基于transformer自适应特征向量融合的图像分类

针对目前基于transformer的图像分类模型直接应用在小数据集上性能较差的问题,本文提出了transformer自适应特征向量融合网络,该网络在特征提取器中将不同阶段的特征进行融合,减少特征信息丢失的同时获得更多不同感受野下的信息,同时利用最大池化来去除特征中的冗余信息,从而使提取的特征更具有判别性。此外,为了充分利用图像的各级特征信息来进行分类预测,本文将网络各阶段产生的特征向量进行融合,使融合后的特征向量更具有表征能力,从而减少网络对大数据集的依赖,使网络在小数据集中也能获得很好的性能。实验表明,本文提出的 算法在数据集Mini-ImageNet-100、CIFAR-100和ImageNet-1k上的TOP-1准确率分别达到了74.22%、85.86%和81.4%。在没有增加计算量的情况下,在baseline上分别提高了6.0%、3.0%和0.1%,且参数量减少了18.3%。本文代码开源在“https://github.com/xhutongxue/afvf”。     

基于背景感知的相关滤波抗遮挡优化算法

针对相关滤波目标跟踪中由于目标遮挡、出视野引起的跟踪失败等问题,以背景感知相关滤波(background aware correlation filters, BACF)算法为基础,提出一种抗遮挡优化算法。首先特征提取部分融合方向梯度直方图(histogram of oriented gradient, HOG)特征与颜色名称(color name, CN)特征;其次提出层级遮挡优化算法,在目标跟踪过程中根据平均峰值相关能量(average peak to correlation energy,APCE)和最大响应峰值判断目标外观是否发生较大变化,并通过巴氏距离进一步计算目标相邻滤波器模板特征相似程度,以此判断造成目标外观变化的真正原因,进而决定是否更新模板;针对目标出视野问题,提出模板筛查策略,跟踪过程中每隔K帧对滤波器模板进行置信度考查,若目标丢失,则生成新的模板并对目标进行全局搜索重新抓取目标。通过在目标跟踪数据集OTB2015上测试,优化算法精确度与成功率分别为83.0%与78.8%,有效提高了算法性能。     

基于FMCW雷达的呼吸模式分类技术研究

针对当前使用调频连续波雷达的呼吸模式分类算法准确度不高的问题,本文提出一种基于一维卷积神经网络（1DCNN）结合长短时记忆（LSTM）网络的多呼吸模式分类方法。方法共分为四步：第一步,对雷达提取的呼吸信号进行预处理;第二步,使用快速傅里叶变换（FFT）与连续小波变换（CWT）提取呼吸信号特征;第三步,根据呼吸特征对五种呼吸模式信号（正常呼吸、呼吸过速、呼吸过缓、呼吸深大、呼吸暂停）打标签制作数据集;第四步,使用数据集训练网络得到模型,并使用新数据测试模型。实验结果表明,此方法分类准确度要比现有使用CNN网络方法高5%左右。     

IPC-Net: Incomplete point cloud classification network based on data augmentation and similarity measurement

Existing point cloud classification researches are usually conducted on datasets with complete structure and clear semantics. However, in real point cloud scenes, the occlusion and truncation may destroy the completeness of objects affecting the classification performance. To solve this problem, we propose an incomplete point cloud classification network (IPC-Net) with data augmentation and similarity measurement. The proposed network learns the feature representation of incomplete point clouds and the semantic differences compared to the complete ones for classification. Specifically, IPC-Net adopts a random erasing-based data augmentation to deal with incomplete point clouds. IPC-Net also introduces an auxiliary loss function weighted by attention scores to measure the similarity between the incomplete and the complete point clouds. Extensive experiments verify that IPC-Net has the ability to classify incomplete point clouds and significantly improves the robustness of point cloud classification under different completeness.     

Real-time 3D multi-pedestrian detection and tracking using 3D LiDAR point cloud for mobile robot

Mobile robots are used in modern life; however, object recognition is still insufficient to realize robot navigation in crowded environments. Mobile robots must rapidly and accurately recognize the movements and shapes of pedestrians to navigate safely in pedestrian-rich spaces. This study proposes real-time, accurate, three-dimensional (3D) multi-pedestrian detection and tracking using a 3D light detection and ranging (LiDAR) point cloud in crowded environments. The pedestrian detection quickly segments a sparse 3D point cloud into individual pedestrians using a lightweight convolutional autoencoder and connected-component algorithm. The multi-pedestrian tracking identifies the same pedestrians considering motion and appearance cues in continuing frames. In addition, it estimates pedestrians' dynamic movements with various patterns by adaptively mixing heterogeneous motion models. We evaluate the computational speed and accuracy of each module using the KITTI dataset. We demonstrate that our integrated system, which rapidly and accurately recognizes pedestrian movement and appearance using a sparse 3D LiDAR, is applicable for robot navigation in crowded spaces.     

