 21 thinned cuneiform, 22,23 polygon, 24 or specially designed shapes. 20,25 Albitar et al 19 adopted binary shapes instead of colors as the coding elements to generate a binary pattern based on M-array.…”

“…It is very challenging to detect and recognize the degraded pattern elements for traditional feature detectors. [19][20][21][22][23][24][25] Since the pattern elements are designed as a rhombic shape in our pattern, a graph can be generated by connecting four grid-points of the pattern element. Then, by collecting abundant pattern elements with blurring and distortions, an extensive training dataset can be set up for convolutional neural networks.…”

“…Image segmentation is usually applied to segment each pattern element, and the template matching is usually used to identify the pattern elements. [19][20][21][22][23][24][25] But the performance of pattern decoding is inferior when the pattern elements are greatly affected by complex factors, such as surface color, textures, distortion, reflections, and so on.…”

“…The primitive in color pattern can be coded by color multislits, [7][8][9] color stripes, [10][11][12] color grids, 13 color spots, 14,15 color diamonds, 16,17 or color squares. 18 For the binary geometrical patterns, the primitive can be represented by different geometrical shapes [19][20][21][22][23][24] or hybrid coding. 25 Compared with color coding methods, shape coding methods are more robust because they are less sensitive to surface color.…”