3D point cloud primitive segmentation aims to segment an original entire point cloud into a set of geometric primitives with different types, which is widely used in the manufacturing industry. The primitive segmentation task is challenging faced with complex shapes and ambiguous boundaries. We observe that the boundary properties of point clouds have not been fully investigated and exploited in previous works, and the primitive segmentation performance is not satisfactory near boundaries, especially gradually-changed boundaries. In this paper, we propose a novel probabilistic boundary guided primitive segmentation network (PBPS) to improve the primitive segmentation ability by emphasizing the boundary cues. Firstly, the point cloud boundary is represented by Gaussian distribution instead of binary representation, which can describe boundaries more informatively and also provides an indication of the ambiguous relationship between point cloud boundaries and inner regions. Second, a probabilistic boundary-guided feature fusion module as well as an instance clustering and type voting strategy are proposed, which process the boundary points and non-boundary points conditioning on different boundary probabilities, to reduce the impact of boundary ambiguity on primitive segmentation. Thirdly, a primitive instance contrastive loss is designed which can relatively loosen the constraints on the distances from boundary points to centroid in the embedding space. The effectiveness of PBPS was verified by a series of experiments on two CAD-based datasets and two real-scene dataset.

Appearance quality assessment plays a crucial role in industrial product manufacturing, where traditional inspection methods struggle with the diverse surface structures and complex shapes. This article introduces a novel hierarchical viewpoint planning paradigm designed to tackle the challenges associated with mapping camera viewpoints onto complex object surfaces featuring demanding imaging quality requirements. Based on multilevel geometric representation of the object point cloud, the proposed paradigm utilizes a divide-and-conquer strategy for systematic and effective viewpoint planning, which encompasses both bottom–up and top–down methodologies tailored for regular and irregular surfaces, respectively. The bottom–up method employs gridization-based viewpoint generation for rapid acquisition of high-quality viewpoints, while the top–down method utilizes hybrid confidence and dynamic viewpoint optimization to achieve complete and high-quality surface coverage. By combining these complementary strategies, the proposed method ensures high-quality surface coverage for different types of geometric primitives. Experimental evaluations demonstrate superior performance compared with existing approaches, and real-world experiments validate the efficiency and effectiveness of the proposed method in industrial settings.

Foot measurement is necessary for personalized customization. Nowadays, people usually obtain their foot size by using a ruler or foot scanner. However, there are some disadvantages to this, namely, large measurement error and variance when using rulers, and high price and poor convenience when using a foot scanner. To tackle these problems, we obtain foot parameters by 3D foot reconstruction based on mobile phone photography. Firstly, foot images are taken by a mobile phone. Secondly, the SFM (Structure-from-Motion) algorithm is used to acquire the corresponding parameters and then to calculate the camera position to construct the sparse model. Thirdly, the PMVS (Patch-based Multi View System) is adopted to build a dense model. Finally, the Meshlab is used to process and measure the foot model. The result shows that the experimental error of the 3D foot reconstruction method is around 1 mm, which is tolerable for applications such as shoe tree customization. The experiment proves that the method can construct the 3D foot model efficiently and easily. This technology has broad application prospects in the fields of shoe size recommendation, high-end customized shoes and medical correction.

It is important to identify and remove the wastes not only from manufacturing process, but also from non-manufacturing process. In the last several decades, significant research achievements and practice benefits have been achieved about removing wastes from manufacturing process. Since the 1990s, some researchers and lean practitioners have paid more attention to removing waste from non-manufacturing process. Based on the authors ʼ research work and industrial practice, the paper introduces a kind of lean approach for removing waste from non-manufacturing process. In its case study, the order handling process in a value chain is described with respect to a factory and its downstream distribution centers ( DCs ). The paper proposes a lean approach solution for creating the improved order handling process, and analyze how great improvements in performance can be achieved. As a result, the significant achievement has created a win-win scenario for both the non-manufacturing process in a factory and non-manufacturing facilities ( like DCs ) across the value chain. It demonstrates that improvements have been made by removing waste from the non-manufacturing process that takes place within a factory as well as with external participants through the whole value chain. Likewise, the proposed lean approach has helped the case companies to achieve greater levels of efficiency and more benefits. Finally, some conclusions are drawn.

Any successful change in an organization requires an appropriate change management method and a process for involved staff and department to accept the change and become engaged in order to achieve its success. It is even more important and difficult to adopt a novel change management method to bring multiple organizations across the business value chain into the change implementation. This research does not focused on change management within a single organization but rather emphasizes a change management method, including an appropriate change framework, well-defined critical success factors (CSFs), and related tools for implementing change in multiple organizations. This article introduces one kind of change management method to support a process change through global value chain (GVC) in multiple organizations, and the method is used in a case study to achieve a successful change. In order to succeed in optimizing GVC performance, this research applies the proposed change management method to the case GVC, to support technical change by obtaining the staff’s full commitment and engagement. The achieved results from the case study prove that successful change comes not only through technical solutions implemented in the problem process throughout the GVC but also through strong support and engagement from all organizations and involved staff. The proposed change management method not only helped the case GVC to implement change successfully but also can help the relevant multiple organizations to improve the GVC performance and add value by optimizing their problem process.