Entire surface point clouds in complex objects cannot be captured in a single direction by using noncontact measurement methods, such as machine vision; therefore, different direction point clouds should be obtained and registered. However, high efficiency and precision are crucial for registration methods when dealing with huge number of point clouds. To solve this problem, an improved registration algorithm based on double threshold feature extraction and distance disparity matrix (DDM) is proposed in this study. Firstly, feature points are extracted with double thresholds using normal vectors and curvature to reduce the number of points. Secondly, a fast point feature histogram is established to describe the feature points and obtain the initial corresponding point pairs. Thirdly, obviously wrong corresponding point pairs are eliminated as much as possible by analysing the Euclidean invariant features of rigid body transformation combined with the DDM algorithm. Finally, the sample consensus initial alignment and the iterative closest point algorithms are used to complete the registration. Experimental results show that the proposed algorithm can quickly process large data point clouds and achieve efficient and precise matching of target objects. It can be used to improve the efficiency and precision of registration in distributed or mobile 3D measurement systems.
The deformation of large glass substrate in air-flotation system affects detection accuracy of inspection instrument. According to the gas lubrication theory, Timoshenko’s thin film theory and the simulation figure of the pressure distribution of the air film flow field, the air load distribution model of the air film is established, and the deformation expression of the large liquid crystal glass substrate in air-flotation system is given. On this basis, a theoretical design method for designing nozzle pitch of orifice throttling air-flotation system was proposed. Combined with examples, the results of theories and simulation are compared. An experiment on the deformation of the glass substrate was carried out on an experimental prototype. The difference between the experimental results and the theoretical results does not exceed 10%.
n order to completely avoid the inter-axis coupling phenomenon in the triaxial force measurement process and improve the measurement accuracy, an air-supported force measurement method considering both supporting and force measurement is proposed. Based on this, a triaxial force measurement device without inter-axis coupling is constructed. The model of air-supported one-axis force measuring unit and air-supported triaxial force measurement device are established. An air-supported triaxial force measurement platform is developed to explore the measurement accuracy of the force in each axial direction and the Inter-axis coupling phenomenon. The experimental results show that the air-supported triaxial force measurement platform has the characteristics of "no Inter-axis coupling" and "high precision". The measurement error of the air-supported triaxial force measurement platform is 0.17% in the x-axis direction and 0.10% in the y-axis direction.
Automatic defect-detection technology based on deep learning is increasingly used for distinguishing production quality by many industries. However, production lines are usually installed with lots of function modules, which make it difficult to integrate new modules. Common deep learning models run on PC platforms and require a big space with high cost, while ARM64 mobile platforms are much smaller with less cost and equivalent connectivity but also weaker performance. Considering these facts, ARM64 platforms with a fully optimized model are the best solution for adding a defect-detection function for existing production lines. This paper focused on a mobile-optimized model to achieve higher speed and equivalent precision on the ARM64 mobile platform for detection. First, the model structure is simplified by reducing the redundancy of feature maps to increase the network inference speed. Second, a convolutional block attention module is attached to compensate for the decrease in precision caused by structure simplification. Furthermore, a transfer learning method is adopted to improve training performance. Finally, the trained and compiled module is exported to the PyTorch Mobile format and deployed on the mobile platform application to execute its defect-detection function. The results show that the optimized network achieves a speed of 2.124 fps, 210.7% compared with that of You Only Look Once v5n, i.e., 1.008 fps, on the RK3399 ARM64 platform, and has an average mAP of 99.2%. The studied mobile-optimized model has better speed and equivalent precision and can be available on many different ARM64 platforms regardless of the processor manufacturer. It can satisfy the need for real-time defect detection and can be used in similar scenarios. In the future, more improvements could be made such as deploying on platforms with NPU support to achieve faster speed, exploring the relationships between dataset properties and transfer learning effects, even training and running the model directly on ARM64 platforms.
A large liquid crystal glass substrate detection instrument usually uses the air flotation platform to support a glass substrate. The glass substrate will be deformed by air pressure on the air flotation platform, which will affect the accuracy of detection. In this paper, combined with the characteristics of the detection method of the detection instrument, an optimal detection scanning path with the minimum deflection variation range of the glass substrate is planned so as to minimize the influence of glass substrate deformation on the detection accuracy. In theory, the calculation model of the deflection variation ranges of different paths on the glass substrate is established, the numerical method is used to solve it, and finally, the optimal scanning path for the optical inspection is obtained. The experimental results verify the correctness of the model.