Object Tracking in 3-D Space with Passive Acoustic Sensors using Particle Filter

Object tracking is one of the most important tasks in computer vision, many researchers have proposed a lot of effective methods to solve the all kinds of the recent problems in object tracking. During the movement of the targets, the change of object scale may produce a lot of difficulties in object tracing problems, and it may lead to be failed in tracking. The paper proposed method is designed both correlation filter and particle filter. In order to achieve the purpose of tracking, the process of correlation filter is to learn an array of filters so that the response value obtained by the convolution of the learned filters is the largest. The particle filter guides the sample particles to the distribution mode of the target state. The samples of the particle strategy can effectively deal with the large scale variations of the target during movement. Experiment on the OTB database shows that the paper proposed method makes good performance.

This paper presents a new approach to using locally linear embedding (LLE) method in object tracking problems. By means of measuring the divergence of the K nearest neighbors of test data, a novel method is proposed to distinguish object from background directly through the LLE embedding results. Avoiding training a mapping function, this approach is less dependent on a beforehand training set of object compare to other attempts of utilizing manifold embedding method on object tracking. Besides, an asymmetric version of LLE is derived to improve the tracking performance. A Bayesian inference framework is built to apply this approach to visual tracking problem using particle filter. Experimental results demonstrate both efficiency and adaptability of our algorithm.

Four different parallel particle filters such as globally distributed particle filter (GDPF), resampling with proportional allocation filter (RPA), resampling with non-proportional allocation filter (RNA) and the Gaussian particle filter (GPF), are studied in terms of speedup and tracking accuracy in a bearings-only tracking problem. The filters are implemented on a shared memory multicore computer, where the speedup is measured using up to eight cores. The tracking accuracy is studied in a simulated BOT application where the GPF exhibits best tracking accuracy, and RNA, RPA and GDPF give tracking accuracy comparable to the sequential particle filter. Both GPF and RNA appear to be capable of achieving linear speedup in the number of cores used, while RPA shows somewhat less encouraging speedup and GDPF is found to have a speedup limited to about 3 times.

Particle Filter (PF) is considered as an extension of the Kalman filter to deal with non-Gaussian non-linear dynamic systems. The key idea is to construct a posterior probability by a set of hypotheses representing a potential state of the system. Sample impoverishment is the flaw of the PF techniques in the case of noisy observations. Recently, evolutionary algorithms are added to PF based methods to improve their functionality in noisy environments. A new PF based method called Adaptive Velocity Particle Filter (AVPF) is introduced to overcome this flaw of the PF. The experimental results show that the proposed method has a superior performance in relation to other evolutionary PF in cases of noisy observations.

In this work we study the methods for pedestrian tracking in video sequences and indicate various applications of these methods ranging from surveillance systems to aiding the visually impaired persons. First, we define the general problem of object tracking that comprises the tasks of object detection, identifying the flow of object location in consecutive video images and finally analysis of the tracked trajectory data. We review the well known object tracking techniques i.e. the Mean-Shift and the CAMSHIFT algorithm and discuss their properties. Then we introduce the computational technique known as particle filtering (PF) and explain how we have applied it to the tasks of pedestrian tracking. We compare the PF approach against the Mean-Shift and the CAMSHIFT algorithms in terms of tracking robustness and the required computational demand. We conclude, that on the tested video sequences, the PF tracker outperforms the Mean-Shift and by a small margin the CAMSHIFT algorithm. The PF tracker requires more computational power, however, its tracking performance can be flexibly adjusted to the application requirements.

