Loopy belief propagation based data association for extended target tracking

The data association problem of multiple extended target tracking is very challenging because each target may generate multiple measurements.Recently,the belief propagation based multiple target tracking algorithms with high efficiency have been a research focus.Different from the belief propagation based Extended Target tracking based on Belief Propagation(ET-BP)algorithm proposed in our previous work,a new graphical model formulation of data association for multiple extended target tracking is proposed in this paper.The proposed formulation can be solved by the Loopy Belief Propagation(LBP)algorithm.Furthermore,the simplified measurement set in the ET-BP algorithm is modified to improve tracking accuracy.Finally,experiment results show that the proposed algorithm has better performance than the ET-BP and joint probabilistic data association based on the simplified measurement set algorithms in terms of accuracy and efficiency.Additionally,the convergence of the proposed algorithm is verified in the simulations.

Multi-target pig tracking algorithm based on joint probability data association and particle filter

In order to evaluate the health status of pigs in time,monitor accurately the disease dynamics of live pigs,and reduce the morbidity and mortality of pigs in the existing large-scale farming model,pig detection and tracking technology based on machine vision are used to monitor the behavior of pigs.However,it is challenging to efficiently detect and track pigs with noise caused by occlusion and interaction between targets.In view of the actual breeding conditions of pigs and the limitations of existing behavior monitoring technology of an individual pig,this study proposed a method that used color feature,target centroid and the minimum circumscribed rectangle length-width ratio as the features to build a multi-target tracking algorithm,which based on joint probability data association and particle filter.Experimental results show the proposed algorithm can quickly and accurately track pigs in the video,and it is able to cope with partial occlusions and recover the tracks after temporary loss.

A Study of Using Synthetic Data for Effective Association Knowledge Learning

Association,aiming to link bounding boxes of the same identity in a video sequence,is a central component in multi-object tracking(MOT).To train association modules,e.g.,parametric networks,real video data are usually used.However,annotating person tracks in consecutive video frames is expensive,and such real data,due to its inflexibility,offer us limited opportunities to evaluate the system performance w.r.t.changing tracking scenarios.In this paper,we study whether 3D synthetic data can replace real-world videos for association training.Specifically,we introduce a large-scale synthetic data engine named MOTX,where the motion characteristics of cameras and objects are manually configured to be similar to those of real-world datasets.We show that,compared with real data,association knowledge obtained from synthetic data can achieve very similar performance on real-world test sets without domain adaption techniques.Our intriguing observation is credited to two factors.First and foremost,3D engines can well simulate motion factors such as camera movement,camera view,and object movement so that the simulated videos can provide association modules with effective motion features.Second,the experimental results show that the appearance domain gap hardly harms the learning of association knowledge.In addition,the strong customization ability of MOTX allows us to quantitatively assess the impact of motion factors on MOT,which brings new insights to the community.

A split target detection and tracking algorithm for ballistic missile tracking during the re-entry phase

In the re-entry phase of a ballistic missile,decoys can be deployed as a mean to overburden enemy defenses.This results in a single track being split into multiple track-lets.Tracking of these track-lets is a critical task as any miss in the tracking procedure can become a cause of a major threat.The tracking process becomes more complicated in the presence of clutter.The low detection rate is one of the factors that may contribute to increasing the difficulty level in terms of tracking in the cluttered environment.This work introduces a new algorithm for the split event detection and target tracking under the framework of the joint integrated probabilistic data association(JIPDA)algorithm.The proposed algorithm is termed as split event-JIPDA(SE-JIPDA).This work establishes the mathematical foundation for the split target detection and tracking mechanism.The performance analysis is made under different simulation conditions to provide a clear insight into the merits of the proposed algorithm.The performance parameters in these simulations are the root mean square error(RMSE),confirmed true track rate(CTTR)and confirmed split true track rate(CSTTR).

Dense Mapping From an Accurate Tracking SLAM

In recent years, reconstructing a sparse map from a simultaneous localization and mapping(SLAM) system on a conventional CPU has undergone remarkable progress. However,obtaining a dense map from the system often requires a highperformance GPU to accelerate computation. This paper proposes a dense mapping approach which can remove outliers and obtain a clean 3D model using a CPU in real-time. The dense mapping approach processes keyframes and establishes data association by using multi-threading technology. The outliers are removed by changing detections of associated vertices between keyframes. The implicit surface data of inliers is represented by a truncated signed distance function and fused with an adaptive weight. A global hash table and a local hash table are used to store and retrieve surface data for data-reuse. Experiment results show that the proposed approach can precisely remove the outliers in scene and obtain a dense 3D map with a better visual effect in real-time.

A multi-target tracking algorithm based on Gaussian mixture model

Since the joint probabilistic data association(JPDA)algorithm results in calculation explosion with the increasing number of targets,a multi-target tracking algorithm based on Gaussian mixture model(GMM)clustering is proposed.The algorithm is used to cluster the measurements,and the association matrix between measurements and tracks is constructed by the posterior probability.Compared with the traditional data association algorithm,this algorithm has better tracking performance and less computational complexity.Simulation results demonstrate the effectiveness of the proposed algorithm.

A survey: which features are required for dynamic visual simultaneous localization and mapping?

In recent years,simultaneous localization and mapping in dynamic environments(dynamic SLAM)has attracted significant attention from both academia and industry.Some pioneering work on this technique has expanded the potential of robotic applications.Compared to standard SLAM under the static world assumption,dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly.Therefore,dynamic SLAM can provide more robust localization for intelligent robots that operate in complex dynamic environments.Additionally,to meet the demands of some high-level tasks,dynamic SLAM can be integrated with multiple object tracking.This article presents a survey on dynamic SLAM from the perspective of feature choices.A discussion of the advantages and disadvantages of different visual features is provided in this article.

