一种新的行人多目标跟踪算法

基于TBD(track by detection)框架,使用YOLO网络训练并优化得到了较好的行人检测器,提出一种匹配网络进行多目标的匹配,得到一个准确率较高的行人多目标跟踪框架。为解决行人多目标跟踪中误匹配、目标丢失等问题,提出对于跟踪轨迹模板更新的策略以及对于计算的优化。在MOT数据集上的实验证明,该算法在行人多目标跟踪中取得了较高的准确率,其他多项指标也都达到了较高的水平。     

基于注意力机制和卡尔曼滤波的多目标跟踪

为了解决目前多目标跟踪算法在行人遮挡后无法再次准确跟踪的问题,提出了一种融入注意力机制和改进卡尔曼滤波的多目标跟踪算法,选用联合检测和重识别框架提取特征,同时完成目标检测和重识别任务.设计了并行支路注意力机制,包括空间注意力和通道注意力两个部分,每个部分都采用并行支路的方式完成池化和卷积操作.在跟踪阶段,本文提出了速度先验卡尔曼滤波,实现对行人运动状态更精确的预测.采用CUHK-SYSU数据集对算法进行训练,并在MOT16数据集上做算法的验证和测试.本算法的多目标跟踪准确度(MOTA)达到了65.1％,多目标跟踪精确度(MOTP)达到了78.8％,识别F1值(IDF1)达到62.3％.实验表明,提出的跟踪算法可以有效地提高跟踪的整体性能,实现对目标的持续跟踪.     

融合人群密度的自适应深度多目标跟踪算法

多目标跟踪技术不能较好地解决目标严重遮挡场景下的多目标跟踪问题,因此文中提出融合人群密度的自适应深度多目标跟踪算法.首先,融合人群密度图和目标检测结果,利用人群密度图的位置和计数信息修正检测器结果,消除漏检、误检.然后,使用自适应三元组损失改进行人重识别模型的损失函数,提高对重识别特征的辨别能力.最后,使用外观和运动信息进行目标关联,得到最终的跟踪结果.实验验证文中算法可有效解决目标严重遮挡场景下的多目标跟踪问题.     

视频监控系统中行人的自动分割算法

视频监控系统在智能安防等众多领域有着广泛的应用空间,是近年来研究的热点之一。行人的分割在视频监控系统中极其重要,其分割的有效性直接影响目标识别、行为理解等。本文提出一种自动的行人分割算法,使用基于HOG特征的行人检测算法对目标进行定位,获得粗略的前景和背景信息,把获得的预分割信息作为GrabCut算法的先验知识,无需交互式操作,自动地对行人进行精确分割。实验证明该算法不仅有效,而且能满足应用需求。     

基于YOLOv5和FCN-DenseNet水下图像多目标语义分割算法

带视觉系统的水下机器人作业离不开对水下目标准确的分割, 但水下环境复杂, 场景感知精度和识别精度不高等问题会严重影响目标分割算法的性能. 针对此问题本文提出了一种综合YOLOv5和FCN-DenseNet的多目标分割算法. 本算法以FCN-DenseNet算法为主要分割框架, YOLOv5算法为目标检测框架. 采用YOLOv5算法检测出每个种类目标所在位置; 然后输入针对不同类别的FCN-DenseNet语义分割网络, 实现多分支单目标语义分割, 最后融合分割结果实现多目标语义分割. 此外, 本文在Kaggle竞赛平台上的海底图片数据集上将所提算法与PSPNet算法和FCN-DenseNet算法两种经典的语义分割算法进行了实验对比. 结果表明本文所提的多目标图像语义分割算法与PSPNet算法相比, 在MIoU和IoU指标上分别提高了14.9%和11.6%; 与FCN-DenseNet算法在MIoU和IoU指标上分别提高了8%和7.7%, 更适合于水下图像分割.     

