滞留与偷窃物体实时检测与分类算法

研究了在静止的单摄像机条件下滞留与偷窃物体检测与分类算法。基于轮廓的判别方法在环境轮廓复杂情况下检测率会降低。在吸收了原有轮廓空间相似性算法的基础上，加入了轮廓的连通性判断，只有轮廓同时满足空间和连通性都相似的物体才被判定为滞留物体。此外还研究了基于颜色直方图的巴氏距离的判定方法，将以上两种方法进行了比较。实验结果表明，在现实环境下，改进后的轮廓判别方法比颜色方法适应性更强，检测正确率更高。     

A real-time object detecting and tracking system for outdoor night surveillance

Autonomous video surveillance and monitoring has a rich history. Many deployed systems are able to reliably track human motion in indoor and controlled outdoor environments. However, object detection and tracking at night remain very important problems for visual surveillance. The objects are often distant, small and their signatures have low contrast against the background. Traditional methods based on the analysis of the difference between successive frames and a background frame will do not work. In this paper, a novel real time object detection algorithm is proposed for night-time visual surveillance. The algorithm is based on contrast analysis. In the first stage, the contrast in local change over time is used to detect potential moving objects. Then motion prediction and spatial nearest neighbor data association are used to suppress false alarms. Experiments on real scenes show that the algorithm is effective for night-time object detection and tracking.     

基于实例分割模型优化的道路抛洒物检测算法

在交通安全领域,道路抛洒物易引发交通事故,构成了交通安全隐患。针对传统抛洒物检测方式识别率低、对于多类抛洒物检测效果不佳等问题,提出了一种基于实例分割模型CenterMask优化的道路抛洒物检测算法。首先,使用空洞卷积优化的残差网络ResNet50作为主干神经网络来提取特征并进行多尺度处理;然后,通过距离交并比（DIoU）函数优化的全卷积单阶段（FCOS）目标检测器实现对抛洒物的检测和分类;最后,使用空间注意力引导掩膜作为掩膜分割分支来实现对于目标形态的分割,并采用迁移学习的方式实现模型的训练。实验结果表明,所提算法对于抛洒物目标的检测率为94.82%,相较常见实例分割算法Mask R-CNN,所提的道路抛洒物检测算法在边界框检测上的平均精度（AP）提高了8.10个百分点。     

Multi-spectral fusion for surveillance systems

Surveillance systems such as object tracking and abandoned object detection systems typically rely on a single modality of colour video for their input. These systems work well in controlled conditions but often fail when low lighting, shadowing, smoke, dust or unstable backgrounds are present, or when the objects of interest are a similar colour to the background. Thermal images are not affected by lighting changes or shadowing, and are not overtly affected by smoke, dust or unstable backgrounds. However, thermal images lack colour information which makes distinguishing between different people or objects of interest within the same scene difficult.By using modalities from both the visible and thermal infrared spectra, we are able to obtain more information from a scene and overcome the problems associated with using either modality individually. We evaluate four approaches for fusing visual and thermal images for use in a person tracking system (two early fusion methods, one mid fusion and one late fusion method), in order to determine the most appropriate method for fusing multiple modalities. We also evaluate two of these approaches for use in abandoned object detection, and propose an abandoned object detection routine that utilises multiple modalities. To aid in the tracking and fusion of the modalities we propose a modified condensation filter that can dynamically change the particle count and features used according to the needs of the system.We compare tracking and abandoned object detection performance for the proposed fusion schemes and the visual and thermal domains on their own. Testing is conducted using the OTCBVS database to evaluate object tracking, and data captured in-house to evaluate the abandoned object detection. Our results show that significant improvement can be achieved, and that a middle fusion scheme is most effective.     

