This paper proposes a smooth-trajectory estimator for the labelled multi-Bernoulli (LMB) filter by exploiting the special structure of the generalised labelled multi-Bernoulli (GLMB) filter. We devise a simple and intuitive approach to store the best association map when approximating the GLMB random finite set (RFS) to the LMB RFS. In particular, we construct a smooth-trajectory estimator (i.e., an estimator over the entire trajectories of labelled estimates) for the LMB filter based on the history of the best association map and all of the measurements up to the current time. Experimental results under two challenging scenarios demonstrate significant tracking accuracy improvements with negligible additional computational time compared to the conventional LMB filter. The source code is publicly available at https://tinyurl.com/ste-lmb, aimed at promoting advancements in MOT algorithms.
Estimating the trajectories of multi-objects poses a significant challenge due to data association ambiguity, which leads to a substantial increase in computational requirements. To address such problems, a divide-and-conquer manner has been employed with parallel computation. In this strategy, distinguished objects that have unique labels are grouped based on their statistical dependencies, the intersection of predicted measurements. Several geometry approaches have been used for label grouping since finding all intersected label pairs is clearly infeasible for large-scale tracking problems. This paper proposes an efficient implementation of label grouping for label-partitioned generalized labeled multi-Bernoulli filter framework using a secondary partitioning technique. This allows for parallel computation in the label graph indexing step, avoiding generating and eliminating duplicate comparisons. Additionally, we compare the performance of the proposed technique with several efficient spatial searching algorithms. The results demonstrate the superior performance of the proposed approach on large-scale data sets, enabling scalable trajectory estimation.
This paper proposes an efficient and robust algorithm to estimate target trajectories via multi-sensor bearing-only measurements with unknown target detection profiles and clutter rates. In particular, we propose to combine the multi-sensor Generalized Labeled Multi-Bernoulli (MS-GLMB) filter to estimate target trajectories and robust Cardinalized Probability Hypothesis Density (CPHD) filters to estimate the clutter rates. Experimental results show that the proposed robust filter exhibits near-optimal performance in the sense that it is comparable to the optimal MS-GLMB operating with the true clutter rate. More importantly, it outperforms other studied filters when the detection profile and clutter rate are unknown an time-variant. This is attributed to the ability of the robust filter to learn the background parameters on-the-fly.
Determining the trajectories of cells and their lineages or ancestries in live-cell experiments are fundamental to the understanding of how cells behave and divide. This paper proposes novel online algorithms for jointly tracking and resolving lineages of an unknown and time-varying number of cells from time-lapse video data. Our approach involves modeling the cell ensemble as a labeled random finite set with labels representing cell identities and lineages. A spawning model is developed to take into account cell lineages and changes in cell appearance prior to division. We then derive analytic filters to propagate multi-object distributions that contain information on the current cell ensemble including their lineages. We also develop numerical implementations of the resulting multi-object filters. Experiments using simulation, synthetic cell migration video, and real time-lapse sequence, are presented to demonstrate the capability of the solutions.
Performance evaluation is indispensable to the advancement of machine vision, yet its consistency and rigour have not received proportionate attention. This paper examines performance evaluation criteria for basic vision tasks namely, object detection, instance-level segmentation and multi-object tracking. Specifically, we advocate the use of criteria that are (i) consistent with mathematical requirements such as the metric properties, (ii) contextually meaningful in sanity tests, and (iii) robust to hyper-parameters for reliability. We show that many widely used performance criteria do not fulfill these requirements. Moreover, we explore alternative criteria for detection, segmentation, and tracking, using metrics for sets of shapes, and assess them against these requirements.