Global Data Association Research Articles

Real-Time Lidar Odometry and Mapping with Loop Closure.

Real-time performance and global consistency are extremely important in Simultaneous Localization and Mapping (SLAM) problems. Classic lidar-based SLAM systems often consist of front-end odometry and back-end pose optimization. However, due to expensive computation, it is often difficult to achieve loop-closure detection without compromising the real-time performance of the odometry. We propose a SLAM system where scan-to-submap-based local lidar odometry and global pose optimization based on submap construction as well as loop-closure detection are designed as separated from each other. In our work, extracted edge and surface feature points are inserted into two consecutive feature submaps and added to the pose graph prepared for loop-closure detection and global pose optimization. In addition, a submap is added to the pose graph for global data association when it is marked as in a finished state. In particular, a method to filter out false loops is proposed to accelerate the construction of constraints in the pose graph. The proposed method is evaluated on public datasets and achieves competitive performance with pose estimation frequency over 15 Hz in local lidar odometry and low drift in global consistency.

Efficient Global MOT Under Minimum-Cost Circulation Framework.

We developed a minimum-cost circulation framework for solving the global data association problem, which plays a key role in the tracking-by-detection paradigm of multi-object tracking (MOT). The global data association problem was extensively studied under the minimum-cost flow framework, which is theoretically attractive as being flexible and globally solvable. However, the high computational burden has been a long-standing obstacle to its wide adoption in practice. While enjoying the same theoretical advantages and maintaining the same optimal solution as the minimum-cost flow framework, our new framework has a better theoretical complexity bound and leads to orders of practical efficiency improvement. This new framework is motivated by the observation that minimum-cost flow only partially models the data association problem and it must be accompanied by an additional and time-consuming searching scheme to determine the optimal object number. By employing a minimum-cost circulation framework, we eliminate the searching step and naturally integrate the number of objects into the optimization problem. By exploring the special property of the associated graph, that is, an overwhelming majority of the vertices are with unit capacity, we designed an implementation of the framework and proved it has the best theoretical computational complexity so far for the global data association problem. We evaluated our method with 40 experiments on five MOT benchmark datasets. Our method was always the most efficient in every single experiment and averagely 53 to 1,192 times faster than the three state-of-the-art methods. When our method served as a sub-module for global data association methods utilizing higher-order constraints, similar running time improvement was attained. We further illustrated through several case studies how the improved computational efficiency enables more sophisticated tracking models and yields better tracking accuracy. We made the source code publicly available on GitHub with both Python and MATLAB interfaces.

Search and rescue under the forest canopy using multiple UAVs

We present a multi-robot system for GPS-denied search and rescue under the forest canopy. Forests are particularly challenging environments for collaborative exploration and mapping, in large part due to the existence of severe perceptual aliasing which hinders reliable loop closure detection for mutual localization and map fusion. Our proposed system features unmanned aerial vehicles (UAVs) that perform onboard sensing, estimation, and planning. When communication is available, each UAV transmits compressed tree-based submaps to a central ground station for collaborative simultaneous localization and mapping (CSLAM). To overcome high measurement noise and perceptual aliasing, we use the local configuration of a group of trees as a distinctive feature for robust loop closure detection. Furthermore, we propose a novel procedure based on cycle consistent multiway matching to recover from incorrect pairwise data associations. The returned global data association is guaranteed to be cycle consistent, and is shown to improve both precision and recall compared with the input pairwise associations. The proposed multi-UAV system is validated both in simulation and during real-world collaborative exploration missions at NASA Langley Research Center.

Instance Segmentation Enabled Hybrid Data Association and Discriminative Hashing for Online Multi-Object Tracking

Online multi-object tracking remains a difficult problem in complex scenes because of inaccurate detections, frequent occlusions by clutter or other objects, similar appearances of different objects, and other factors. In this paper, we propose a hybrid data association strategy combined with instance segmentation and online feature learning to handle these difficulties effectively. First, we utilize an instance segmentation algorithm to separate each object from other objects and backgrounds in a pixel-to-pixel manner, which will help resolve typical difficulties in multi-object tracking, such as ID-switches and track drifting. Moreover, we propose a local-to-global hybrid data association strategy to take advantage of the superiorities of both online and batch data association methods. The local data association between observations in consecutive frames reduces the computational complexity, hence ensuring the efficiency of online tracking. The global data association complements the local data association by integrating multiple video frames, thus alleviating the fragmented tracklets. Last, to improve the appearance discriminability and make it more robust in dealing with appearance variations during tracking, a lightweight semantic-preserving hashing algorithm has been proposed to learn compact hash codes online. Experiments with the MOT17 Challenge dataset demonstrate the superior performance of the proposed approach over other state-of-the-art batch and online tracking methods.

