6D target object detection is of great importance to many applications such as robotics, industrial automation, and unmanned vehicles and is increasingly influencing broad industries including manufacturing, transportation, and retail industries, to name a few. This paper focuses on detecting the 6D poses of the target objects from the point cloud of a cluttered scene. However, conventional point cloud-based 6D object detection methods rely on the robustness of key-point detection results that are not straightforward for humans to understand. The drawback makes conventional point cloud-based methods require expert knowledge to tune. In this paper, we introduced a 6D target object detection method that uses segmented object point cloud patches instead of key points to predict object 6D poses and identity. Our main contributions are an end-to-end data-driven pose correction model that is enhanced with a novel simple yet efficient basis spanning layer booster. Experiments show that although the proposed model is trained only using object CAD models, its 6D detection performance matches that of the models using view data. Thus, the proposed method is suitable for 6D detection applications that have object CAD models instead of labeled scene data.

Laser triangulation sensors (LTS) are widely used to acquire depth information in industrial applications. However, the parameters of the components, e.g., the camera, of the off-the-shelf LTS are typically unknown. This makes it difficult to recalibrate the degenerated LTS devices during regular maintenance operations. In this paper, a novel one-dimensional target-based camera intrinsic matrix-free LTS calibration method is proposed. In contrast to conventional methods that calibrate the LTS based on the precise camera intrinsic matrix, we formulate the LTS calibration as an optimization problem taking all parameters of the LTS into account, simultaneously. In this way, many pairs of the camera intrinsic matrix and the equation of the laser plane can be solved and different pairs of parameters are equivalent for displacement measurement. A closed-form solution of the position of the one-dimensional target is proposed to make the parameters of the LTS optimizable. The results of simulations and experiments show that the proposed method can calibrate the LTS without knowing the camera intrinsic matrix. In addition, the proposed approach significantly improves the displacement measurement precision of the LTS after calibration. In conclusion, the proposed method proved that the precise camera intrinsic matrix is not the necessary condition for LTS displacement measurement.

X-ray images are commonly used to ensure the security of devices in quality inspection industry. The recognition of signs printed on X-ray weld images plays an essential role in digital traceability system of manufacturing industry. However, the scales of objects vary different greatly in weld images, and it hinders us to achieve satisfactory recognition. In this paper, we propose a signs recognition framework based on convolutional neural networks (CNNs) for weld images. The proposed framework firstly contains a shallow classification network for correcting the pose of images. Moreover, we present a novel spatial and channel enhancement (SCE) module to address the above scale problem. This module can integrate multi-scale features and adaptively assign weights for each feature source. Based on SCE module, a narrow network is designed for final weld information recognition. To enhance the practicability of our framework, we carefully design the architecture of framework with a few parameters and computations. Experimental results show that our framework achieves 99.7% accuracy with 1.1 giga floating-point of operations (GFLOPs) on classification stage, and 90.0 mean average precision (mAP) with 176.1 frames per second (FPS) on recognition stage.