An adaptive template matching-based single object tracking algorithm with parallel acceleration

Visual tracking has been widely used in robot systems, and numerous approaches for visual tracking have been proposed. However, developing a robust and real-time visual tracking algorithm which can adaptively track the varying appearance of target under challenging conditions for mobile robot is still an open problem. This paper presents an adaptive probabilistic tracking algorithm with multiple cues integration. An effective evaluation function is proposed to evaluate each cue used for tracking based on their discriminating abilities between foreground and background. Then the likelihood functions of the cues are integrated in particle filter framework with different weights determined based on the evaluation scores. A novel target model updating strategy is proposed to adapt to the varying appearance of target resisting gradual drift which is still an unsolved problem in many adaptive tracking algorithms. Experimental results on a mobile robot demonstrate the robust performance of the proposed algorithm under challenging conditions.

The demand for intelligent robots is increasing rapidly with the advancement in technology. This paper presents an end-to-end approach for a person following robot. It would be a great help if robots could behave as a helping hand for humans in critical environments like industries, markets as well as in hospitals. Because of balanced accuracy and speed, Siamese trackers got great attention. Here we are using a single object tracker for a person following and Robot Operating System (ROS) for communication between various nodes. The Robot is equipped with a Microsoft Kinect sensor which will provide RGBD (Red Green Blue image and Depth image) image. Initially, this system utilizes a deep learning algorithm for single object tracking to track a person. Further, the system can calculate the centroid of the target person as well as the depth information. Finally, this data is given to the navigation module of the robot. This will control the robot's motion

The receiver of a global navigation satellite system (GNSS) is likely to lose tracking for a GNSS signal in some degraded environments. To solve this problem, this paper designs a new adaptive tracking algorithm for GNSS signals. First, we design an error extraction module to extract phase errors so that a CTL can estimate phase errors without using a loop discriminator, which can reduce the requirements of the carrier-to-noise ratio (CNR) of GNSS signals. Second, we design a motion detection module to detect the real-time movement status of GNSS receivers. Then, using its detecting results as inputs, we design an algorithm to automatically make the CTL switch between a second-order loop and a third-order loop. Third, we design a bandwidth-adjusting module to adjust the bandwidth of CTL, according to the CNR and the movement status of a GNSS receiver. Finally, a simulation is performed to verify that our adaptive carrier tracking algorithm can effectively improve the precision of CTL, as well as enhance its dynamic range.

Despite many years of research, object tracking remains a challenging problem, not only because of the variety of object appearances, but also because of the complexity of surrounding environments. In this research, we present an algorithm for single object tracking using a particle filter framework and color histograms. Particle filters are iterative algorithms that perform predictions in each iteration using particles, which are samples drawn from a statistical distribution. Color histograms are embedded in these particles, and the distances between histograms are used to measure likelihood between targets and observations. One downside of color histograms is that they ignore spatial information, which may produce tracking failure when objects appear that are similar in color. To overcome this disadvantage, we propose a saliency-based weighting scheme for histogram calculation. Given an image region, first its saliency map is generated. Next, its histogram is calculated based on the generated saliency map. Pixels located in salient regions have higher weights than those in others, which helps preserve the spatial information. Experimental results showed the efficiency of the proposed appearance model in object tracking under various conditions.

Object tracking tasks often face problems such as illumination and appearance changes due to various scenarios. To effectively solve such problems, single object tracking algorithms in recent years have improved the stability of the tracker by introducing online learning, reducing tracking drift, and tracking objects stably even with large deformations. However, on the one hand, employing online learning increases computation costs, causing the tracker to run slower. On the other hand, because it learns from the tracking results, the tracking template will only be correctly updated if the object is accurately tracked. Any incorrect update will result in tracking failure. In this paper, we propose a filtering algorithm for online learning sample processing in object tracking to remedy these issues. Our method can select valid training samples and discard unnecessary training samples in object tracking. Numerous experiments demonstrate that our algorithm improves the tracking accuracy, reduces the computation complexity, and improves the running speed and run‐time. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

