Environmental Perception with Spatial Regularization Correlation Filter for Visual Tracking

With the introduction of correlation filtering (CF), the performance of visual object tracking is significantly improved. Circular shifts collecting samples is a key component of the CF tracker, and it also causes negative boundary effects. Most trackers add spatial regularization to alleviate boundary effects well. However, these trackers ignore the effect of environmental changes on tracking performance, and the filter discriminates poorly in the background interference. Here, to break these limitations, we propose a new correlation filter model, namely Environmental Perception with Spatial Regularization Correlation Filter for Visual Tracking. Specifically, we use the Average Peak to Correlation Energy (APCE) and the response value error between the two frames together to perceive environmental changes, which adjusts the learning rate to make the template more adaptable to environmental changes. To enhance the discriminatory capability of the filter, we use real background information as negative samples to train the filter model. In addition, the introduction of the regular term destroys the closed solution of CF, and this problem can be effectively solved by the use of the alternating direction method of multipliers (ADMM). Extensive experimental evaluations on three large tracking benchmarks are performed, which demonstrate the good performance of the proposed method over some of the state-of-the-art trackers.     

Proactive replication for rare objects in unstructured peer-to-peer networks

Unstructured peer-to-peer (P2P) networks have become a very popular architecture for content distribution in large-scale and dynamic environments. The search efficiency problem in unstructured P2P networks has not been adequately addressed so far, especially concerning search for rare objects. In this paper, we propose a proactive replication strategy to improve search efficiency for rare objects. It uses an object-probing technique for peers to decide whether or not to establish replications for their objects when they join the network. This strategy can effectively increase the popularity of rare objects in order to enhance search efficiency. We also present a rare object search algorithm to reduce the overhead caused by the replication strategy. When a peer forwards a search request, the forward probability is calculated according to its neighbors' degrees and the number of neighbors' objects. Therefore, the search request is forwarded to the peers more likely containing target objects. Simulations show that our proactive replication strategy greatly improves search efficiency for rare objects with moderate communication overhead. The rare object search algorithm not only improves search efficiency for rare objects, but also achieves load balance in search.     

建立加气砼直观数理模型的探索

若视加气砼为细观的“两相”材料,则可建立起其细观几何结构的随机直观数理模型,本文应用随机几何的方法探索了加气砼最佳合理内部细观几何结构模型的建立,及其计算机随机模拟,由细观角度讨论了改善加气砼性能的可能性。     

均衡化特征匹配的非刚体细胞形态跟踪

提出利用均衡化特征匹配来进行非刚性细胞形体跟踪的方法。采用重启动的随机游走方法建立并求解特征匹配概率模型,利用双向均衡方法对匹配邻接矩阵进行均衡化处理,得到指定目标与待跟踪目标之间的精确匹配,以获得目标的定位跟踪结果。同时利用特征匹配结果进行目标的自动标定,并应用图像分割方法进行目标的精确轮廓跟踪。实验结果表明,将该方法应用于视频中动态背景下的运动细胞形态跟踪时,在背景相似度较高及目标迅速移动的条件下,表现出了良好的性能,与同类方法相比可获得较高的定位精度以及更为准确的目标轮廓。     

红外弱小目标的匹配方法研究与仿真

研究红外图像中的目标匹配问题。针对传统的红外图像中目标匹配效果不理想,匹配不准确。当红外图像中是弱小目标时,背景灰度值与目标灰度值非常相近,灰度直方图均衡化无法实现目标与背景的完整分离,导致漏匹配率较高的问题。为提高目标的匹配精度,提出一种形态学预处理的红外目标匹配方法,通过形态学算法提取出图像中的形状信息,利用形状信息将红外图像中的目标与背景完整分离,避免了只依靠灰度图像信息造成的不能完整分离目标与背景带来的漏匹配问题。进行仿真的结果证明,采用的形态学与处理的匹配方法能够完整将目标与背景分离,成功完成目标匹配,取得了满意的结果。     

基于改进YOLOv3的运动目标分类检测算法研究

提出一种基于改进YOLOv3算法的一类运动目标检测算法. 为进一步提高YOLOv3的检测精度,采用基于DIoU优化的边界框回归损失函数进行计算; 优化非极大值抑制,有效减少了目标框重叠的现象,提高检测精度; 针对运动目标检测,提出一种基于目标框多中心点位移的检测算法. 经UA-DETRAC数据集上的实验表明,改进后的算法在提高检测精度的同时保证了较快的速度,准确率和召回率相比原始YOLOv3分别提高了 8.07%和3.87%,对运动目标的检测速度可达20 fps/s,可满足实时检测的要求.     

一种新的知觉分割模型*

根据知觉的最新理论研究和实验结果,提出一种新的知觉模型,并用于考查计算机视觉中的分割问题.分割问题实质上是知觉表达问题,现在分割的困难性可能是知觉上局部到整体的还原论假设造成的;分割可能不是一次完成的,而是经过整体到局部的过程才最终完成.新的知觉模型将对建立更好的分割模型提供理论基础.     

FMS实时控制系统动态建模方法(一)

在建立FMS物理对象的功能模型，状态转移图（STD），面向对象的Petri网（OPN）模型的基础上，本文将着色Petri网与面向对象技术相结合，提出了一种实时控制系统的建模方法－面向对象的着色Petri网（OCPN）建模方法，此建模方法在无锡职业学院的FMS的实时控制系统中得到验证。     

Online learning and fusion of orientation appearance models for robust rigid object tracking

We introduce a robust framework for learning and fusing of orientation appearance models based on both texture and depth information for rigid object tracking. Our framework fuses data obtained from a standard visual camera and dense depth maps obtained by low-cost consumer depth cameras such as the Kinect. To combine these two completely different modalities, we propose to use features that do not depend on the data representation: angles. More specifically, our framework combines image gradient orientations as extracted from intensity images with the directions of surface normals computed from dense depth fields. We propose to capture the correlations between the obtained orientation appearance models using a fusion approach motivated by the original Active Appearance Models (AAMs). To incorporate these features in a learning framework, we use a robust kernel based on the Euler representation of angles which does not require off-line training, and can be efficiently implemented online. The robustness of learning from orientation appearance models is presented both theoretically and experimentally in this work. This kernel enables us to cope with gross measurement errors, missing data as well as other typical problems such as illumination changes and occlusions. By combining the proposed models with a particle filter, the proposed framework was used for performing 2D plus 3D rigid object tracking, achieving robust performance in very difficult tracking scenarios including extreme pose variations.     

结合方向纹理熵的Haar-like特征在线boosting跟踪算法

针对传统基于Haar-like特征的on-line boosting跟踪算法（HBT）需要产生大规模随机特征、占用大量计算资源和存储空间的缺点,提出结合方向纹理熵的Haar-like特征在线boosting跟踪算法（HBTT）。HBTT算法利用灰度共生矩阵的熵获得目标纹理的方向信息,在此基础上有针对性地产生具有方向纹理信息的Haar-like特征,从而可有效避免无效随机特征的产生,减小特征池容量;更进一步,可根据目标纹理的复杂程度自动调整特征数量,使得算法更灵活。在跟踪过程中,在线学习模块可以使错误率较高的特征被结合了目标纹理方向信息的Haar-like特征所替换。与HBT算法比较,HBTT算法的跟踪误差降低了10%以上;在相同特征池容量下,置信度提高了2%以上。实验结果表明,该算法不仅具有较高的鲁棒性,而且在跟踪效率和性能上都有所提高。