Fast‐moving coin recognition using deep learning

Multimedia Tools and Applications - Deep learning has made essential contributions to the development of visual object detection and recognition. Identifying fast-moving objects from the viewpoint...     

组件感知的高分辨率三维物体重建方法

基于体素表示的三维物体重建计算代价会随着体素分辨率的增加呈立方增长.为了缓解这一问题,提出组件感知的三维物体重建方法,将三维物体分解成多个组件,通过预测组件几何结构和组装组件的方式重建三维物体,从而将高分辨率三维物体的重建问题分解成一系列低分辨率组件的重建问题.组件感知的三维物体重建方法使用组件位置预测模块预测所有组件的位置;使用组件特征提取模块融合组件表观特征与组件几何特征生成组件联合特征;使用组件几何结构重建模块根据组件联合特征重建组件的几何形状;最后将所有组件按其位置信息组装成高分辨率的三维物体.实验使用ShapeNet数据集在一个拥有12 GB内存的NVIDIA 1080 Maxwell GPU上进行.对比方法包括一个基于八叉树的高分辨率重建方法、一个基于LSTM的低分辨率重建方法和一个使用编码器-解码器架构的Baseline方法.高分辨率重建结果显示,组件感知的三维物体重建方法能够以较小的计算代价取得满意的高分辨率三维物体重建精度.在低分辨率重建实验上,该方法也取得了更高的重建精度,在13个类别上的平均精度达到了0.618.     

Video super-resolution reconstruction method based on deep Back projection and motion feature fusion

How to effectively utilize inter-frame redundancies is the key to improve the accuracy and speed of video super-resolution reconstruction methods. Previous methods usually process every frame in the whole video in the same way, and do not make full use of redundant information between frames, resulting in low accuracy or long reconstruction time. In this paper, we propose the idea of reconstructing key frames and non-key frames respectively, and give a video super-resolution reconstruction method based on deep back projection and motion feature fusion. Key-frame reconstruction subnet can obtain key frame features and reconstruction results with high accuracy. For non-key frames, key frame features can be reused by fusing them and motion features, so as to obtain accurate non-key frame features and reconstruction results quickly. Experiments on several public datasets show that the proposed method performs better than the state-of-the-art methods, and has good robustness.

     

A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition

Palmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition, and have achieved impressive results. However, the research on deep learning-based palmprint recognition and palm vein recognition is still very preliminary. In this paper, in order to investigate the problem of deep learning based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct performance evaluation of seventeen representative and classic convolutional neural networks (CNNs) on one 3D palmprint database, five 2D palmprint databases and two palm vein databases. A lot of experiments have been carried out in the conditions of different network structures, different learning rates, and different numbers of network layers. We have also conducted experiments on both separate data mode and mixed data mode. Experimental results show that these classic CNNs can achieve promising recognition results, and the recognition performance of recently proposed CNNs is better. Particularly, among classic CNNs, one of the recently proposed classic CNNs, i.e., EfficientNet achieves the best recognition accuracy. However, the recognition performance of classic CNNs is still slightly worse than that of some traditional recognition methods.

     

基于检测与跟踪相互迭代的极暗弱目标搜索算法

针对极低信噪比（LSNR）情况下暗弱运动目标和背景噪声的强度难以区分的问题,提出了一种基于检测与跟踪相互迭代的极暗弱目标搜索算法,总体上采用将时域检测与空域跟踪的过程联合、迭代进行的新型策略。首先,在检测过程中计算检测窗口内信号片段与已经提取的背景估计特征的差别;然后,在跟踪过程中运用动态规划算法保留使得轨迹能量累积最大的轨迹;最后,自适应地调整下一检测过程中被保留轨迹的检测器阈值参数,使该轨迹内的像素能以更宽容的策略被保留到下一检测跟踪阶段。实验测试结果表明,所提算法可以在1%~2%的虚警率和约70%的检测率下探测到低至0 dB的暗弱运动目标。可见该算法可有效改善对LSNR暗弱目标的检测能力。     

