•A data-driven approach is proposed to associate maneuvering target observations.•The features including echo similarity and kinematic constraints are designed.•Heterogeneous features are fully fused ...to achieve accurate data association decisions.•The maneuvering target observations can be accurately associated even when pfa is high.
Data association plays an important role in forming target tracks when false alarms exist. Its accuracy is key to reducing the computational burden of the combinatorial explosion problem inherent to target tracking in environments where false alarms are densely distributed. Traditional methods are usually developed according to some assumed motion models and suffer performance degradation when there is mismatch between assumed models and the actual motion, which may often be the case for maneuvering targets. To cope with this problem, we propose a data-driven method that learns the association criteria directly from data. By use of the domain knowledge and a convolutional Siamese network, features of different attributes present in the observations are extracted. Then the features are fused through the use of XGBoost. Simulation results show that the proposed method performs better than the traditional model-based methods in correlating observations of maneuvering targets and avoiding correlations of false alarms. By visualizing the decision process of the feature fusion model, it is found that the proposed method learns from the data to make comprehensive use of multiple features and does not simply set hard thresholds for the features. The computational complexity is also analyzed both theoretically and experimentally.
Traditionally, radar‐based localisation systems are designed to deal with targets in line‐of‐sight (LOS) scenarios. However, the performance of those radar systems is limited by multipath echoes ...reflected from non‐line‐of‐sight (NLOS) targets and walls in the urban areas. In recent years, there has been an increasing interest in multipath exploitation methods aided by urban environmental knowledge. Based on the exploitation of space diversity provided by the multipath effect, this article proposes a novel two‐stage localisation method using a single monostatic radar via association of multipath time‐of‐arrivals (TOAs). In the offline stage, reference TOA data at different locations is generated by a ray‐tracing method to avoid the heterogeneity of multipath propagation at different locations, assuming that the environment information is completely known prior. In the online stage, the TOA set of multipath echoes from the target is estimated by a sparse reconstruction method to achieve super‐resolution rather than the matched filter. Then based on the finite‐set statistics (FISST) theory, a grid‐based multi‐observation data association (GMODA) algorithm is present as the likelihood function of the multipath measurement given a candidate location, which is followed by a maximum likelihood estimation to derive the location of the target. Furthermore, the global nearest neighbour approximation of GMODA is introduced to avoid combinatorial explosion in the association algorithm. Simulation and experiment results on a single antenna millimetre‐wave radar in various scenarios show that the proposed method achieves high localisation accuracy in both LOS and NLOS conditions while maintaining low computational cost at the same time. The presented results suggest that our method can be applied to target localisation applications in the complex urban environment.
Video multi-object tracking is a key task in the field of computer vision and has a wide application prospect in industry, commerce and military fields. At present, the rapid development of deep ...learning provides many solutions to solve the problem of multi-object tracking. However, the challenging problems such as mutation of target appearance, serious occlusion of target area, disappearance and appearance of target have not been completely solved. This paper focuses on online multi-object tracking algorithm based on deep learning, and summarizes the latest progress in this field. According to the three important modules of feature prediction, apparent feature extraction and data association, as will as the two frameworks of detection-based-tracking (DBT) and joint-detection-tracking (JDT), this paper divides deep online multi-object tracking algorithms into six sub-classes, and discusses the principles, advantages and disadvantages of different types of algorithms. Among them, the multi-stage design of the
Multiobject tracking provides situational awareness that enables new applications for modern convenience, public safety, and homeland security. This paper presents a factor graph formulation and a ...particle-based sum-product algorithm (SPA) for scalable detection and tracking of extended objects. The proposed method dynamically introduces states of newly detected objects, efficiently performs probabilistic multiple-measurement to object association, and jointly infers the geometric shapes of objects. Scalable extended object tracking (EOT) is enabled by modeling association uncertainty by measurement-oriented association variables and newly detected objects by a Poisson birth process. Contrary to conventional EOT methods, a fully particle-based approach makes it possible to describe different geometric object shapes. The proposed method can reliably detect, localize, and track a large number of closely-spaced extended objects without gating and clustering of measurements. We demonstrate significant performance advantages of our approach compared to the recently introduced Poisson multi-Bernoulli mixture filter. In particular, we consider a simulated scenarios with up to twenty closely-spaced objects and a real autonomous driving application where measurements are captured by a lidar sensor.