基于自校准与异构网络的多目标跟踪算法

为解决多目标跟踪算法在遮挡场景下导致的身份切换等问题,提升算法跟踪精度,提出一种融合自校准与异构卷积的离线图跟踪网络(self-calibrated convolutions and asymmetric convolution track, SCAACTrack)。利用融合自校准卷积网络与非对称结构进行目标外观特征提取,提升算法行人重识别能力。通过采用不同帧之间目标外观特征、时间和空间3种维度进行图神经网络建模,引入基于时间感知的消息传递网络加强多目标跟踪流式守恒约束。实验结果表明,与传统的多目标跟踪算法MPNTrack、Tracktor、KCF等模型相比,该模型跟踪效果更有效。     

基于YOLOX和重识别的行人多目标跟踪方法

针对在拥堵场景下多目标跟踪身份频繁切换的问题，该文提出了一种融合行人重识别任务与目标检测任务的联合网络。在YOLOX检测算法上添加重识别（Re-identification）分支，获得含有重识别特征的行人检测框；在ByteTrack跟踪算法的检测框与预测框特征匹配的基础上，利用重识别特征弥补ByteTrack网络在匹配过程中行人外观特征缺失的问题，并结合行人运动特征，进一步提升特征匹配的准确率，减少身份切换次数。在公开数据集MOT17上进行实验，改进后的网络m AP提升2.6%，达到了95.4%，不同尺寸的mAP与mAR均获得明显提升，运行效率几乎保持不变。     

基于新型AFCM的多传感器目标跟踪航迹融合

多目标跟踪是多传感器系统信息融合中的核心技术之一.采用新型的AFCM模糊算法实现对多目标交叉状态下航迹数据关联.该算法定义了一种新的度量空间中的距离,通过新的距离定义有效抑制含有噪声点的样本及目标航迹交叉在迭代中对数据关联聚类中心点的大幅偏差.同时应用改进带加权的航迹融合算法对红外和毫米波雷达传感器测量的航迹数据进行融合.仿真试验证明,新的算法在综合多传感器探测优势的基础上,对航迹的融合结果优于SF算法.新的数据关联算法和改进的加权航迹融合算法为多源信息融合提供了一种可靠有效的多目标跟踪技术.     

基于单目视觉的移动机器人导航算法研究进展

基于单目视觉的移动机器人导航的研究,涵盖了机器视觉、模式识别和多目标跟踪多个领域．其算法框架不仅成功应用于移动机器人导航,还为目标检测、识别与跟踪领域的研究提供了可供参考的模型．该综述将以算法发展历史为脉络,结合一些典型系统,通过对关键技术和算法结构的分析比较,总结算法本身的发展前景和由此发展起来的可供相关研究参考的算法框架．     

融合SPA遮挡分割的多目标跟踪方法

复杂环境下的多目标视频跟踪是计算机视觉领域的一个难点,有效处理目标间遮挡是解决多目标跟踪问题的关键。将运动分割方法引入目标跟踪领域,提出一种融合骨架点指派(SPA)遮挡分割的多目标跟踪方法。由底层光流信息得到骨架点,并估计骨架点遮挡状态;综合使用目标外观、运动、颜色信息等高级语义信息,将骨架点指派给各个目标;最后以骨架点为核,对运动前景密集分类,得到准确的目标前景像素;在粒子滤波器跟踪框架下,使用概率外观模型进行多目标跟踪。在PETS2009数据集上的实验结果表明,文中方法能够改进现有多目标跟踪方法对目标间交互适应性较差的缺点,更好地处理动态遮挡问题。     

A label field fusion model with a variation of information estimator for image segmentation

This paper proposes a new and reliable segmentation approach based on a fusion framework for combining multiple region-based segmentation maps (with any number of regions) to provide a final improved (i.e., accurate and consistent) segmentation result. The core of this new combination model is based on a consensus (cost) function derived from the recent information Theory based variation of information criterion, proposed by Meila, and allowing to quantify the amount of information that is lost or gained in changing from one clustering to another. In this case, the resulting consensus energy-based segmentation fusion model can be efficiently optimized by exploiting an iterative steepest local energy descent strategy combined with a connectivity constraint. This new framework of segmentation combination, relying on the fusion of inaccurate, quickly and roughly calculated, spatial clustering results, emerges as an appealing alternative to the use of complex segmentation models existing nowadays. Experiments on the Berkeley Segmentation Dataset show that the proposed fusion framework compares favorably to previous techniques in terms of reliability scores.     