基于帧间差分和边缘差分的遗留物检测算法

遗留物检测是智能视频监控系统的核心功能,遗留物一般较小,所处环境复杂,传统的运动目标检测算法直接用于遗留物检测效果一般.提出了一种基于帧间差分与边缘差分的遗留物检测算法,首先进行帧间差分得到运动目标区域,然后将当前帧图像和前一帧的背景图像进行边缘差分运算得到运动目标的边缘,融合二次差分的结果即可得到运动目标的完整轮廓特征,最终通过判断运动目标在场景中的滞留时间是否达到或超过报警系统设置的阈值来标示遗留物,供智能视频监控系统处理.实验结果证明该算法实时性好且识别率较高.     

多信息动态融合的运动目标检测方法

针对基于视觉显著性的运动目标检测算法存在时空信息简单融合及忽略运动信息的问题,提出一种动态融合视觉显著性信息和运动信息的运动目标检测方法。该方法首先计算每个像素的局部显著度和全局显著度,并通过贝叶斯准则生成空间显著图;然后,利用结构随机森林算法预测运动边界,生成运动边界图;其次,根据空间显著图和运动边界图属性的变化,动态确定最佳融合权值;最后,根据动态融合权值计算并标记运动目标。该方法既发挥了显著性算法和运动边界算法的优势,又克服了各自的不足,与传统背景差分法和三帧差分法相比,检出率和误检率的最大优化幅度超过40%。实验结果表明,该方法能够准确、完整地检测出运动目标,提升了对场景的适应性。     

Moving object detection algorithm based on pixel spatial sample difference consensus

Moving object detection is an essential component for security video surveillance system and other computer vision applications. Although the latest object detection methods get promising detection expectations, however, accurate detection is still a tricky problem due to various challenges such as aperture effects, illumination variations, camouflage issues and retention problems in unconstrained video environments. In this paper, we propose a brand-new theoretical framework for foreground object detection based on the stable spatial relationship between current pixel and the randomly selected pixels in current frame. Different from the existing methods which determine the moving object area by comparing each pixel value with its surrounding pixels or by comparing two pixel values occupying the same positions in adjacent frames, the proposed algorithm sets up a spatial sample set for each individual pixel and defines Spatial Sample Difference Consensus (SSDC), which denotes changes of stable spatial relationship rather than direct changes in pixel values. Thus, the proposed algorithm computes the SSDC between two adjacent frames to subtract the moving objects. The experiments on recent data-set in both indoor and outdoor surveillance video sequences show that the proposed method achieved promising performance after compared with several state-of-the art methods.     

空间约束混合高斯运动目标检测

目的 针对传统混合高斯模型前景检测运算量过大问题,提出一种基于空间约束的混合高斯前景检测算法。方法 通过快速初始化缩短模型的初始建立过程;采用双重背景模型机制,以自适应背景减法的前景检测结果作为混合高斯前景检测的空间约束条件,降低模型在背景区域的冗余运算;运用多策略自适应模型更新,提高前景检测的准确性。结果 在各种测试场景下,与传统混合高斯法、CodeBook、GMG、偏差均值混合高斯模型(MODGMM)等算法相比,该算法具有更好的准确率以及4倍以上的处理速度。结论 在固定相机场景下的运动目标检测中,算法能有效提高传统混合高斯法的准确性且具有极高的实时性。     

动态背景下空时特性均显著的运动目标检测

从序列图像中提取变化区域是运动检测的主要作用,动态背景的干扰严重影响检测结果,使得有效性运动检测成为一项困难工作。受静态图像显著性检测启发,提出了一种新的运动目标检测方法,采用自底向上与自顶向下的视觉计算模型相结合的方式获取图像的空时显著性：先检测出视频序列中的空间显著性,在其基础上加入时间维度,利用改进的三帧差分算法获取具有运动目标的时间显著性,将显著性目标的检测视角由静态图像转换为空时性均显著的运动目标。实验和分析结果表明：新方法在摄像机晃动等动态背景中能较准确检测出空时均显著的运动目标,具有较高的鲁棒性。     

