基于前视三维声呐的轨条砦识别方法

A Method of Erect Rail Barricade Recognition Based on Forward-Looking 3D Sonar

针对轨条砦目标探测和识别困难的问题,文中利用前视三维成像声呐提高轨条砦目标探测效果,并设计一种基于单步检测(SSD)的三维点云目标识别方法(PCSSD)。该方法首先对原始波束域数据进行阈值滤波和直通滤波处理;接着,对滤波后的三维点云数据进行前向投影,并得到深度灰度图和深度伪彩图;而后,利用SSD目标检测模型对深度伪彩图进行检测识别;随后,从深度灰度图检测目标特征中计算目标的深度范围;最后,结合二维目标检测结果和深度范围对三维点云中的轨条砦目标进行标注。与此同时,提出了一个基于多尺度注意力机制的特征提取模块,并利用该模块设计了改进的目标检测模型SSD-MV3ME。在三维点云轨条砦目标检测数据集GTZ上,SSD-MV3ME在检测时间基本相等的条件下,检测精度比轻量化目标检测模型SSD-MV3提升1.05%,模型参数减少2482 KB。实验结果表明,基于SSD-MV3ME的PCSSD更适合轨条砦目标识别任务。

To alleviate the difficulty in detecting and recognizing erect rail barricades, a forward-looking threedimensional(3D) imaging sonar is used to improve the effectiveness of erect rail barricade recognition, and a single shot detector(SSD)-based 3D point cloud(PCSSD) target recognition method is proposed. First, the original beam domain data are processed using a threshold filter and pass-through filter. Next, forward projection of the filtered 3D point cloud data is performed, and the grayscale depth image and pseudo color depth image are obtained. The SSD was then used to recognize the targets from the pseudo color depth image. Subsequently, the depth range of the selected targets is calculated based on the characteristics of the targets recognized from the grayscale depth image. Finally, erect rail barricades in the form of 3D point clouds were detected by combining the two-dimensional detection results and the corresponding depth range. A feature extraction block based on the multi-scale attention mechanism was proposed, and a novel target detector SSD-MV3ME was used for the design. On the 3D point cloud erect rail barricades dataset GTZ, under the condition of the same detection time,the detection accuracy of SSD-MV3ME was higher than that of the lightweight target detection model SSD-MV3 by 1.05%,and the model parameters had less than 2 482 kB. The results show that the PCSSD based on SSD-MV3ME is more suitable for erect rail barricade recognition tasks.