We present an adaptive multi-feature fusion visual object tracking algorithm based on Siamese neural network with cross-attention mechanism, SiamAtten for short, which can effectively deal with large appearance changes, complex back-ground and interference. The proposed network consists of two parts. One is the full convolution feature extraction network based on cross-attention mechanism and the other is the region proposal generation network based on adaptive multi-feature fusion. The cross-attention mechanism is used in the first part to improve the response ability of feature extraction of the target. The adaptive feature fusion method is used in the second part to infer the target location in a step-by-step process and to get the robust region proposal by regression. Meanwhile, network parameters are reduced by using the depth-wise separable convolution, and the cross-attention mechanism is proposed in this paper can effectively enhance the target identification ability and elevate the robustness. Extensive experiments are carried out on three benchmark datasets and much advanced tracking results are obtained.

Considering the poor performance that CamShift algorithm only applies to track targets with certain color,an improved algorithm named adaptive color space tracking algorithm was proposed.Using the new measurements,the current color space was selected dynamically according to the average distance between objects and backgrounds.With the introduction of the mechanism in similarity analysis,time cost was decreased.The experimental results show the new algorithm can track multi-color targets in complex backgrounds more accurately.

For the tracking problem of moving target with scale changes, an adaptive bandwidth tracking algorithm based on principal component variation detection of histogram is proposed. Considering feature characteristics of target and background, such as conspicuousness and similarity, discrimination is estimated to select the feature which can differentiate the target and its background to its extent. The number of feature bins is determined by the discrimination. Target scale variation is analyzed by the number of pixels of principal component in histogram. A novel bandwidth criterion is defined to adjust the tracking window adaptively. Simulation shows that the algorithm can detect the scale change of the target and track the target more accurately.

In this paper an advanced anti-jam indoor adaptive GNSS signal acquisition and tracking algorithm is considered. Initially, we were able to determine that double-dwell structure (DDS) reduces the processing time penalty caused by false alarm. Nevertheless, the double-dwell structure is still vulnerable to interference and jamming. In order to determine a suitable advanced anti-jam indoor adaptive GNSS signal acquisition and tracking algorithm for DDS we first perform the Bayesian parameter estimation; i.e., we analytically compute the posterior Bayes probability density function (pdf) and cumulative distribution function (cdf) by applying the Bayes theorem in three steps. First, we compute the complex signal distribution and complex matrix variate signal distribution. This is an original new result never published before. Second, we provide an introduction of the complex Bessel or parabolic function interference distribution due to earlier assumptions of the DDS interference distribution models. We further explain that the process that is required to produce Complex Matrix Variate Bessel Interference Distribution or Complex Matrix Variate Parabolic Function Interference Distribution is an extremely daunting task let alone the Complex Matrix Variate DDS Bayesian posterior density it would seem at the moment nearly an impossible task because it may require the computation of functions such as Kampe de Feriet function and Jack functions of matrix arguments. Third, instead of performing the second step, we relax the assumption of interference to normal distribution. In both the scalar case and complex matrix variate cases we observe that the complex matrix variate Bayesian posterior pdf or cdf is invariant of the observation data or is identical to the prior complex matrix variate signal distribution model. This is an original new and very powerful result never published before. Why this result is so powerful is because up until now we never had a complete theoretical validation of our GNSS receiver design based on either autocorrelation or cross-correlation properties since, the complex matrix variate Bayesian posterior pdf or cdf is invariant of the observation data or is identical to the prior complex matrix variate signal distribution model. Future simulation results will illustrate that an anti-jam indoor adaptive DDS stable detection structure reduces by half the average acquisition time and significantly outperform its predecessor against interference and jamming. Moreover, future simulation results will show further advancements of the Giftet Inc. MATLAB library capability to perform advanced numerical computations based on closed form expressions of the generalized Bessel function distributions and generalized parabolic cylinder function distribution models via Kampe de Feriet function and Jack functions.

