Search

Automatic image segmentation of surgical instruments is a fundamental task in robot-assisted minimally invasive surgery, which greatly improves the context awareness of surgeons during the operation. A novel method based on Mask R-CNN is proposed in this paper to realize accurate instance segmentation of surgical instruments.A novel feature extraction backbone is built, which could extract both local features through the convolutional neural network branch and global representations through the Swin-Transformer branch. Moreover, skip fusions are applied in the backbone to fuse both features and improve the generalization ability of the network.The proposed method is evaluated on the dataset of MICCAI 2017 EndoVis Challenge with three segmentation tasks and shows state-of-the-art performance with an mIoU of 0.5873 in type segmentation and 0.7408 in part segmentation. Furthermore, the results of ablation studies prove that the proposed novel backbone contributes to at least 17% improvement in mIoU.The promising results demonstrate that our method can effectively extract global representations as well as local features in the segmentation of surgical instruments and improve the accuracy of segmentation. With the proposed novel backbone, the network can segment the contours of surgical instruments' end tips more precisely. This method can provide more accurate data for localization and pose estimation of surgical instruments, and make a further contribution to the automation of robot-assisted minimally invasive surgery.

With the continuous development and progress of society, electricity has been integrated into people’s lives. However, power transmission is a very complex process that requires power transmission and power system conversion. A large amount of data will be generated during the operation of the power system. Through these data, we can use electricity better and more efficiently. This paper aims to study the power system data application based on data association rules. Based on the analysis of data association rules related algorithms and the application of data association algorithms in the power system, a power failure prediction system is designed and the performance of the system is analyzed. The test results show that the system has a very high transaction success rate, the longest response time does not exceed 20 seconds, and the CPU is operating normally, reaching the expected expectations.

In recent years image fusion plays a vital role in the image processing area. Fused images would help in doing many applications in image processing like segmentation, image enhancement and many.In order to improve the effect of fusion visible and infrared image images of the same scene, this paper presents an image fusion method based on lifting wavelet domain. Firstly, the source images are decomposed using lifting wavelet domain transform (LWT). Secondly, a weighted average approach based on normalized Shannon entropy is used to fuse low frequency lifting wavelet coefficients of the visible and infrared images. The fusion rule of local energy maximum is used to combine corresponding high frequency coefficients. After fusing low and high frequency coefficients of the source images, the final fused image is obtained using the inverse LWT. The experiments show that the proposed method provides improved subjective and objectives results as compared to previous image fusion methods such as Laplacian transform and traditional Wavelet transform. DOI: http://dx.doi.org/10.11591/telkomnika.v11i11.2898 Full Text: PDF