A typical wide-bandwidth passive acoustic seafloor sensor can record tens of millions of impulsive signals produced by biological, anthropogenic, and physical sources each year. Sources include echolocating toothed whales, snapping shrimp, ship propeller cavitation, echosounders, and weather. The volume and variety of detections make manual classification by human analysts unmanageable without in-depth knowledge of the overall acoustic context of each monitoring location. We describe an interactive machine learning toolkit in development for efficiently detecting and classifying short, highly variable impulsive signals in large passive acoustic datasets. Modules include a configurable event detector, an unsupervised clustering module for identifying dominant signal categories, a deep learning unit for learning and applying event classes, and a graphical user interface for viewing, correcting and evaluating detectors and classifiers. These tools are discussed and illustrated in the context of efforts to extract distinctive features of toothed whale clicks from towed array recordings collected by NOAA SEFSC and to use them to classify detections in unlabeled seafloor sensor recordings. The goal of the toolkit is to facilitate classification of individual signals to species in very large PAM datasets across sensor types and monitoring locations, and to improve quantitative assessment of these sources.

This paper presents efficient object tracking in video sequences using multiple features by embedding mean shift into particle filters. When clutter background and occlusions are present. Particle filtering is used because it is very robust and performs well for non-linear and non-Gaussian dynamic state estimation problems. The image features, such as shape, texture, color, contours, and random motion appearance can be used to track the moving object(s) in videos. We proposed a smart video surveillance system with real-time as well as offline stored video database for moving object detection, classification and tracking capabilities. The graphical user interface of the proposed system using MATLAB 2012b is implemented that operates on both color and gray scale video images from a stationary camera. In this method, we proposed real time moving object detection and tracking system using static webcam that can processes 800*600, 640*480, and 320*240 resolution video sequences for capturing live scene as well as stored database of segmented videos. Issues related with object detection and tracking is jointly employed using mean shift and particle filters. Tracker will estimate the dynamic shape and random appearance of objects. Tracking requires location and shape of object in every segmented frame. Rectangular bounding box is used to improve the estimate of its shape and appearance. Target object may experience partial occlusions, intersection with other objects with similar color distributions, abrupt motion speed changes, and cluttered background. Test result shows improvement in terms of robustness, tracking drifts, accuracy of tracked bounding box to occlusions.

Object/target tracking refers to the problem of using sensor measurements to determine the location, path and characteristics of objects of interest. A sensor can be any measuring device, such as radar, sonar, ladar, camera, infrared sensor, microphone, ultrasound or any other sensor that can be used to collect information about objects in the environment. The typical objectives of object tracking are the determination of the number of objects, their identities and their states, such as positions, velocities and in some cases their features. A typical example of object/target tracking is the radar tracking of aircraft. The object tracking problem in this context attempts to determine the number of aircraft in a region under surveillance, their types, such as military, commercial or recreational, their identities, and their speeds and positions, all based on measurements obtained from a radar. There are a number of sources of uncertainty in the object tracking problem that render it a highly non-trivial task. For example, object motion is often subject to random disturbances, objects can go undetected by sensors and the number of objects in the field of view of a sensor can change randomly. The sensor measurements are subject to random noises and the number of measurements received by a sensor from one look to the next can vary and be unpredictable. Objects may be close to each other and the measurements received might not distinguish between these objects.

As the interest for sensor networks is growing, the demand for integrating both measurement algorithm and data transmission pushes to develop adapted electronic platforms to address this challenge. The use of radiofrequency (RF) passive surface acoustic wave sensors probed by radiomodem interfaces commonly found on wireless sensor node platforms is therefore investigated in this work. This approach allows for providing sensors with virtually infinite life expectancy since no local power source is needed on the sensing site. Rather than harvesting energy from the environment, the passive sensor is loaded by an incoming RF source provided by the same RF interface than the one used for digital communication of the gathered data. Implementing such a scheme in an adhoc wireless sensor network configuration is demonstrated using a novel platform based on the XE1203F radiomodem which provides the specific interfaces mandatory to such an application. Furthermore, a measurement demonstration locating the sensing element in an oven heated to 550°C emphasizes environmental conditions in which no energy storage or battery would withstand such harsh conditions, while the wireless interrogation between the interrogation unit (reader) and the sensor removes the need for high temperature-compatible connector and electrical cable. Implementing the sensor probing algorithm as well as the radiomodem control interface in the TinyOS executive environment then provides access to all the functionalities of this portable development tool, including multi-hop data routing and dynamic ad-hoc network construction, while complying with a clear software hierarchy ranging from low level drivers accessing the hardware to user applications implemented as tasks.