Multiple pedestrian tracking by combining particle filter and network flow model

A novel network flow model is proposed for multiple pedestrian tracking in this paper. Based on tracklets, only a short and reliable detection sequence is needed for effective tracking. Our model fuses the local and global data association strategies to compensate for their respective shortcomings, and can be divided into two stages: a local stage and a global stage. In the local stage, we follow the tracking-by-detection framework to generate confident tracklets by employing a boosted particle filter. In the global stage, the data association is formulated as a Maximum-a-Posteriori (MAP) problem and solved by a typical min-cost flow algorithm. A double-step optimization is designed to solve the long term occlusion. The experimental results show that our method outperforms several state-of-the-art methods for multiple pedestrian tracking.

Multiple Hypothesis Semantic Mapping for Robust Data Association

In this paper, we present a semantic mapping approach with multiple hypothesis tracking for data association. As semantic information has the potential to overcome ambiguity in measurements and place recognition, it forms an eminent modality for autonomous systems. This is particularly evident in urban scenarios with several similar looking surroundings. Nevertheless, it requires the handling of a non-Gaussian and discrete random variable coming from object detectors. Previous methods facilitate semantic information for global localization and data association to reduce the instance ambiguity between the landmarks. However, many of these approaches do not deal with the creation of complete globally consistent representations of the environment and typically do not scale well. We utilize multiple hypothesis trees to derive a probabilistic data association for semantic measurements by means of position, instance and class to create a semantic representation. We propose an optimized mapping method and make use of a pose graph to derive a novel semantic SLAM solution. Furthermore, we show that semantic covisibility graphs allow for a precise place recognition in urban environments. We verify our approach using real-world outdoor dataset and demonstrate an average drift reduction of 33 % w.r.t. the raw odometry source. Moreover, our approach produces 55 % less hypotheses on average than a regular multiple hypotheses approach.

Multi-target tracking with hierarchical data association using main-parts and spatial-temporal feature models

Multi-target tracking in complex scenes is challenging because target appearance features generate partial or significant variations frequently. In order to solve the problem, we propose a multi-target tracking method with hierarchical data association using main-parts and spatial-temporal feature models. In our tracking framework, target feature models and tracklets are initialized when the new targets appear. Main-parts feature model is presented to represent target with partial or no appearance variations. It is established by partitioning a target template into several parts and formulating appearance variation densities of these parts. For the target with significant appearance variations, the tracker learns its global spatial-temporal feature model by integrating appearance with histogram of optical flow features. During tracking, tracklet confidence is exploited to implement hierarchical data association. According to different tracklet confidence values, main-parts and global data association are respectively performed by employing main-parts and spatial-temporal feature models. As a result, our approach uses the Hungarian algorithm to obtain optimal associated pairs between target tracklets and detections. Finally, target feature models and tracklets are updated by the association detections for subsequently tracking. Experiments conducted on CAVIAR, Parking Lot and MOT15 datasets verify the effectiveness and improvement of our multi-target tracking method.

A Hybrid Data Association Framework for Robust Online Multi-Object Tracking.

Global optimization algorithms have shown impressive performance in data-association-based multi-object tracking, but handling online data remains a difficult hurdle to overcome. In this paper, we present a hybrid data association framework with a min-cost multi-commodity network flow for robust online multi-object tracking. We build local target-specific models interleaved with global optimization of the optimal data association over multiple video frames. More specifically, in the min-cost multi-commodity network flow, the target-specific similarities are online learned to enforce the local consistency for reducing the complexity of the global data association. Meanwhile, the global data association taking multiple video frames into account alleviates irrecoverable errors caused by the local data association between adjacent frames. To ensure the efficiency of online tracking, we give an efficient near-optimal solution to the proposed min-cost multi-commodity flow problem, and provide the empirical proof of its sub-optimality. The comprehensive experiments on real data demonstrate the superior tracking performance of our approach in various challenging situations.

PIXiE: an algorithm for automated ion mobility arrival time extraction and collision cross section calculation using global data association.

MotivationDrift tube ion mobility spectrometry coupled with mass spectrometry (DTIMS-MS) is increasingly implemented in high throughput omics workflows, and new informatics approaches are necessary for processing the associated data. To automatically extract arrival times for molecules measured by DTIMS at multiple electric fields and compute their associated collisional cross sections (CCS), we created the PNNL Ion Mobility Cross Section Extractor (PIXiE). The primary application presented for this algorithm is the extraction of data that can then be used to create a reference library of experimental CCS values for use in high throughput omics analyses.ResultsWe demonstrate the utility of this approach by automatically extracting arrival times and calculating the associated CCSs for a set of endogenous metabolites and xenobiotics. The PIXiE-generated CCS values were within error of those calculated using commercially available instrument vendor software. Availability and implementationPIXiE is an open-source tool, freely available on Github. The documentation, source code of the software, and a GUI can be found at https://github.com/PNNL-Comp-Mass-Spec/PIXiE and the source code of the backend workflow library used by PIXiE can be found at https://github.com/PNNL-Comp-Mass-Spec/IMS-Informed-Library.Supplementary information Supplementary data are available at Bioinformatics online.

