The accurate identification of high-quality correspondences is a prerequisite task in feature-based point cloud registration. However, it is extremely challenging to handle the fusion of local and global features due to feature redundancy and complex spatial relationships. Given that Gestalt principles provide key advantages in analyzing local and global relationships, we propose a novel Gestalt-guided Parallel Interaction Network via orthogonal geometric consistency (GPI-Net) in this paper. It utilizes Gestalt principles to facilitate complementary communication between local and global information. Specifically, we introduce an orthogonal integration strategy to optimally reduce redundant information and generate a more compact global structure for high-quality correspondences. To capture geometric features in correspondences, we leverage a Gestalt Feature Attention (GFA) block through a hybrid utilization of self-attention and cross-attention mechanisms. Furthermore, to facilitate the integration of local detail information into the global structure, we design an innovative Dual-path Multi-Granularity parallel interaction aggregation (DMG) block to promote information exchange across different granularities. Extensive experiments on various challenging tasks demonstrate the superior performance of our proposed GPI-Net in comparison to existing methods. The code will be released at https://github.com/XXX/GPI-Net.

Power control acts as an important role in solving the near-far problem in cellular radio systems. A new distributed power control algorithm was proposed in this paper for cellular mobile radio systems, we called it balanced distributed power control (BDPC) algorithm, which can converge to the CIR balancing with probability one quickly. Compared with DPC (distributed power control) and FDPC (fully distributed power control), BDPC does not need any global information especially the normalization procedure of DPC, in the meantime it can prevent the transmitting powers from falling out of the desired range. The excellent properties of FDPC are also with BDPC.

The intelligence of an ALV (autonomous land vehicle) mostly comes from the vision system of the ALV. In order to improve the intelligence of the vision system, a knowledge-based road scene understanding system KRUS has been built. In the system, a road recognition algorithm combining fusing of edge and region information and using scene knowledge is presented, which makes the KRUS system intelligent enough to recognize road scenes robustly and precisely.

Preprocessing, which plays an important role in pattern recognition, is investigated from the point of view of real-time processing, and a set of one-pass processing algorithms are described. All of the algorithms, which are based on easy hardware implementation, only require one single cycle of parallel operations per image frame, and the operations are confined in a window of size 3*3. Computer simulation shows that the algorithms are efficient and easily realized in hardware.>