Efficient beam alignment for millimeter-wave (mmWave) massive MIMO integrated sensing and communication (ISAC) must jointly address resource coupling and mobility. This letter proposes a weighted hierarchical dual-beam sweeping and tracking framework, where candidate communication/sensing beam pairs are evaluated by a coupled score with a power-split factor $ ho $ , enabling a controllable signal-to-interference-plus-noise ratio (SINR) tradeoff. Aperture-preserving hierarchical codebooks are adopted to synthesize wide beams by coherently combining full-aperture narrow beams with an offline phase taper. To enhance temporal robustness, tracker-assisted refinement based on cubature/extended Kalman filtering or spline extrapolation is further combined with a rollback mechanism. Simulation results show that the proposed method achieves higher angular accuracy, a smoother communication-sensing tradeoff, and lower error-spike and estimate-jump rates than representative benchmark methods, demonstrating better robustness and stability.

In this paper, to address the problem of intra-class consistency and inter-class variation in the deep convolutional neural network (CNN) based methods for semantic segmentation of images, we propose a class-aware feature regularization strategy to revise the features extracted by a deep convolutional neural network, without any change of the original network structure. A pixel-context similarity term is proposed to measure the consistency between feature vectors of pixels and class centers, which guarantees the intra-class consistency of pixels in the interior of an object and is supervised by a One-Hot label to preserve the inter-class variation of different objects. Based on the similarity term, we design a lightweight and efficient plug-in loss term to ensure that the features yielded by a deep CNN possess the quality of intra-class consistency and inter-class variation. As our ideal can be fulfilled effectively by the proposed plug-in loss term, we can simply incorporate it into a CNN-based segmentation model without changing the model structure. The effectiveness of the proposed strategy is proved by incorporating the loss term into some state-of-the-art segmentation models on Cityscapes and ADE20K datasets.

Visual SLAM is easily interfered by movable objects in dynamic scenes, which reduces the localization accuracy and robustness due to existence of inaccurate key points on movable objects. To address this problem, this paper proposes a visual SLAM algorithm for dynamic scenes based on target detection in RGB-D images. The algorithm first identifies movable objects in the scene using the Yolov5 target detector, whose results will be transmitted into a SLAM framework through socket communication. Then a threshold operation on a depth map is used to generate a mask of movable objects have been removed are inputted into the ORB-SLAM2 system. Experimental results show that the proposed algorithm successfully handles dynamic scenes, obtaining a better balance between processing speed and localization accuracy of the reconstructed map comparing with some other SLAM system for dynamic scenes.

针对原木端面存在污渍、裂痕和伐痕等导致原木轮廓难以被鲁棒地识别的问题,提出了结合图像和图形特征的原木轮廓识别方法.首先,引入YOLO V3,在对200多张原木图像样本进行学习后,实现利用图像信息进行目标检测;其次,利用原木轮廓图形上近似于圆的特点,采用轮廓重叠度计算和随机Hough变换校正YOLO V3识别结果的中心不准的问题.与同类原木图像的识别结果进行比较,结果表明,它能100％识别其中的完整原木,边缘的平均重叠度提高了10个点;在各类复杂端面轮廓情况下的识别结果中,该方法都有较好的鲁棒性,识别率达到98.8％.

Noising methods (NMs) include a set of local search methods and can be considered as simulated annealing algorithm or threshold accepting (TA) method when its components are properly chosen. This paper studies how to utilize NMs for solving the 0–1 knapsack problem (0–1 KP). Two noising strategies, noising variation of objective function and noising data, are used to help NMs escape from local optima. When noising variation of objective function is used, probabilistic acceptance or deterministic acceptance is used to decide whether to accept neighbor solutions. Two decreasing strategies, arithmetical decreasing and geometrical decreasing, are used to control the change of parameter noise-rate. In total, six variants of NMs including two TAs are designed to solve the 0–1 KP. In those variants, a hybrid greedy repair operator, which combines density-based and value-based greedy drop and add operators, is designed to get better balance between intensification and diversification. Extensive experiments were performed to compare the performances of the six variants of NMs. The performances of the six variants of NMs were also compared with some state-of-the-art metaheuristics on a wide range of small size, medium size, and large size 0–1 KP instances. Simulation results show that NMs are better than or competitive with other state-of-the-art metaheuristics.

In this paper, a parallel region merging strategy is proposed for partitioning Synthetic Aperture Radar (SAR) images into several disjoint regions, based on the region adjacency graph (RAG) of an initial partition and the nearest neighbor graph (NNG) produced from the RAG. Developed from the multi-direction ratio edge detector, a multi-scale-multi-direction (MSMD) one is used to extract edge strength map (ESM) of an initial SAR image, feeded into watershed transform to generate an initial partition result of the initial SAR image. Considering local image properties, which makes the generated NNG center around bi-node circles situated in interiors of homogeneous regions, many of which are independently located in different homogeneous regions, the predication of the parallelizability for bi-node circles is proposed to make the proposed parallel region merging strategy. The proposed parallel merging strategy simultaneously merges bi-node circles far away from boundaries of regions, characterized by the length of path from a node to the bi-node circle in the NNG. The performance of the proposed parallel merging strategy is analyzed theoretically and experimentally, and our experiments show that the proposed method outweighs other compared methods.

