实时运动目标检测与跟踪平台的构建*

构建了一个基于图像采集卡的复杂环境下实时运动目标检测与跟踪的实验平台。基于此平台提出并实现了一种改进的运动目标检测算法,它融合了帧间差分法和背景差分法的优点,以适应复杂环境的变化。实验表明,该算法利用所构建的平台,对变化场景中的运动目标实施了快速有效的检测与跟踪,为智能视频技术的研究提供了一个实用的实验平台。     

Robust object tracking under appearance change conditions

We propose a robust visual tracking framework based on particle filter to deal with the object appearance changes due to varying illumination, pose variantions, and occlusions. We mainly improve the observation model and re-sampling process in a particle filter. We use on-line updating appearance model, affine transformation, and M-estimation to construct an adaptive observation model. On-line updating appearance model can adapt to the changes of illumination partially. Affine transformation-based similarity measurement is introduced to tackle pose variantions, and M-estimation is used to handle the occluded object in computing observation likelihood. To take advantage of the most recent observation and produce a suboptimal Gaussian proposal distribution, we incorporate Kalman filter into a particle filter to enhance the performance of the resampling process. To estimate the posterior probability density properly with lower computational complexity, we only employ a single Kalman filter to propagate Gaussian distribution. Experimental results have demonstrated the effectiveness and robustness of the proposed algorithm by tracking visual objects in the recorded video sequences.     

动态背景下运动目标检测与跟踪研究

主要研究动态背景下的运动目标检测和跟踪问题。背景补偿差分法是一种常用的动态背景下运动目标检测算法,但检测到的目标轮廓要比其真实轮廓大,检测结果不准确且算法复杂度较高。主动轮廓模型在图像分割和目标提取过程中具有拓扑结构变化灵活性,对数值计算方案的设计更加方便、有效,据此提出一种基于改进C-V模型和卡尔曼滤波的算法,用来检测和跟踪动态背景下的运动目标。提出的算法利用C-V模型曲线演化检测和跟踪目标,使C-V模型在目标的边缘处收敛。结合卡尔曼滤波预测运动目标下一帧位置,从而实现对运动目标轮廓的跟踪。实验结果表明,该方法可以对动态背景下运动目标进行精确的检测与跟踪。     

基于改进高斯混合模型的实时运动目标检测与跟踪*

为提高运动目标检测与跟踪的可靠性,提出了一种基于改进高斯混合模型的实时运动目标检测与跟踪算法。该算法建立可自动调节分布数目的高斯混合背景模型,通过背景减除获取前景图像;利用目标相邻帧的连续性分割运动目标;在此基础上将传统的颜色直方图模型进行改进,提高目标颜色分布的可信度,进而根据目标的位置、大小和颜色构造运动目标全局匹配相似度函数,实时完成运动目标检测与跟踪。利用大量的监控视频数据进行验证,结果表明,与传统的检测跟踪算法相比,该算法减少了计算量,提高了复杂背景情况下运动目标检测与跟踪的可靠性。     

Agent-based reconfigurable architecture for real-time object tracking

Most conventional object tracking algorithms are implemented on general-purpose processors in software due to its great flexibility. However, the real-time performance is hard to achieve due to the inherent characteristics of the sequential processing of these processors. To tackle this issue, a reconfigurable system-on-chip (rSoC) platform with microprocessors and FPGAs is applied in this paper. To simplify the hardware/software interface, a Belief–Desire–Intention (BDI)-based multi-agent architecture is proposed as the unified framework. Then an agent-based task graph and two heuristic partitioning methods are proposed to partition the hardware and software on an rSoC platform. Compared to the module-based architecture, this BDI-based multi-agent architecture provides more efficiency, flexibility, autonomy, and scalability for the real-time tracking systems. A particle swarm optimization (PSO)-based object detection and tracking algorithm is applied to evaluate the proposed architecture. Extensive experimental results of object tracking demonstrate that the proposed architecture is efficient and highly robust with real-time performance.     

