Particle Filter For Object Tracking Research Articles

Parallel implementation of color-based particle filter for object tracking in embedded systems

Recently, embedded systems have become popular because of the rising demand for portable, low-power devices. A common task for these devices is object tracking, which is an essential part of various applications. Until now, object tracking in video sequences remains a challenging problem because of the visual properties of objects and their surrounding environments. Among the common approaches, particle filter has been proven effective in dealing with difficulties in object tracking. In this research, we develop a particle filter based object tracking method using color distributions of video frames as features, and deploy it in an embedded system. Because particle filter is a high-complexity algorithm, we utilize computing power of embedded systems by implementing a parallel version of the algorithm. The experimental results show that parallelization can enhance the performance of particle filter when deployed in embedded systems.

Particle Filter with Gaussian Weighting for Human Tracking

Particle filter for object tracking could achieve high tracking accuracy. To track the object, this method generates a number of particles which is the representation of the candidate target object. The location of target object is determined by particles and each weight. The disadvantage of conventional particle filter is the computational time especially on the computation of particle’s weight. Particle filter with Gaussian weighting is proposed to accomplish the computational problem. There are two main stages in this method, i.e. prediction and update. The difference between the conventional particle filter and particle filter with Gaussian weighting is in the update Stage. In the conventional particle filter method, the weight is calculated in each particle, meanwhile in the proposed method, only certain particle’s weight is calculated, and the remain particle’s weight is calculated using the Gaussian weighting. Experiment is done using artificial dataset. The average accuracy is 80,862%. The high accuracy that is achieved by this method could use for the real-time system tracking

Object Tracking in Frame-Skipping Video Acquired Using Wireless Consumer Cameras

Object tracking is an important and fundamental task in computer vision and its high-level applications, e.g., intelligent surveillance, motion-based recognition, video indexing, traffic monitoring and vehicle navigation. However, the recent widespread use of wireless consumer cameras often produces low quality videos with frame-skipping and this makes object tracking difficult. Previous tracking methods, for example, generally depend heavily on object appearance or motion continuity and cannot be directly applied to frame-skipping videos. In this paper, we propose an improved particle filter for object tracking to overcome the frame-skipping difficulties. The novelty of our particle filter lies in using the detection result of erratic motion to ameliorate the transition model for a better trial distribution. Experimental results show that the proposed approach improves the tracking accuracy in comparison with the state-of-the-art methods, even when both the object and the consumer are in motion.

An Adaptive Motion Model and Multi-feature Cues Based on Particle Filter for Object Tracking

If there is an occlusion, the target state model would not match motion model anymore and measurement model also would get worse. To solve these problems, an improved particle filtering algorithm based on adaptive motion model and multiple-cue fusion is presented. Under the theory framework of particle filters, the weighted color histogram and LBP texture feature entropy are used to describe features. And the algorithm adjusts features distribution coefficient automatically by calculating the Bhattacharyya distance between the object reference distribution and object sample distribution, thus the color and texture features can intelligently be fused to develop the observation model. The simple second order auto regressive model is chosen as the state transition model, and the system noise variance is adaptively determined by the minimum noise variance of every feature in object tracking. For the occlusion problem, the system maximum noise variance can be selected, along with particle random motion intensified and disseminating coverage amplified. The posterior distribution of the object is approximated by a set of weighted samples, while object tracking is implemented by the Bayesian propagation of the sample set. The analyses and experiments show that the performance of the proposed method is more effective and robust to target maneuver and occlusion and has good performances under complex background.