In this paper, a novel edge detector for synthetic aperture radar (SAR) images is proposed by introducing the Bhattacharyya coefficient (BC) combining with the rotated biwindow configuration. Based on the quantified input image, the BC is computed from two sample distribution histograms of local regions supported by the subwindows on the opposite sides of the pixel to be detected. With biwindows of different directions sliding through the image, multiple directional Bhattacharyya coefficient matrices are obtained, which are utilized to extract the edge strength map (ESM), characterizing the intensity variation in SAR images. Sequent nonmaximum suppression and hysteresis thresholding refine the extracted ESM into thin edges. Experiment results show that the proposed edge detector can accurately extract edges. Moreover, the BC-based ESM can act as a good precursor to guide SAR image segmentation based on region merging.

In this paper, we proposed a simple yet substantially efficient approach termed as Feature Matching via Guided Motion Field Consensus. The key idea of our approach is to model the transformation between two images by using the motion smooth constraint and use matching results on a small correspondence set with high inlier ratio to guide the matching on the whole image correspondences. In addition, we adopt a new regularization to overcome the overfitting of the matching process. Experiments demonstrate the practicability of our approach, and it is better than the state-of-the-art methods with better accuracy in feature matching.

在约束子集定义的基础上,提出面向旅游景点推荐的约束关联规则挖掘算法,将最为耗时的目标项集搜索限定在约束子集中,降低了数据集搜索的规模.同时通过约束条件提升了最终规则生成的针对性,避免大量无趣规则的生成,使得挖掘算法效率更高、挖掘结果更符合用户需求.最后在望路者文化旅游服务数据集中开展了示范应用研究,验证了所提出的算法可为旅游景点推荐提供更为合理的信息.

This paper presents a new method of parsing indoor scene from an RGB-D image using superpixel of the RGB image and region merging of depth information. The goal of parsing indoor scene is to reconstruct the interior wall and floor scene based on an RGB-D image, the architecture of Manhattan structure. Firstly, an original RGB image of an indoor scene is segmented into superpixels using SLIC method, and a region merging procedure is used to iteratively merge adjacent superpixels possessing some identical properties in RGB- and depth-channel, which assures that the pixels in a merged region have basically identical normal, which is essential for reconstructing indoor wall and floor plane from a RGB-D image. Secondly, the obtained regions of the scene are translated into plane surface using normal information of regions, and then wall segments and walls are extracted to remove the influence of furniture and persons in the indoor scene on the reconstruction of indoor wall and floor plane. Finally, the Manhattan structure wall and floor scene of an indoor scene can be reconstructed by using dynamic programming method on candidate wall segments. The experiments show that the proposed method obtains better 3D structures than the ones the state-of-the-art produced.

In this paper, a hierarchical region merging method is proposed for partitioning synthetic aperture radar (SAR) image into un-overlapping scene area, such as forest regions, urban regions, agricultural regions, and so on. The proposed method mainly consists of two steps: initial over-segmentation and hierarchical regions merging. The over-segmentation uses the watershed transform to the thresholded Bhattacharyya-coefficient-based edge strength map (BESM), and the hierarchical regions merging applies a new region merging cost weighted by a gradually increasing orientated edge strength penalty. There is a defect that the ratio-based edge detector widely used in homogeneous SAR image fails to distinguish the transitions between uniform and texture regions in high spatial resolution SAR image, and yields an initial over-segmentation result with some regions straddling multiple uniform or texture areas. To overcome this, the Bhattacharyya coefficient is used to replace the ratio-based edge detector for extracting the ESM of a SAR image by using a bi-rectangle-window configuration. Multi-scale windows are utilized to capture additional edge information. A new region merging cost is proposed based on the Kuiper's distance, weighted by a new gradually increasing orientated edge strength penalty term. The hierarchical region merging criterion is obtained with the increasing of the strength of the edge penalty. The effectiveness of the proposed method is demonstrated by comparing it qualitatively and quantitatively with several state-of-the-art methods.

针对课程教学学时数有限,而教学内容较多这一矛盾.本文探索一种基于视频课件的引导与督促式教学方法,并以数字信号处理课程教学为例,详细探讨了该教学方法的实施方案.该教学方法的主要思想由"引导"和"督促"两个环节组成.在"引导"环节,要求学生在课前认真观看教师录制的关于知识点的视频课件,确保课前基本了解重要知识点."督促"环节是由课前预习题目来达到目的,要求学生观看完课前知识点之后,完成预习题目.该教学方法能有效地培养学生的自学习惯和提高对新知识点的理解能力.

