基于Adaboost-CSHG的特定类目标跟踪识别

目标跟踪识别是计算机视觉领域的热点研究对象。首先采用基于Adaboost的目标检测算法,训练得到了特定类目标坦克模型的级联分类器,对图像中的坦克目标完成了 “粗检测”;通过构建类属超图(CSHG)模型,采取Adaboost与CSHG相结合的方式,有效滤除了大量虚警,实现了对坦克目标的“精检测”,同时完成了对目标的跟踪;最后利用基于类属超图的目标识别原理对目标进行识别,实验结果表明该方法在简单背景和复杂背景图像条件下均具有可行性。     

Identifying underground voids using a GPR circular-end bow-tie antenna system based on a support vector machine

This article presents a pattern recognition approach based on discrete cosine transform (DCT) and polarization attributes to identify voids underground in ground penetrating radar (GPR) images. Features vectors composed of DCT coefficients supplying to the support vector machine classifier are studied, together with their linearity. To evaluate the proposed method, we hold an experimental study of GPR data obtained by numerical modelling of a GPR circular-end bow-tie antenna system using the finite-integration technique based simulator. In order to form the database of features, different acquisition scenarios of GPR models are achieved by varying buried object’s material type, position, shape, size parameters, and electric characteristics of subsurface medium. The robustness of the proposed system towards degradation of the generated GPR data is tested by introducing Gaussian and speckle noise. The experimental results show the proposed approach exhibits encouraging performance in terms of void identification with errors of object apex position in GPR images.     

Parallel particle filter for tracking road centrelines from high-resolution SAR images using detected road junctions as initial seed points

Acquiring road junction information is helpful for improving the quality of road network extraction. This article presents a new road network extraction method with three stages. First, road junction candidates are extracted by our previously proposed valley-finding algorithm. Second, numerous particle filters running in parallel track road centrelines starting from all of the detected junction candidates. Finally, the road centrelines are approximated by fitting the tracked centrepoints. The main contribution of this article lies in two aspects. First, road centrepoint tracking routes are launched simultaneously by considering the detected road junctions as starting points, which helps overcome the interference of various obstacles. Second, parallel tracking is implemented by a graphics processing unit (GPU) running accelerated particle filters, which significantly improves the execution time of the road network extraction task. The experimental results show that our proposed method not only handles various obstacles that occur on the roads capably, but also, on average, is 10.5 times as fast as previous methods. We compared the proposed method with two other existing methods in the literature using two different synthetic aperture radar (SAR) images to validate the superior performance of our proposed method.     

Preliminary study evaluating manual dexterity tests assessing gloves protecting against cuts and stabs by hand knives

The paper presents preliminary results on the research methodology of evaluating the ergonomic properties of gloves protecting against cuts and stabs by hand knives. Four manual dexterity tests were selected for the study: TEST 1: evaluation of fine finger movements pursuant to PN-EN 420; TEST 2: cylinder grip and pull test according to PN-EN 1082 evaluating gross movements of the arms and hands; TEST 3: Purdue Pegboard Test evaluating fine finger movements; TEST 4: evaluation of gross movements of the arms and hands while performing simulated occupational tasks. The tested gloves differed in terms of construction and material (metal mesh or knitwear incorporating a metal yarn) and were selected depending on the scope of work activities performed during meat cutting and boning. The tests were conducted on a homogeneous group of subjects. During the performance of the four dexterity tests, we monitored the loading of four groups of muscles of the upper limb (adductor pollicis, extensor carpi radialis, flexor carpi ulnaris, and biceps brachii) using surface electromyography (EMG). Additionally, subjective sensations concerning the strain on the upper limb were evaluated using a questionnaire survey.The objective of the study was to identify a group of tests that would be characterized by high sensitivity and ensure reliable assessment of gloves protecting against cuts and stabs by hand knives. The results showed that not all of the dexterity captured differences in the way the gloves affected dexterity. This was corroborated by electromyographic measurements, which revealed considerable differences in load of upper limb muscles when using various gloves and further supported by the subjective sensations of the participants, as reported in the questionnaire study. It was concluded that in order to reliably evaluate the ergonomic properties of gloves protecting against cuts and stabs by hand knives it is necessary to design new dexterity tests that would reflect actual workplace conditions, and could simulate occupational activities. Workplace observations helped to identify specific aspects of manual dexterity (fine, medium, gross), and types of hand movement associated with professional activities including different force configurations (finger flexion, wrist abduction, and pressing with the fingers and wrist). Based on those observations three new manual dexterity tests dedicated exclusively to evaluation of the ergonomic properties of gloves protecting against cuts and stabs by hand knives have been proposed.     