自适应人脸多区域分析的视频心率检测

心率是衡量人体心血管健康状况和情绪压力的重要生理参数. 然而, 基于视频的非接触式心率检测技术在真实场景中, 会由于人脸运动和光照变化等导致检测准确性的降低. 为了解决上述问题, 考虑到心率检测算法中感兴趣区域(region of interest, ROI)的选取与检测准确度高度相关. 故提出一种自适应超像素分割多区域综合分析的心率检测新方法. 首先利用人脸检测和追踪算法, 裁切获得人脸图像; 之后采用自适应超像素分割算法将ROI划分成互不重叠的子块; 再通过色度特征提取构建各子块原始血液容积脉搏矩阵; 最后对脉搏矩阵使用多指标综合分析并挑选出最佳区域进行心率估计. 实验结果表明, 通过自适应超像素分割和多区域分析优选可以有效提升心率检测准确性. 在静止状态下和运动干扰条件下准确性分别达到99.1%和95.6%, 光照干扰条件下准确性相对传统方法最高提升8.2%. 增强了真实场景下心率检测的鲁棒性.     

Range Image Segmentation through Pattern Analysis of the Multiscale Wavelet Transform

This work presents an image segmentation method for range data that uses multiscale wavelet analysis in combination with statistical pattern recognition. A feature-detection framework based on multiscale analysis and pattern recognition has several potential advantages over other feature detection systems. These advantages are detection of features at different scales (i.e., features of all sizes), robustness, and few or no free parameters. Our system creates a fuzzy edge map and derives a segmentation from this edge detection. A scale-space signature is the vector of measurements at different scales taken at a single point in an image. We analyze these 1-D signatures with traditional pattern-recognition methods. We train a pattern-recognition system with scale-space signatures from the edge points of a training image. Once trained, the system determines the degree ofedgenessof points in a new image. The goal is to create a system that exploits the advantages of a multiscale, pattern-recognition framework.     

基于高阶CRF模型的图像语义分割

图像语义分割方法大多基于点对条件随机场模型, 不能定位到单个目标, 并且难以利用全局形状特征, 造成误识。针对这些问题, 提出一种新的高阶条件随机场模型, 将基于全局形状特征的目标检测结果和点对条件随机场模型统一在一个概率模型框架中, 同时完成图像分割、目标检测与识别的任务。利用目标检测器和前背景分割算法获取图像中目标区域, 在目标区域上定义新的高阶能量项。新的高阶条件随机场模型就是高阶能量项和点对条件随机场模型的加权混合模型, 其最优解即为图像语义分割结果。在MSRC-21类数据库上进行的实验验证了该模型能够显著提升图像语义分割性能, 并定位到单个目标。     

融合边界信息和颜色特征的显著性区域检测

传统的显著性检测方法多利用图像的颜色特征并进行超像素分割作为预处理来进行检测,对于涂抹效应不足、误检测等问题一直没能有效解决。针对涂抹效应不足提出了一种结合图像边界信息及颜色特征的显著性区域检测方法。首先,为了更好地取得图像边缘信息并去除噪声,用多次WMF（加权中值滤波）和简单线性迭代聚类（SLIC）处理源图像,再通过颜色、亮度等信息找出滤波后图像中的自然边界。将得到的边界信息和通过SLIC分割得到的超像素的颜色特征进行融合作为先验概率,以SLIC分割得到超像素位于Graph-based分割得到初步显著图中的概率为条件概率,利用贝叶斯法则得到最终的显著图。在公开数据集MSRA-1000上对算法进行验证,结果表明该算法与7种主流算法相比有更好的查全率和查准率,最高查准率达到98.03%。     

