RESUMO
Obtaining accurate depth information is key to robot grasping tasks. However, for transparent objects, RGB-D cameras have difficulty perceiving them owing to the objects' refraction and reflection properties. This property makes it difficult for humanoid robots to perceive and grasp everyday transparent objects. To remedy this, existing studies usually remove transparent object areas using a model that learns patterns from the remaining opaque areas so that depth estimations can be completed. Notably, this frequently leads to deviations from the ground truth. In this study, we propose a new depth completion method [i.e., ClueDepth Grasp (CDGrasp)] that works more effectively with transparent objects in RGB-D images. Specifically, we propose a ClueDepth module, which leverages the geometry method to filter-out refractive and reflective points while preserving the correct depths, consequently providing crucial positional clues for object location. To acquire sufficient features to complete the depth map, we design a DenseFormer network that integrates DenseNet to extract local features and swin-transformer blocks to obtain the required global information. Furthermore, to fully utilize the information obtained from multi-modal visual maps, we devise a Multi-Modal U-Net Module to capture multiscale features. Extensive experiments conducted on the ClearGrasp dataset show that our method achieves state-of-the-art performance in terms of accuracy and generalization of depth completion for transparent objects, and the successful employment of a humanoid robot grasping capability verifies the efficacy of our proposed method.
RESUMO
OBJECTIVE: To quantity the amount of tetramethylpyrazine in Szechwan Lovage Rhizome (Chuanxiong, the rhizome of Ligusticum chuanxiong Hort., CX) and Cnidium Rhizome(Japanese Chuanxiong, the rhizome of Cnidium officinale Makino, JCX) for quality assessment. METHODS: An HPLC-DAD-MS technique was employed to detect tetramethylpyrazine in 27 CX and 10 JCX samples. Tetramethylpyrazine was separated on a Waters Symmetry C,, column (250 mm x 4. 6 mm, 5 µm). The mobile phase was methanol-acetonitrile-water(27: 1: 72) at a flow rate of 1. 0 mL/min. The column temperature was 35 °C. DAD detection wavelength was 280 nm, while electrospray ionization detector was set at positive mode to collect MS spectrum. RESULTS: In the total of 37 herb samples, 11 samples were found to contain tetramethylpyrazine with the mean amount of 2. 19 µg/g(n = 11). 6 of 27 CX samples and 5 of 10 JCX sample were found the existence of tetramethylpyrazine with the amount of 0. 60 - 11. 75 µg and 0. 61 - 3. 05 µg/g,respectively. The correlation was not found between tetramethylpyrazine and the cultivation area, morphological character, processing or storage method for CX and JCX samples. It was possible that tetramethylpyrazine resulted from the microbes in soil. CONCLUSION: The developed method is accurate to quantify tetramethylpyrazine in CX and JCX herbs. Both the two herbs indeed contain tetramethylpyrazine, but it is not suitable to be a chemical marker to assess the quality of CX and JCX owing to low content.