In this paper, we propose an algorithm to deal with the data association problem of the robust confidence ellipsoid filter. First, at every time instant, for each target, we need to get a validation ...gate based on the confidence ellipsoid of the previous time instant. Herein, the validation gate is the minimum volume ellipsoid which guarantees that the true measurement of the target at the current time instant must be contained within it. To obtain the validation gate, an optimization problem is derived from the uncertain dynamic system and it is further converted into a semidefinite programming problem. Then, we make use of the measurements in the validation gate (candidate measurements) and the confidence ellipsoid of the previous time instant to gain the confidence ellipsoid of the current time instant. Similar to the process of obtaining the validation gate, the confidence ellipsoid is obtained by solving a semidefinite programming problem. The ellipsoid has the minimum volume and simultaneously, ensures that the true state vector is contained in it. Next, we propose a strategy to deal with the case where there is no measurement in the validation gate (missing measurement). Last, the numerical examples show the verifications of the proposed algorithm.
•We deal with the data association problem of the robust confidence ellipsoid filter.•A convex optimization problem is derived to obtain the validation gate.•Based on the validation gate, we construct a convex problem to obtain the confidence ellipsoid.•We propose a strategy to deal with the case without measurement in the validation gate.
Multi-Object Tracking (MOT) remains a vital component of intelligent video analysis, which aims to locate targets and maintain a consistent identity for each target throughout a video sequence. ...Existing works usually learn a discriminative feature representation, such as motion and appearance, to associate the detections across frames, which are easily affected by mutual occlusion and background clutter in practice. In this paper, we propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets, so as to achieve robust data association in the tracking process. For the detections without being associated, we design a novel single-shot feature learning module to extract discriminative features of each detection, which can efficiently associate targets between adjacent frames. For the tracklets being lost several frames, we design a novel multi-shot feature learning module to extract discriminative features of each tracklet, which can accurately refind these lost targets after a long period. Once equipped with a simple data association logic, the resulting VisualTracker can perform robust MOT based on the single-shot and multi-shot feature representations. Extensive experimental results demonstrate that our method has achieved significant improvements on MOT17 and MOT20 datasets while reaching state-of-the-art performance on DanceTrack dataset.
In this paper, we explore the performance of the distance-weighting probabilistic data association (DWPDA) approach in conjunction with the loopy sum-product algorithm (LSPA) for tracking multiple ...objects in clutter. First, we discuss the problem of data association (DA), which is to infer the correspondence between targets and measurements. DA plays an important role when tracking multiple targets using measurements of uncertain origin. Second, we describe three methods of data association: probabilistic data association (PDA), joint probabilistic data association (JPDA), and LSPA. We then apply these three DA methods for tracking multiple crossing targets in cluttered environments, e.g., radar detection with false alarms and missed detections. We are interested in two performance metrics: tracking accuracy and computation time. LSPA is known to be superior to PDA in terms of the former and to dominate JPDA in terms of the latter. Last, we consider an additional DA method that is a modification of PDA by incorporating a weighting scheme based on distances between position estimates and measurements. This distance-weighting approach, when combined with PDA, has been shown to enhance the tracking accuracy of PDA without significant change in the computation burden. Since PDA constitutes a crucial building block of LSPA, we hypothesize that DWPDA, when integrated with LSPA, would perform better under the two performance metrics above. Contrary to expectations, the distance-weighting approach does not enhance the performance of LSPA, whether in terms of tracking accuracy or computation time.
Multi-Person Tracking (MPT) is often addressed within the detection-to-association paradigm. In such approaches, human detections are first extracted in every frame and person trajectories are then ...recovered by a procedure of data association (usually offline). However, their performances usually degenerate in presence of detection errors, mutual interactions and occlusions. In this paper, we present a deep learning based MPT approach that learns instance-aware representations of tracked persons and robustly online infers states of the tracked persons. Specifically, we design a multi-branch neural network (MBN), which predicts the classification confidences and locations of all targets by taking a batch of candidate regions as input. In our MBN architecture, each branch (instance-subnet) corresponds to an individual to be tracked and new branches can be dynamically created for handling newly appearing persons. Then based on the output of MBN, we construct a joint association matrix that represents meaningful states of tracked persons (e.g., being tracked or disappearing from the scene) and solve it by using the efficient Hungarian algorithm. Moreover, we allow the instance-subnets to be updated during tracking by online mining hard examples, accounting to person appearance variations over time. We comprehensively evaluate our framework on a popular MPT benchmark, demonstrating its excellent performance in comparison with recent online MPT methods.
This paper describes a method of single-shot global localization based on graph-theoretic matching of instances between a query and a prior map. The proposed framework employs correspondence matching ...based on the maximum clique problem (MCP). The framework is potentially applicable to other map and/or query modalities thanks to the graph-based abstraction of the problem, while many existing global localization methods rely on a query and the dataset in the same modality. We implement it with a semantically labeled 3D point cloud map, and a semantic segmentation image as a query. Leveraging the graph-theoretic framework, the proposed method realizes global localization exploiting only the map and the query. The method shows promising results on multiple large-scale simulated maps of urban scenes.