无表观特征小目标检测与跟踪

检测跟踪模糊的小目标是计算机视觉领域中难度极大,富有挑战的任务。由于被跟踪的目标过小或过于模糊,难以提取合适的可用于检测和跟踪的表观特征,使得现有的目标检测和跟踪算法不能解决上述问题。前景运动物体区别于背景随机噪声的一个重要特征是运动物体具有一定的运动规律,基于这个假设提出一种新方法,根据物体的运动规律对其进行跟踪。首先,提出利用运动物体的时空域关联性,对视频中的运动目标进行分割和去噪;其次,提出了利用动态规划得出并优化物体的运动轨迹。各种条件下的实验结果表明了上述方法的精确性和鲁棒性。     

基于置信度策略选择的实时目标跟踪方法

目标跟踪一直是计算机视觉领域研究的热点和难点,受自然场景中复杂干扰因素影响,现有方法的速度和精度尚待改善。本文首先对基于颜色属性的目标跟踪算法改进,使之更为鲁棒且速度达到实时。接下来,针对被跟踪目标发生遮挡时,采用基于颜色属性的跟踪算法导致错误累积进而产生漂移甚至跟踪失败的问题,引入运算量较大但对遮挡有较强抵抗能力的稀疏协作表观模型。为了同时保证算法的速度和准确性,本文构建了一套基于跟踪结果置信度评量的策略选择机制,将两种算法有机整合。在多个公开数据集下的对比实验显示,与现有跟踪算法相比,本文方法在跟踪效果和速度上具有较显著优势,并在目标存在严重遮挡、光照变化、运动模糊等情况时,均可以取得较好的跟踪效果。     

Dual-template adaptive correlation filter for real-time object tracking

Multimedia Tools and Applications - Visual object tracking is a hot topic in the field of computer vision. The drift of the tracking box or loss of the tracking target often occurs for existing...     

Moving object detection using region tracking

For many vision-based systems, it is important to detect a moving object automatically. The region-based motion estimation method is popular for automatic moving object detection. The region-based method has several advantages in that it is robust to noise and variations in illumination. However, there is a critical problem in that there exists an occlusion problem which is caused by the movement of the object. The occlusion problem results in an incorrect motion estimation and faulty detection of moving objects. When there are occlusion regions, the motion vector is not correctly estimated. That is, a stationary background in the occluded region can be classified as a moving object.In order to overcome this occlusion problem, a new occlusion detection algorithm is proposed. The proposed occlusion detection algorithm is motivated by the assumption that the distribution of the error histogram of the occlusion region is different from that of the nonocclusion region. The proposed algorithm uses the mean and variance values to decide whether an occlusion has occurred in the region. Therefore, the proposed occlusion detection and motion estimation scheme detects the moving regions and estimates the new motion vector, while avoiding misdetection caused by the occlusion problem. The experimental results for several video sequences demonstrate the robustness of the proposed approach to the occlusion problem.This work was presented in part at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24–26, 2003     

A distributed approach for real-time multi-camera multiple object tracking

Estimating the positions of a set of moving objects captured from a network of cameras is still an open problem in Computer Vision. In this paper, a distributed and real-time approach for tracking multiple objects on multiple cameras is presented. A quantitative comparison with six state-of-the-art methods has been carried out on the publicly available PETS 2009 data set, demonstrating the effectiveness of the algorithm. Moreover, the proposed method has been tested also on a multi-camera soccer data set, showing its data fusion capabilities.     

视频监控中运动物体的检测与跟踪

针对固定摄像头下的交通监控场景,首先给出一种基于分块原理的背景重建算法,克服了平均法重建的背景图像模糊的缺点。然后用减背景方法检测运动物体,并利用数学形态学方法对得到原始前景点作处理,填补了运动物体内部的空洞,减少了噪声点,改善了检测性能。为适应背景的变化,对背景进行自适应更新,并且通过对Meanshift算法的改进提高了跟踪的准确性。实验结果表明,算法在有效检测到运动物体的同时能够快速准确地跟踪运动物体。     

Blink detection for real-time eye tracking

This work is motivated by our goal of providing non-contact head and eye based control of computer systems for people with motor difficulties. The system described here uses spatio-temporal filtering and variance maps to locate the head and find the eye-feature points, respectively. These feature points are accurately tracked in the succeeding frames by using a modified version of the Lucas–Kanade tracking algorithm with pyramidal implementation. Accurate head and eye tracking results are obtained at a processing rate of more than 30 frames per second (fps) in more than 90% cases with a low false positive blink detection rate of 0.01%. This is achieved under varying lighting conditions for people of different ethnicity, with and without wearing glasses.     