Joint frame rate adaptation and object recognition model selection for stabilized unmanned aerial vehicle surveillance

We propose an adaptive unmanned aerial vehicle (UAV)-assisted object recognition algorithm for urban surveillance scenarios. For UAV-assisted surveillance, UAVs are equipped with learning-based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self-adaptive control strategy to maximize the time-averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real-world data demonstrate that the proposed algorithm achieves the desired performance improvements.     

SRI-Net: Similarity retrieval-based inference network for light field salient object detection

The cutting-edge RGB saliency models are prone to fail for some complex scenes, while RGB-D saliency models are often affected by inaccurate depth maps. Fortunately, light field images can provide a sufficient spatial layout depiction of 3D scenes. Therefore, this paper focuses on salient object detection of light field images, where a Similarity Retrieval-based Inference Network (SRI-Net) is proposed. Due to various focus points, not all focal slices extracted from light field images are beneficial for salient object detection, thus, the key point of our model lies in that we attempt to select the most valuable focal slice, which can contribute more complementary information for the RGB image. Specifically, firstly, we design a focal slice retrieval module (FSRM) to choose an appropriate focal slice by measuring the foreground similarity between the focal slice and RGB image. Secondly, in order to combine the original RGB image and the selected focal slice, we design a U-shaped saliency inference module (SIM), where the two-stream encoder is used to extract multi-level features, and the decoder is employed to aggregate multi-level deep features. Extensive experiments are conducted on two widely used light field datasets, and the results firmly demonstrate the superiority and effectiveness of the proposed SRI-Net.     

一种实时多尺度目标检测识别算法

无人机目标检测与识别任务中,目标随着飞行高度的改变尺寸发生显著变化。常规目标检测模型中,获取的小目标细节信息有限,检测精度较低;而适用于小目标的实时检测模型往往容易丢失大目标的背景信息,降低大目标的检测精度。针对以上多尺度目标检测识别任务难点,提出一种基于改进特征金字塔网络(Feature Pyramid Network, FPN)结构的实时多尺度目标检测识别模型。该模型通过增加特征金字塔层级覆盖更广的目标尺度,获取更为丰富的目标信息;同时,利用跨连接增加不同尺度特征融合的多样性,降低特征传导距离,保留更加完整的尺度特征来提高模型检测识别多尺度目标的性能。通过实验发现,相比于原始网络结构和相同特征层级的四层特征金字塔结构,加入改进特征金字塔结构的多尺度目标检测模型识别性能得到了提升。     

数据安全治理现状研究与分析

近年来,国内外数据泄露事件频发,大量企业的商业利益、声誉受损。数据安全法律法规相继颁布,监管力度不断升级,企业逐渐意识到数据安全治理的重要性与紧迫性。通过对2021年开展的企业数据安全治理能力评估现状进行整理,总结企业数据安全治理工作在组织建设、人才培养、技术工具等方面的现状与趋势,提供能力提升思路,以供业界参考。     

基于Focal-EIOU函数的被动式太赫兹图像违禁物品识别

针对被动式太赫兹安检系统因环境影响导致图像质量波动,从而影响识别算法,导致准确率大幅降低的问题,提出了基于Focal-EIOU损失函数的改进YOLOv4算法,并用被动式太赫兹人体安检图像对刀、枪违禁物品进行模型训练获得模型。建立不同环境、不同位置角度携带刀枪嫌疑物人员的太赫兹图像数据库,采用图像增广的方法构建丰富数据集;将YOLOv4的CIOU loss改进为Focal-EIOU loss,提高算法对太赫兹图像识别的鲁棒性,进而经过训练获得较优的模型。在本文的测试集中,使用改进后的算法训练的模型平均检测精确度(mAP)达到96.4%,检测速度在28 ms左右,交并比(IOU)平均值为0.95,在同等条件下高于常规算法,改善了检测识别的效果。实验结果表明,本文方法能够有效提高被动式太赫兹人体安检系统的嫌疑物识别准确率,有利于该项技术在人体安检领域的推广应用。