2.3.1. Spatter 2D Image Processing Algorithm

Algorithms for 2D image processing are less complex than those for 3D image processing. Tan et al. [40] captured spatter images using Kalman filter tracking, segmented the images with grayscale and edge information, and obtained spatter information using fully convolutional networks and Mask R-CNN. Yin et al. [61] projected the 3D spatter trajectory into a 2D plane with image processing, used a filtering technique to improve the sharpness of the spatter image, and tracked the spatter motion information frame by frame using ImageJ.

#### 2.3.2. Spatter 3D Image Processing Algorithm

Barrett et al. used a low-cost binocular sensor for spatter detection, laying a foundation for future analysis of the data [43]. Eschner et al. [44] used algorithms in a binocular sensor system to carry out many processes on the images, including (1) identifying particle positions and calibrating the camera system, (2) matching particles between multi-camera images, (3) determining the 3D coordinates, (4) using a priori knowledge of processes and particles to distinguish ghost particles from real particles, (5) tracking particles, and (6) processing the 3D data. Those processes require more complex algorithms to complete. Currently, they have enabled the construction of a quadruple-eye sensor system, which uses a third camera to achieve the recognition of ghost particles. However, relative to the binocular sensor detection system, the quadruple-eye sensor detection system must process a larger amount of information that is more difficult to process [45].

#### *2.4. Full-Cycle Detection of Spatter in L-PBF*

During L-PBF process, the full cycle of the spatter can be divided into three stages: the initial stage (generation), the flight stage (ejection), and the fall-back stage (re-deposition). The detection of the spatter in these three stages is conductive to the deep understanding

of the origin of the spatter, the correlation of the spatter and defect, and the influence of the spatter on the part.