基于图像检测的双绞线绕距测量方法

针对双绞线绕距测量,提出了一种图像检测框架。此框架通过图像分割、修复、细化、拟合以及比例尺的设置,可实时计算出双绞线绕距值。在此框架下,针对传统二维最大类间方差法--Otsu运行时间较长的问题,提出了一种新的基于区域斜分的快速算法。快速算法通过对二维直方图区域重新划分,结合快速查找表以及递推算法,大大减少了分割时间。针对图像缺失的问题,采用了基于边缘检测的算法对其特定区域进行填充修复,并对修复后的图像进行细化。通过最小二乘法,拟合细化图像中的单像素点,得到拟合曲线。通过计算拟合曲线交点间的距离可得双绞线绕距的图像距离。最后将图像距离按比例尺转换为绕距的测量值。实验结果表明,基于区域斜分的快速算法其分割时间约为传统算法的0.22%,且两种算法的分割效果基本一致。将图像检测方法测得的绕距值与其真实值进行比较,结果表明测量值与真实值的绝对误差为0.48%。通过使用图像检测方法测量双绞线绕距,可以准确测得绕距值,提高绕距测量的效率。     

TRASMIL: A local anomaly detection framework based on trajectory segmentation and multi-instance learning

Local anomaly detection refers to detecting small anomalies or outliers that exist in some subsegments of events or behaviors. Such local anomalies are easily overlooked by most of the existing approaches since they are designed for detecting global or large anomalies. In this paper, an accurate and flexible three-phase framework TRASMIL is proposed for local anomaly detection based on TRAjectory Segmentation and Multi-Instance Learning. Firstly, every motion trajectory is segmented into independent sub-trajectories, and a metric with Diversity and Granularity is proposed to measure the quality of segmentation. Secondly, the segmented sub-trajectories are modeled by a sequence learning model. Finally, multi-instance learning is applied to detect abnormal trajectories and sub-trajectories which are viewed as bags and instances, respectively. We validate the TRASMIL framework in terms of 16 different algorithms built on the three-phase framework. Substantial experiments show that algorithms based on the TRASMIL framework outperform existing methods in effectively detecting the trajectories with local anomalies in terms of the whole trajectory. In particular, the MDL-C algorithm (the combination of HDP-HMM with MDL segmentation and Citation kNN) achieves the highest accuracy and recall rates. We further show that TRASMIL is generic enough to adopt other algorithms for identifying local anomalies.     

Integrating multiple cues into adaptive hierarchical segmentation for high-resolution remote-sensing images

Image segmentation has been, and still is, a hot research topic in computer vision and pattern recognition. However, few existing segmentation algorithms are suitable for all objects presented in high-resolution remote-sensing (HRRS) images, because the relevant methods often implement segmentation in the same mode for the whole image rather than considering the different characteristics of various objects. Therefore, this article proposes an adaptive hierarchical segmentation framework for HRRS images by integrating multiple cues (e.g. intensity, texture and boundary). This two-stage framework first analyses the class of region presented in the study image, then according to this analysis, partitions each region class by adaptively utilizing the proper segmentation method with the most representative features. The distinctive characteristics of this framework are that the first stage simplifies the problem before using the segmentation method, and the second stage guarantees that the segmentation is carried out with the representative cues and corresponding suitable method for these cues. The performance of the proposed segmentation framework is demonstrated through a complete set of experimental results and substantiated using quantitative criteria.     

Text line and word segmentation of handwritten documents

In this paper, we present a segmentation methodology of handwritten documents in their distinct entities, namely, text lines and words. Text line segmentation is achieved by applying Hough transform on a subset of the document image connected components. A post-processing step includes the correction of possible false alarms, the detection of text lines that Hough transform failed to create and finally the efficient separation of vertically connected characters using a novel method based on skeletonization. Word segmentation is addressed as a two class problem. The distances between adjacent overlapped components in a text line are calculated using the combination of two distance metrics and each of them is categorized either as an inter- or an intra-word distance in a Gaussian mixture modeling framework. The performance of the proposed methodology is based on a consistent and concrete evaluation methodology that uses suitable performance measures in order to compare the text line segmentation and word segmentation results against the corresponding ground truth annotation. The efficiency of the proposed methodology is demonstrated by experimentation conducted on two different datasets: (a) on the test set of the ICDAR2007 handwriting segmentation competition and (b) on a set of historical handwritten documents.