Collision Detection between Robot Arms and People

As the result of an increasing number of robots performing tasks in a range of human life activites, human–robot interaction has become a very active research field. Safety of people around robots is a major concern. This paper presents some research in this context: our aim is to avoid mechanical injure of people interacting with robots. We approach the collision detection problem in a scene with people and several moving robot arms. Fast collision detection for practical motion planning depends on an adequate spatial representation for the objects involved in the scene. The authors have previosly proposed a system that automatically generates a hierarchy of approximations for general objects. The spatial model has interesting properties and has been used in efficient collision detection algorithms between moving robots [8]. In spatial representations, there is a trade-off between generality and efficiency. Some existing approaches claim to be general but they are less efficient. In this paper, we present two extensions to the spatial model. First, the system can deal with a general class of objects, those that are composed of nonhomogeneous generalized cylinders. Secondly, a simple method for automatic converting from a polyhedral representation to such a generalized cylinder is presented. Therefore, we enhance the generality of the system but without compromising the efficiency. With these extensions virtually any object can be dealt with, and particularly those composing the human body.     

Robust and efficient foreground analysis in complex surveillance videos

Mixture of Gaussians-based background subtraction (BGS) has been widely used for detecting moving objects in surveillance videos. It is very efficient and can update the background model with slow lighting changes, however, it suffers from a number of limitations in complex surveillance conditions such as quick lighting variations, heavy occlusion, foreground fragments, slow moving or stopped object etc. To address these issues, this paper first focuses on foreground analysis within the mixture of Gaussians BGS framework in long-term scene monitoring to handle (1) quick lighting changes, (2) static objects, (3) foreground fragments, (4) abandoned and removed objects, and (5) camera view changes. Then, we propose a framework with interactive mechanisms between BGS and processing from different high levels (i.e. region, frame, and tracking) to improve the accuracy of moving object detection and tracking to handle (1) objects that stop for a significant period of time and (2) slow-moving objects. The robustness and efficiency of the proposed mechanism are tested in IBM Smart Surveillance Solution on a variety of sequences, including standard datasets. The proposed method is very efficient and handles ten video streams in real-time on a 2GB Pentium IV machine with MMX optimization.     

基于大数据分析的移动对象轨迹预测方法

对移动对象的轨迹预测将在移动目标跟踪识别中具有较好的应用价值。移动对象轨迹预测的基础是移动目标运动参量的采集和估计,移动目标的运动参量信息特征规模较大,传统的单分量时间序列分析方法难以实现准确的参量估计和轨迹预测。提出一种基于大数据多传感信息融合跟踪的移动对象轨迹预测算法。首先进行移动目标对象进行轨迹跟踪的控制对象描述和约束参量分析,对轨迹预测的大规模运动参量信息进行信息融合和自正整定性控制,通过大数据分析方法实现对移动对象运动参量的准确估计和检测,由此指导移动对象轨迹的准确预测,提高预测精度。仿真结果表明,采用该算法进行移动对象的运动参量估计和轨迹预测的精度较高,自适应性能较强,稳健性较好,相关的指标性能优于传统方法。     

Accuracy versus speed in context-based object detection

The visual detection and recognition of objects is facilitated by context. This paper studies two types of learning methods for realizing context-based object detection in paintings. The first method is called the gradient method; it learns to transform the spatial context into a gradient towards the object. The second method, the context-detection method, learns to detect image regions that are likely to contain objects. The accuracy and speed of both methods are evaluated on a face-detection task involving natural and painted faces in a wide variety of contexts. The experimental results show that the gradient method enhances accuracy at the cost of computational speed, whereas the context-detection method optimises speed at the cost of accuracy. The different results of both methods are argued to arise from the different ways in which the methods trade-off accuracy and speed. We conclude that both the gradient method and the context-detection method can be applied to reliable and fast object detection in paintings and that the choice for either method depends on the application and user constraints.     