Proposed hardware architectures of particle filter for object tracking

In this article, efficient hardware architectures for particle filter (PF) are presented. We propose three different architectures for Sequential Importance Resampling Filter (SIRF) implementation. The first architecture is a two-step sequential PF machine, where particle sampling, weight, and output calculations are carried out in parallel during the first step followed by sequential resampling in the second step. For the weight computation step, a piecewise linear function is used instead of the classical exponential function. This decreases the complexity of the architecture without degrading the results. The second architecture speeds up the resampling step via a parallel, rather than a serial, architecture. This second architecture targets a balance between hardware resources and the speed of operation. The third architecture implements the SIRF as a distributed PF composed of several processing elements and central unit. All the proposed architectures are captured using VHDL synthesized using Xilinx environment, and verified using the ModelSim simulator. Synthesis results confirmed the resource reduction and speed up advantages of our architectures.

Distributed Markov Chain Monte Carlo kernel based particle filtering for object tracking

Particle filters are computationally intensive and thus efficient parallelism is crucial to effective implementations, especially object tracking in video sequences. Two schemes for pipelining particles under high performance computing environment, including an alternative Markov Chain Monte Carlo (MCMC) resampling algorithm and kernel function, are proposed so as to improve tracking performance and minimize execution time. Experimental results on a network of workstations composed of simple off-the-shelf hardware components show that global parallelizable scheme provides a promising resolution to clearly reduce execution time with increasing particles, compared with generic particle filtering.

A parallel histogram-based particle filter for object tracking on SIMD-based smart cameras

We present a parallel implementation of a histogram-based particle filter for object tracking on smart cameras based on SIMD processors. We specifically focus on parallel computation of the particle weights and parallel construction of the feature histograms since these are the major bottlenecks in standard implementations of histogram-based particle filters. The proposed algorithm can be applied with any histogram-based feature sets—we show in detail how the parallel particle filter can employ simple color histograms as well as more complex histograms of oriented gradients (HOG). The algorithm was successfully implemented on an SIMD processor and performs robust object tracking at up to 30 frames per second—a performance difficult to achieve even on a modern desktop computer.

3D Shape-Encoded Particle Filter for Object Tracking and Its Application to Human Body Tracking

We present a nonlinear state estimation approach using particle filters, for tracking objects whose approximate 3D shapes are known. The unnormalized conditional density for the solution to the nonlinear filtering problem leads to the Zakai equation, and is realized by the weights of the particles. The weight of a particle represents its geometric and temporal fit, which is computed bottom-up from the raw image using a shape-encoded filter. The main contribution of the paper is the design of smoothing filters for feature extraction combined with the adoption of unnormalized conditional density weights. The "shape filter" has the overall form of the predicted 2D projection of the 3D model, while the cross-section of the filter is designed to collect the gradient responses along the shape. The 3D-model-based representation is designed to emphasize the changes in 2D object shape due to motion, while de-emphasizing the variations due to lighting and other imaging conditions. We have found that the set of sparse measurements using a relatively small number of particles is able to approximate the high-dimensional state distribution very effectively. As a measure to stabilize the tracking, the amount of random diffusion is effectively adjusted using a Kalman updating of the covariance matrix. For a complex problem of human body tracking, we have successfully employed constraints derived from joint angles and walking motion.

Robust appearance-guided particle filter for object tracking with occlusion analysis

A major challenge for most tracking algorithms is how to address the changes of object appearance during tracking, incurred by large illumination, scale, pose variations and occlusions. Without any adaptability to these variations, the tracker may fail. In contrast, if adapts too fast, the appearance model is likely to absorb some improper part of the background or occluding objects. In this paper, we explore a tracking algorithm based on the robust appearance model which can account for slow or rapid changes of object appearance. Specifically, each pixel in appearance model is represented using mixture Gaussian models whose parameters are on-line learned by sequential kernel density approximation. The appearance model is then embedded into particle filter framework. In addition, an occlusion handling scheme is invoked to explicitly indicate outlier pixels and deal with occlusion events, thus avoiding the appearance model to be contaminated by undesirable outlier ‘thing’. Extensive experiments demonstrate that our appearance-based tracking algorithm can successfully track the object in the presence of dramatic appearance changes, cluttered background and even severe occlusions.