基于Siamese-YOLOv4的印刷品缺陷目标检测

在印刷工业生产中,针对直接使用YOLOv4网络进行印刷缺陷目标检测精度低、所需训练样本数量大的问题,提出了一种基于Siamese-YOLOv4的印刷品缺陷目标检测方法。首先,使用了一种图像分割和随机参数变化的策略对数据集进行增强;然后,在主干网络中增加了孪生相似性检测网络,并在相似性检测网络中引入Mish激活函数来计算出图像块的相似度,在此之后将相似度低于阈值的区域作为缺陷候选区域;最后,训练候选区域图像,从而实现缺陷目标的精确定位与分类。实验结果表明：Siamese-YOLOv4模型的检测精度优于主流的目标检测模型,在印刷缺陷数据集上,Siamese-YOLOv4网络对卫星墨滴缺陷的检测准确率为98.6%,对脏点缺陷的检测准确率为97.8%,对漏印缺陷的检测准确率为93.9%;检测的平均精度均值（mAP）达到了96.8%,相较于YOLOv4算法、Faster R-CNN算法、SSD算法、EfficientDet算法分别提高了6.5个百分点、6.4个百分点、14.9个百分点、10.6个百分点。所提Siamese-YOLOv4模型一方面在印刷品缺陷检测中有较低的误检率和漏检率,另一方面通过相似性检测网络计算图像块的相似度从而提高了检测的精度,表明所提缺陷检测方法可应用于印刷质检以提高印刷企业的缺陷检测水平。     

基于质心法的车联网目标跟踪方法与应用

车辆目标跟踪是实现车联网不可或缺的一环,旨在获取车辆的动态信息,以提高交通运行效率.其核心是对大量监控探头采集的视频图像进行分析处理,实现车辆的实时检测与跟踪.为了进一步提高目标检测效率,降低硬件成本,文中提出了基于二帧差分法的前景检测方法,以及基于质心法的车辆轮廓检测与跟踪方法.基于OpenCV3.4.1和VS2017进行验证实验和仿真测试,结果表明,该算法对车辆跟踪的精确率达到89.1％,平均处理耗时42.63 ms,具有较好的实时性和鲁棒性,可在车联网嵌入式设备上进行部署和应用.     

引入源端信息的机器译文自动评价方法研究

机器译文自动评价是机器翻译中的一个重要任务。针对目前译文自动评价中完全忽略源语言句子信息,仅利用人工参考译文度量翻译质量的不足,该文提出了引入源语言句子信息的机器译文自动评价方法: 从机器译文与其源语言句子组成的二元组中提取描述翻译质量的质量向量,并将其与基于语境词向量的译文自动评价方法利用深度神经网络进行融合。在WMT-19译文自动评价任务数据集上的实验结果表明,该文所提出的方法能有效增强机器译文自动评价与人工评价的相关性。深入的实验分析进一步揭示了源语言句子信息在译文自动评价中发挥着重要作用。     

Adaptive Safety Motion Control for Underactuated Hovercraft Using Improved Integral Barrier Lyapunov Function

International Journal of Control, Automation and Systems - In this paper, we investigate the problem of safety motion control for an underactuated hovercraft from subject to safety constraint on...     

Improved Computational Model of Grid Cells Based on Column Structure

To simulate the firing pattern of biological grid cells, this paper presents an improved computational model of grid cells based on column structure. In this model, the displacement along different directions is processed by modulus operation, and the obtained remainder is associated with firing rate of grid cell. Compared with the original model, the improved parts include that: the base of modulus operation is changed, and the firing rate in firing field is encoded by Gaussian-like function. Simulation validates that the firing pattern generated by the improved computational model is more consistent with biological characteristic than original model. Besides, the firing pattern is badly influenced by the cumulative positioning error, but the computational model can also generate the regularly hexagonal firing pattern when the real-time positioning results are modified.