Single-crystal diamond micro-cupped resonators made by laser ablation

This paper presents a novel three-dimensional fabrication process of micro-scale shell resonator made of single-crystal diamond (SCD) called micro-cupped resonator (MCR). The key feature of the process is the application of laser ablation, which can contribute to the shaping process of SCD with higher accuracy, better structural symmetry, greater speed, and lower breakage rate. UV laser high precision processing machine has been employed for the ablation of SCD in the present investigation. This paper describes the principle of laser ablation of SCD and analyses the effects of beam parameters on ablation quality. Then MCR with better structural symmetry and less structural imperfection has been successfully fabricated based on optimum parameters by laser ablation. The MCR is promising for emerging applications such as micro rate-integrating gyroscope.     

基于容许集的多胞不确定系统三模RMPC

针对输入和状态受约束的多胞不确定线性系统,提出了基于容许集的扩大吸引域三模鲁棒模型预测控制方法.在多面体不变集离线模型预测控制算法的基础上引入容许集,以多面体不变集序列的并集作为模态1,基于N步容许集的控制容许集作为模态2,并利用离线设计和在线优化的控制策略,设计了三模变终端约束鲁棒模型预测控制算法,以实现系统渐近稳定.该算法不仅降低了在线运算量,而且扩大了吸引域.最后的仿真结果验证了所提出算法的有效性.     

基于扩展的SURF描述符的彩色图像配准技术*

目前大多数图像配准算法都需要先将彩色图像转换为灰度图像再进行图像配准,色彩信息的丢失可能引起图像的误匹配。本文在SURF算法的基础上,提出了构建颜色描述向量扩展SURF描述符,形成ESURF描述符,再进行图像配准的方法。该算法能够充分利用彩色图像的色彩信息,相比大多数算法基于灰度图像的配准方法有更高的鲁棒性,同时继承了SURF算法良好的性能。描述符性能测试和图像配准测试证明：ESURF算法比灰度图像SURF算法在图像尺度变化、旋转、模糊、视角变化、特别是光照变化方面有更高的鲁棒性。     

Low-complexity and energy efficient image compression scheme for wireless sensor networks

Currently most energy-constrained wireless sensor networks are designed with the object of minimizing the communication power at the cost of more computation. To achieve high compression efficiency, the main image compression algorithms used in wireless sensor networks are the high-complexity, state-of-the-art image compression standards, such as JPEG2000. These algorithms require complex hardware and make the energy consumption for computation comparable to communication energy dissipation. To reduce the hardware cost and the energy consumption of the sensor network, a low-complexity and energy efficient image compression scheme is proposed. The compression algorithm in the proposed scheme greatly lowers the computational complexity and reduces the required memory, while it still achieves required PSNR. The proposed implementation scheme of the image compression algorithm overcomes the computation and energy limitation of individual nodes by sharing the processing of tasks. And, it applies transmission range adjustment to save communication energy dissipation. Performance of the proposed scheme is investigated with respect to image quality and energy consumption. Simulation results show that it greatly prolongs the lifetime of the network under a specific image quality requirement.     

3D model based tracking for omnidirectional vision: A new spherical approach

The current work addresses the problem of 3D model tracking in the context of monocular and stereo omnidirectional vision in order to estimate the camera pose. To this end, we track 3D objects modeled by line segments because the straight line feature is often used to model the environment. Indeed, we are interested in mobile robot navigation using omnidirectional vision in structured environments. In the case of omnidirectional vision, 3D straight lines are projected as conics in omnidirectional images. Under certain conditions, these conics may have singularities.In this paper, we present two contributions. We, first, propose a new spherical formulation of the pose estimation withdrawing singularities, using an object model composed of lines. The theoretical formulation and the validation on synthetic images thus show that the new formulation clearly outperforms the former image plane one. The second contribution is the extension of the spherical representation to the stereovision case. We consider in the paper a sensor which combines a camera and four mirrors. Results in various situations show the robustness to illumination changes and local mistracking. As a final result, the proposed new stereo spherical formulation allows us to localize online a robot indoor and outdoor whereas the classical formulation fails.