Color and depth information provided simultaneously in RGB-D images can be used to segment scenes into disjoint regions. In this paper, a graph-based segmentation method for RGB-D image is proposed, in which an adaptive data-driven combination of color- and normal-variation is presented to construct dissimilarity between two adjacent pixels and a novel region merging threshold exploiting normal information in adjacent regions is proposed to control the proceeding of the region merging. We evaluate our method on the NYU-v2 depth database and compare it with several published RGB-D partition methods. The experimental results show that our method is comparable with the state-of-the-art methods and provides more details of structures in the scene.

List-based simulated annealing (LBSA) algorithm, which uses list-based cooling scheme to control the change of parameter temperature, was first proposed for traveling salesman problem. This paper extends the application of LBSA algorithm for 0-1 knapsack problem (0-1 KP). A hybrid greedy repair and optimization operator, which combines density-based and value-based greedy repair and optimization operators, is designed to get better balance between intensification and diversification. Extensive experiments were performed to show the effectiveness and parameter robustness of a list-based cooling scheme and to verify the advantage of using hybrid greedy repair and optimization operator. Comparing experiments, which were conducted on small-scale, medium-scale, and large-scale 0-1 KP instances, have shown that LBSA algorithm is better than or competitive with other state-of-the-art metaheuristics.

程序设计基础教学过程中,学生有多种信息渠道了解课程知识点、多种信息渠道参与课程交流讨论.这一方面使得课堂教学对学生的吸引力相对降低,另一方面也给老师提供了更多渠道完成课程教学.针对这个问题,从信息化环境背景对教学存在的影响及程序设计基础课程本身的特点出发,围绕理论教学内容组织、实践环节实施、课程考核和督促方式三部分内容,以课程教学三个阶段(基础、提高、深入)为描述角度,对程序设计基础课程教学进行深入的探讨.

Non-rigid point set registration is a fundamental problem in many fields related to computer vision, medical image processing, and pattern recognition. In this paper, we develop a new point set registration method by using an adaptive weighted objective function, which formulates the alignment of two point sets as a mixture model estimation problem. The correspondences and the transformation are jointly recovered by using the expectation-maximization algorithm to obtain the promising results. First, the correspondences are established using local feature descriptors, and the adaptation parameters for the mixture model are computed from these correspondences. Then, the underlying transformation is recovered by minimizing the adaptive weighted objective function deduced from the mixture model. We demonstrate the advantages of the proposed method on various types of synthetic and real data and compare the results against those obtained using the state-of-the-art methods. The experimental results show that the proposed method is robust and outperforms the other registration approaches.

As a classical machine learning algorithm,FCM (fuzzy C-means) clustering algorithm is widely used in many applications. For datasets with different feature importance and different sample contribution, features weight based algorithms are proposed to improve the clustering quality in some degree, but can not obtain the optimal result. Based on the weighting strategy of feature and sample,the cost function of feature weight information entropy,and the combination of sample weight,attribute feature weight and objective function,an adaptive FCM clustering algorithm with both sample and feature weight is proposed,by adopting the iterative optimization to measure the weighting coefficients of each sample feature upon each cluster dynamically,as well as the importance of every sample to the clustering. The algorithm takes full account of the influence of different feature and sample contributions on the clustering results,so as to achieve the purpose of improving the clustering effect. The clustering algorithm is verified by using a set of test data sets from the UCI standard machine. The experimental results show that the proposed algorithm has better clustering accuracy than classical clustering algorithm with different distributions and different feature contributions.

遥感影像中的山区阴影覆盖范围广、去除难度大、影响信息提取精度,通过最大值选取函数(Max)与波段比值构建阴影检测模型(Shadow Detection,SD),结合坡度因子提取影像中山地阴影区域,并通过网格随机布置验证点验证精度;通过地面阴影亮度与阴影像元亮度变化规律,拟合影像阴影区亮度曲线模型,结合导函数,建立亮度恢复模型.对长汀县域的Landsat 8影像处理,获得的结果显示:山区阴影的提取精度为99.06％,Kappa系数为98％;聚类显示恢复区与非阴影属于同一类型;通过亮度恢复模型计算得出各个波段的阴影区域像元亮度平均值提升13％,标准差降低80％,距离系数降低96％,较ATCOR_3方法,像元亮度平均值提升6.7％,标准差降低73.7％,距离系数降低88.3％,较一元线性恢复方法,像元亮度平均值降低1.8％,标准差提升6.7％,距离系数降低90％.该方法在恢复山区阴影的过程中实现了不替换阴影像元,不干扰非阴影像元,能较好地保留阴影像元的光谱与亮度特征.

Non-rigid point set registration is often encountered in meical image processing, pattern recognition, and computer vision. This paper presents a new method for non-rigid point set registration that can be used to recover the underlying coherent spatial mapping (CSM). Firstly, putative correspondences between two point sets are established by using feature descriptors. Secondly, each point is expressed as a weighted sum of several nearest neighbors and the same relation holds after the transformation. Then, this local geometrical constraint is combined with the global model, and the transformation problem is solved by minimizing an error function. These two steps of recovering point correspondences and transformation are performed iteratively to obtained a promising result. Extensive experiments on various synthetic and real data demonstrate that the proposed approach is robust and outperforms the state-of-the-art methods.