In this paper the tracking of ground targets using acoustic sensors, distributed in a wireless sensor network, is studied. Since only acoustic sensors are utilized in the study the tracking problem can be regarded as a bearings-only application. The solution to the problem is given within the Bayesian recursive framework, where a sequential Monte Carlo method to the ground target tracking problem is developed. The classical sampling importance resampling (SIR) scheme is redesigned to also track multiple targets. The approach for solving the data association problem is based on hypothesis calculations according to the joint probabilistic data association (JPDA) method. Validation and evaluation of the tracking algorithms are performed using simulated data as well as real data extracted from a ground sensor network.

The problem of model-based object tracking in three dimensions is addressed. Most previous work on tracking assumes simple motion models, and consequently tracking typically fails in a variety of situations. Our insight is that incorporating physics models of object behaviour improves tracking performance in these cases. In particular it allows us to handle tracking in the face of rigid body interactions where there is also occlusion and fast object motion. We show how to incorporate rigid body physics simulation into a particle filter. We present two methods for this based on pose and force noise. The improvements are tested on four videos of a robot pushing an object, and results indicate that our approach performs considerably better than a plain particle filter tracker, with the force noise method producing the best results over the range of test videos.

This chapter presents a multi-object tracking system using scale space representation of objects, the method of linear assignment and Kalman filter. In this chapter basically two very prominent problems of multi object tracking have been resolved; the two prominent problems are (i) irrespective of the size of the objects, tracking all the moving objects simultaneously and (ii) tracking of objects under partial and/or complete occlusion. The primary task of tracking multiple objects is performed by the method of linear assignment for which few cost parameters are computed depending upon the extracted features of moving objects in video scene. In the feature extraction phase scale space representation of objects have been used. Tracking of occluded objects is performed by Kalman filter.

The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or non-Gaussian functions, leading to analytically intractable inference. Solutions then require numerical approximation techniques, of which the particle filter is a popular choice. Particle filters, however, degrade in performance as the dimensionality of the state space increases and the support of the likelihood decreases. As an alternative to particle filters this paper introduces a variational approximation to the tracking recursion. The variational inference is intractable in itself, and is combined with an efficient importance sampling procedure to obtain the required estimates. The algorithm is shown to compare favorably with particle filtering techniques on a synthetic example and two real tracking problems. The first involves the tracking of a designated object in a video sequence based on its color properties, whereas the second involves contour extraction in a single image.

This paper presents a comparative study conducted on the performance of the commonly used object tracking and location prediction algorithms for mobile robot navigation in a dynamically cluttered and GPS-denied mining environment. The study was done to test the different algorithms for the same set criteria (such as accuracy and computational time) under the same conditions.The identified commonly used algorithms for object tracking and location prediction of moving objects used in this investigation are Kalman filter (KF), extended Kalman filter (EKF) and particle filter (PF). The study results of those algorithms are analyzed and discussed in this paper. A trade-off was apparent. However, in overall performance KF has shown its competitiveness.The result from the study has found that the KF based algorithm provides better performance in terms of accuracy in tracking dynamic objects under commonly used benchmarks. This finding can be used in development of an efficient robot navigation algorithm.

Moving object tracking is a tricky job in computer vision problems. In this approach, the object tracking system relies on the deterministic search of target, whose color content matches a reference histogram model. A simple RGB histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by shape information. Particle filtering has been proven very successful for non-Gaussian and non-linear estimation problems. In this approach we combine between particle filter and the probability product kernels as a similarity measure using integral image to compute the histograms of all possible target regions of object tracking in video sequence. The shape similarity between a target and estimated regions in the video sequence is measured by their normalized histogram. Target of object tracking is created instantly by selecting an object from the video sequence by a rectangle. Experimental results have been presented to show the effectiveness of our proposed system.