In this paper, we develop a robust visual servo system for object tracking applications of a nonholonomic mobile robot. The system mainly consists of an adaptive shape tracking algorithm and a robust visual servo controller. The adaptive shape tracking algorithm is designed to automatically detect the shape contours of moving objects, extract the shape parameters, and continuously track the object in shape parameter space. Based on direct measurements of the shape parameters, the visual servo controller is designed by using the sliding mode control technique and is robust to uncertainties of the object's motion. Through a Lyapunov-based stability analysis, a sufficient condition on selection of control gains to achieve the tracking goal in finite time is provided.

At endmost stage of flight for tracking, target often tends to fulfill whole scene. If the target maneuvers rapidly, it is easy to lose the target. In this paper, an adaptive template update tracking algorithm model based on graph-regularized salience is proposed to solve this problem. The proposed algorithm introduces the graph-regularized salience model into the target tracking framework. When the target’s size exceeds the setting threshold or the target will overflow the screen in the setting number of frames, that is, the target’s lifetime, salience model is used to extract the most prominent position of the target to update the template, in order to ensure that the template has a good response to the target and ensure the stability of target tracking.

In order to improve the tracking accuracy of surface target with multiple cruise missiles, an adaptive fusion tracking algorithm based on multi-missile network is proposed. For this method, optimized arrangement of chief missiles and attack missiles is performed to improve the penetration capability of multiple cruise missiles firstly. Then time alignment and space alignment is adopted to reduce the difference multiple cruise missiles. Finally, adaptive fusion tracking algorithm is performed to further improve the tracking accuracy of multiple cruise missiles based on the statistic threshold metric. Simulation results show that, target tracking can be finished more effectively than existing methods by using the proposed algorithm.

The SOPLAT (Single Observer Location And Tracking) technique has been used in bistatic systems, in which the transmitter only emits radar signal, and there is no need for synchronization between the transmitter and receiver. Under conditions of knowing PRF of radar signals emitted by the transmitter and the position of the transmitter, an algorithm, WMEKF (Weighted Modified Extended Kalman Filter) can be used to locate and track targets moving with constant speed by means of DOA and TOA measurement series. But for maneuvering targets, WMEKF algorithm is easily diverging, so it is not applicable. A new method for tracking maneuvering targets in bistatic systems with an independent receiver is described. Based on WMEKF algorithm, this paper introduces an adaptive tracking algorithm AWMEKF with a maneuvering detector for tracking maneuvering targets. Its performance for typical maneuvering target paths is evaluated by means of computer simulation.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Conveyor belt systems are widely used to transport goods within production facilities. An obvious task arising in this scenario is counting items that pass through such system. In this paper we focus on a task of counting poultry eggs transported along a conveyor belt. We propose a computer vision-based solution successfully solving this task. The system consists of two main parts: (1) object detection neural network that detects and localizes eggs on a single video frame and (2) object tracking algorithm that tracks eggs between multiple video frames. Our system is highly effective and efficient reaching 99.92% egg count accuracy and operating in real-time even on a mid-range CPU. Besides, the deployment of the system requires only a regular IP camera and personal computer-level machine that has a potential to process multiple conveyor belts in parallel. To the best of our knowledge, this is the first academic work on applying the aforementioned approach to the task of counting poultry eggs. The developed egg counting solution is a part of the CloudD system for organization of poultry production pipelines and was deployed on multiple conveyor belts on one of the Russian poultry farms.

To investigate the problem of improving tracking performance in wide monitoring area for netted multi-sensor system, an adaptive tracking algorithm with variable observation (ATVO) based on the scheme of monitoring area segmentation is derived. During the computational process of target tracking, the sub monitoring field of the target is calculated by its position estimation and observation distribution matrix (ODM) is introduced to adaptively adjust measurement system of equations. Observing equations with low accuracy are eliminated and observing equations with high accuracy are reserved. Simulation results show that ATVO not only ensures the precision of state estimation but also reduces the dimension number of observation equations. The accuracy and real-time capability of tracking moving target are improved.