基于信度评估的线结构光多重曝光条纹提取

Multiple Exposure Stripe Extraction for Line Structured Light Based on Confidence Evaluation

在单线结构光三角测量法的实际应用中,图像中条纹截面灰度分布的可靠性是保证条纹中心提取精度的重要基础。在物体表面反射特性不均匀的测量场景中,受欠曝光与过曝光的双重影响,造成条纹截面灰度分布不均匀、条纹中心可信度低等问题。基于上述问题,对复杂反射特性表面的单线结构光条纹提取技术进行了研究。提出了一种基于信度评估的条纹提取方法。创新性地应用了条纹能量密度与条纹宽度相结合的双参数评价标准,有效避免了单一能量信度标准下约束力不够的问题。该方法依据信度阈值识别多重曝光图像中的可信条纹,并将可信条纹拼接重建成最终条纹图像。试验结果表明,重建图像具有全局可信度,有效提升了条纹中心计算精度。该方法能够为复杂场景下三维测量技术的发展提供一定参考。

In the practical application of single-line structured light triangulation,the reliability of the gray scale distribution of the stripe cross-section in the image is an important basis for ensuring the accuracy of stripe center extraction.In the measurement scenarios with uneven reflection characteristics of the object surface,the double effects of underexposure and overexposure result in uneven gray scale distribution of the stripe cross-section and low reliability of the stripe center.Based on the above problems,a single-line structured light streak extraction technique for surfaces with complex reflection characteristics is investigated.A stripe extraction method based on confidence evaluation is proposed.The two-parameter evaluation criterion combining stripe energy density and stripe width is innovatively applied,which effectively avoids the problem of insufficient binding under a single energy confidence criterion.The method recognizes the plausible stripes in the multi-exposure image based on the confidence threshold and reconstructs the final stripe image by splicing the plausible stripes.The experimental results show that the reconstructed image has global confidence and effectively improves the accuracy of stripe center calculation.This method can provide some reference for the development of 3D measurement technology in complex scenes.