VIDEO MULTI-TARGET TRACKING BASED ON PROBABILISTIC GRAPHICAL MODEL

In the technique of video multi-target tracking,the common particle filter can not deal well with uncertain relations among multiple targets.To solve this problem,many researchers use data association method to reduce the multi-target uncertainty.However,the traditional data association method is difficult to track accurately when the target is occluded.To remove the occlusion in the video,combined with the theory of data association,this paper adopts the probabilistic graphical model for multi-target modeling and analysis of the targets relationship in the particle filter framework.Ex-perimental results show that the proposed algorithm can solve the occlusion problem better compared with the traditional algorithm.

DESIGN OF LOW-DENSITY PARITY CHECK CODES FOR MIMO SYSTEMS WITH DOUBLY-ITERATIVE RECEIVERS

In this paper, the Multiple Input Multiple Output (MIMO) doubly-iterative receiver which consists of the Probabilistic Data Association detector (PDA) and Low-Density Parity-Check Code (LDPC) decoder is developed. The receiver performs two iterative decoding loops. In the outer loop, the soft information is exchanged between the PDA detector and the LDPC decoder. In the inner loop, it is exchanged between variable node and check node decoders inside the LDPC decoder. On the light of the Extrinsic Information Transfer (EXIT) chart technique, an LDPC code degree profile optimization algorithm is developed for the doubly-iterative receiver. Simulation results show the doubly-receiver with optimized irregular LDPC code can have a better performance than the one with the regular one.

Hybrid-driven Gaussian process online learning for highly maneuvering multi-target tracking

The performance of existing maneuvering target tracking methods for highly maneuvering targets in cluttered environments is unsatisfactory.This paper proposes a hybrid-driven approach for tracking multiple highly maneuvering targets,leveraging the advantages of both data-driven and model-based algorithms.The time-varying constant velocity model is integrated into the Gaussian process(GP)of online learning to improve the performance of GP prediction.This integration is further combined with a generalized probabilistic data association algorithm to realize multi-target tracking.Through the simulations,it has been demonstrated that the hybrid-driven approach exhibits significant performance improvements in comparison with widely used algorithms such as the interactive multi-model method and the data-driven GP motion tracker.

Online multi-target intelligent tracking using a deep long-short term memory network

Multi-target tracking is facing the difficulties of modeling uncertain motion and observation noise.Traditional tracking algorithms are limited by specific models and priors that may mismatch a real-world scenario.In this paper,considering the model-free purpose,we present an online Multi-Target Intelligent Tracking(MTIT)algorithm based on a Deep Long-Short Term Memory(DLSTM)network for complex tracking requirements,named the MTIT-DLSTM algorithm.Firstly,to distinguish trajectories and concatenate the tracking task in a time sequence,we define a target tuple set that is the labeled Random Finite Set(RFS).Then,prediction and update blocks based on the DLSTM network are constructed to predict and estimate the state of targets,respectively.Further,the prediction block can learn the movement trend from the historical state sequence,while the update block can capture the noise characteristic from the historical measurement sequence.Finally,a data association scheme based on Hungarian algorithm and the heuristic track management strategy are employed to assign measurements to targets and adapt births and deaths.Experimental results manifest that,compared with the existing tracking algorithms,our proposed MTIT-DLSTM algorithm can improve effectively the accuracy and robustness in estimating the state of targets appearing at random positions,and be applied to linear and nonlinear multi-target tracking scenarios.

DRO-SLAM: real-time object-aware SLAM for navigation robots and autonomous driving in dynamic environments

Traditional simultaneous localization and mapping(SLAM) mostly performs under the assumption of an ideal static environment, which is not suitable for dynamic environments in the real world. Dynamic real-time object-aware SLAM(DRO-SLAM) is proposed in this paper, which is a visual SLAM that can realize simultaneous localizing and mapping and tracking of moving objects indoor and outdoor at the same time. It can use target recognition, oriented fast and rotated brief(ORB) feature points, and optical flow assistance to track multi-target dynamic objects and remove them during dense point cloud reconstruction while estimating their pose. By verifying the algorithm effect on the public dataset and comparing it with other methods, it can be obtained that the proposed algorithm has certain guarantees in real-time and accuracy, it also provides more functions. DRO-SLAM can provide the solution to automatic navigation which can realize lightweight deployment, provide more vehicles, pedestrians and other environmental information for navigation.

Multi-EAP: Extended EAP for multi-estimate extraction for SMC-PHD filter

The ability to extract state-estimates for each target of a multi-target posterior, referred to as multi-estimate extraction(MEE), is an essential requirement for a multi-target filter, whose key performance assessments are based on accuracy, computational efficiency and reliability. The probability hypothesis density(PHD) filter, implemented by the sequential Monte Carlo approach,affords a computationally efficient solution to general multi-target filtering for a time-varying number of targets, but leaves no clue for optimal MEE. In this paper, new data association techniques are proposed to distinguish real measurements of targets from clutter, as well as to associate particles with measurements. The MEE problem is then formulated as a family of parallel singleestimate extraction problems, facilitating the use of the classic expected a posteriori(EAP) estimator, namely the multi-EAP(MEAP) estimator. The resulting MEAP estimator is free of iterative clustering computation, computes quickly and yields accurate and reliable estimates. Typical simulation scenarios are employed to demonstrate the superiority of the MEAP estimator over existing methods in terms of faster processing speed and better estimation accuracy.