一种基于深度学习目标检测的长时目标跟踪算法

针对长时目标跟踪所面临的目标被遮挡、出视野等常常会导致跟踪漂移或丢失的问题,基于MDNet提出一种深度长时目标跟踪算法(long-term object tracking based on MDNet, LT-MDNet)。首先,引入了一种改进的收缩损失函数,以解决模型训练时正负样本不均衡的问题;其次,设计了一种高置信度保留样本池,对在线跟踪时的每一帧的有效并且置信度最高结果进行保留,并在池满时替换最低置信度的保留样本;最后,在模型检测到跟踪失败或连续跟踪帧数达到特定阈值时,利用保留样本池进行在线训练更新模型,从而使模型在应对长时跟踪时保持鲁棒和高效。实验结果表明,LT-MDNet在跟踪精度和成功率上都展现了极强的竞争力,并且在目标被遮挡、出视野等情况下保持了优越的跟踪性能和可靠性。     

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.     

结合级联卷积目标检测和跟踪的快速人头检测

针对图像序列中遮挡和角度变化等因素易造成人头漏检的情况,提出一种结合级联卷积目标检测模型MTCNN和核相关滤波(KCF)跟踪模型的快速人头检测方法,即MT-KCF人头检测模型。利用批次归一化改进MTCNN网络,采用级联的方式检测人头;将检测到的人头位置信息输入到KCF跟踪模型中,对人头目标进行快速稳定的跟踪;为确保持续稳定地检测到人头,在跟踪多帧后,再次利用检测模型重新对人头进行检测。实验结果表明:MT-KCF模型在图像序列中具有较高的检测精度和较快的检测速度,平均准确率为94. 85%,在640×480大小的图像序列中平均速度为108帧/s。     

A real-time framework for eye detection and tracking

Epidemiological studies indicate that automobile drivers from varying demographics are confronted by difficult driving contexts such as negotiating intersections, yielding, merging and overtaking. We aim to detect and track the face and eyes of the driver during several driving scenarios, allowing for further understanding of a driver’s visual search pattern behavior. Traditionally, detection and tracking of objects in visual media has been performed using specific techniques. These techniques vary in terms of their robustness and computational cost. This research proposes a real-time framework that is built upon a foundation synonymous to boosting, which we extend from learners to trackers and demonstrate that the idea of an integrated framework employing multiple trackers is advantageous in forming a globally strong tracking methodology. In order to model the effectiveness of trackers, a confidence parameter is introduced to help minimize the errors produced by incorrect matches and allow more effective trackers with a higher confidence value to correct the perceived position of the target.     

A framework of joint object tracking and event detection

This paper describes a probabilistic framework for simultaneously performing object tracking and event detection in monocular videos. Mathematically, we cast the problem of jointly tracking and detecting semantic events as a principled model-based search problem in a multi-dimensional state space, where the tracking trajectory and event type are discovered via maximum a posteriori (MAP) optimization. The benefit of this approach comes from its combined utilization of particle probabilistic representation, multiple hypothesis retention, efficient particle propagation, and temporal optimization. We present qualitative and quantitative results from realistic video sequences to demonstrate the effectiveness of this approach.     

Depth-assisted rectification for real-time object detection and pose estimation

RGB-D sensors have become in recent years a product of easy access to general users. They provide both a color image and a depth image of the scene and, besides being used for object modeling, they can also offer important cues for object detection and tracking in real time. In this context, the work presented in this paper investigates the use of consumer RGB-D sensors for object detection and pose estimation from natural features. Two methods based on depth-assisted rectification are proposed, which transform features extracted from the color image to a canonical view using depth data in order to obtain a representation invariant to rotation, scale and perspective distortions. While one method is suitable for textured objects, either planar or non-planar, the other method focuses on texture-less planar objects. Qualitative and quantitative evaluations of the proposed methods are performed, showing that they can obtain better results than some existing methods for object detection and pose estimation, especially when dealing with oblique poses.