融合时域信息的修正分水岭视频分割新方法

提出一种将时域信息融入分水岭的视频分割新方法,以帧间变化检测为基础,通过运动边缘信息得到对象的初始模型,利用时域信息得到前景和背景的标识,结合提出的彩色多尺度形态学梯度算子进行分水岭分割,得到具有精确边界的视频对象,对慢变和快变的目标均有良好的效果,能够检测新出现的运动对象和现有对象的消失,能够定位和跟踪运动目标.继承了变化检测和分水岭算法速度快的优点,克服了两者易受噪声影响的缺点.     

复杂环境下的遗留物检测算法

针对在复杂环境下检测遗留物体的问题,提出一种有效的算法。首先,采用局部更新的混合高斯模型与改进的三帧差分法分别得到前景,通过比较得到目标候选区域,并进一步采用阴影消除与连通域分析分割得到暂时静止物团块。其次对达到静止时间阈值的团块采用方向梯度直方图(HOG)行人检测,在排除驻留行人的可能后将其标记为遗留物。最后对检测出的遗留物进行加速分割检测特征(FAST)局部特征匹配,以克服行人遮挡、光线变化对结果的影响。实验结果表明,本算法具有较高的准确性和处理速度,能较好地克服复杂环境中存在的干扰影响。     

Fusion of thermal infrared and visible spectra for robust moving object detection

The detection of moving objects is a crucial step for many video surveillance applications whether using a visible camera (VIS) or an infrared (IR) one. In order to profit from both types, several fusion methods were proposed in the literature: low-level fusion, medium-level fusion and high-level fusion. The first one is the most used for moving objects’ detection in IR and VIS spectra. In this paper, we present an overview of the different moving object detection methods in IR and VIS spectra and a state of the art of the low-level fusion techniques. Moreover, we propose a new method for moving object detection using low-level fusion of IR and VIS spectra. In order to evaluate quantitatively and qualitatively our proposed method, three series of experiments were carried out using two well-known datasets namely “OSU Color-Thermal Database” and “INO-Database”; the results of these evaluations show promising results and demonstrate the effectiveness of the proposed method.     

基于码本和运行期均值法的双层背景建模方法

背景建模是视频处理的重要部分,是后续运动目标检测、识别和跟踪的基础。针对现有的背景建模方法无法兼顾抗干扰性、适应光照、背景更新速度和遮挡等问题,提出结合码本和运行期均值法对视频进行双层背景建模的方法。首先在第一层提取亮度和颜色特征,使用聚类的方法进行码本建模,接着在第二层建立运行期均值法模型,通过两种背景模型的有效结合快速准确地实现运动目标分割。实验结果表明,该背景建模方法计算简单、背景更新快、抗噪声能力强并且能较好地适应光照变化,适应于复杂环境下的目标检测。     

Target detection algorithm and data model optimization based on improved Gaussian mixture model

A set of multi-stage image processing algorithms developed to detect the change of image sequence analysis. This means Moving Target Identification (MTI). The difference compared with the traditional method, the new method of spatial diversity. General purpose of object detection, image processing and image understanding of the specific field of research. Hue Saturation and Value (HSV,) colour space algorithm uses spot and shape detection to ensure detection under various conditions of lighting, shade, and distance. The algorithm is tested on the lighting and form detection account where the different variation of the displays. The only computational process of the challenge group is the presence of more than one target of the same colour in finding the correct target under changing lighting conditions. It has been found that the elasticity target people based on localization of these image processing methods for better detection is compared with the target detection. Digital image data contains most of this image data recognition model is optimized by integrating task planning normalization and inertial representation of the remote sensing image classification model based on spatial communication. The immediate message issue is that the Gaussian compound model cannot detect the entire moving object, and is prone to sudden light changes, etc. The advanced algorithm to be performed is proposed based on the Gaussian compound model and the detection method of the three legal difference moving object. Subsequently, a new adaptive selection technique for Gaussian distributions is introduced to reduce processing time and improve detection accuracy.