Distributed data association in smart camera network via dual decomposition

One of the fundamental requirements for pedestrian surveillance using smart camera network is the correct association of each person's observations generated on different camera nodes to the person's track. Recently, distributed data association methods that involve only local information processing on each camera node and mutual information exchanging between neighboring cameras have attracted many research interests due to their superiority in large scale applications. In this paper, we propose a new method that performs global data association in a distributed manner by fusing the appearance and spatio-temporal measurements of objects captured by all camera nodes in the entire network. Specifically, we formulate the data association problem in smart camera networks as an Integer Programming problem by introducing a set of linking variables, and propose two distributed algorithms, namely L-DD and Q-DD, to solve the Integer Programming problem using the dual decomposition technique. In our algorithms, the original Integer Programming problem is decomposed into several subproblems, which can be solved locally on each smart camera. Different subproblems reach consensus on their solutions in a rigorous way by adjusting their parameters iteratively based on the projected subgradient optimization. The proposed method is simple and flexible, in that (i) we can incorporate any feature extraction and matching technique into our framework to calculate the similarity between observations, which corresponds to the costs of links in our model, and (ii) we can decompose the original problem in any way as long as the resulting subproblem can be solved independently and efficiently. We show the competitiveness of our method in both accuracy and speed by theoretical analysis and experimental comparison with state-of-the-art algorithms.

Investigation of wind farm effects on radar multiple target tracking

The increasing demand on wind farm (WF) installations has been raising the necessity and significance of performance assessment of electronic systems in the vicinity of WFs. Using a signal model for WF scattering, the interaction between the wind turbines (WTs) and pulse-Doppler radars (PDRs), the effects of WTs on the PDRs’ detection and tracking processes are investigated in this study. The extensive examination in this study provides insightful perspectives on the tracking performance of PDRs that are employing global nearest neighbor or probabilistic data association methods for the multiple target tracking operation under WF scatterings by exhibiting statistical metrics related to the track losses, false tracks depending on several system parameters, and WF configurations. Additionally, a novel WF design approach that is focused on minimizing WF effects on radar tracking performance is proposed in this study. The signal and tracking model employed in the examination provides a baseline for the analysis for WF-radar interactions, and the proposed WF design approach is promising to minimize the deteriorating effects of WFs on radar tracking performance.

A Multi-Sensor Data Association Algorithm Based on Time Constraint

For the high real-time demands of multi-sensor target tracking system, a global optimum data association algorithm based on time constraint is presented. Firstly, the statistical distance between measurement and prediction center of the track is calculated. An optimal association model among all measurements and all tracks is founded. Then, an improved auction algorithm is proposed to solve the association model. Multi-time auction is conducted in the constrained time, and the optimal solution is obtained by comparing the value of objective function. Simulation shows that the proposed method has a perfect association performance in the constrained time.

Stereo-Based Tracking-by-Multiple Hypotheses Framework for Multiple Vehicle Detection and Tracking

In this paper, we present a tracking-by-multiple hypotheses framework to detect and track multiple vehicles accurately and precisely. The tracking-by-multiple hypotheses framework consists of obstacle detection, vehicle recognition, visual tracking, global position tracking, data association and particle filtering. The multiple hypotheses are from obstacle detection, vehicle recognition and visual tracking. The obstacle detection detects all the obstacles on the road. The vehicle recognition classifies the detected obstacles as vehicles or non-vehicles. 3D feature-based visual tracking estimates the current target state using the previous target state. The multiple hypotheses should be linked to corresponding tracks to update the target state. The hierarchical data association method assigns multiple tracks to the correct hypotheses with multiple similarity functions. In the particle filter framework, the target state is updated using the Gaussian motion model and the observation model with associated multiple hypotheses. The experimental results demonstrate that the proposed method enhances the accuracy and precision of the region of interest.

New optimal algorithm of data association for multi-passive-sensor location system

In dense target and false detection scenario of four time difference of arrival (TDOA) for multi-passive-sensor location system, the global optimal data association algorithm has to be adopted. In view of the heavy calculation burden of the traditional optimal assignment algorithm, this paper proposes a new global optimal assignment algorithm and a 2-stage association algorithm based on a statistic test. Compared with the traditional optimal algorithm, the new optimal algorithm avoids the complicated operations for finding the target position before we calculate association cost; hence, much of the procedure time is saved. In the 2-stage association algorithm, a large number of false location points are eliminated from candidate associations in advance. Therefore, the operation is further decreased, and the correct data association probability is improved in varying degrees. Both the complexity analyses and simulation results can verify the effectiveness of the new algorithms.