The detection of infrared small targets under low signal-to-clutter ratio (SCR) and complex background conditions has been a challenging and popular research topic. In this article, a spatial-temporal feature-based detection framework is proposed. First, several factors, such as the infrared target’s small sample, the sensitive size, and the usual sample selection strategy, that affect the detection of small targets are analyzed. In addition, the small intersection over union (IOU) strategy, which helps to solve the false convergence and sample misjudgment problem, is proposed. Second, aiming at the difficulties due to the target’s dim information and complex background, the interframe energy accumulation (IFEA) enhancement mechanism-based end-to-end spatial-temporal feature extraction and target detection framework is proposed. This framework helps to enhance the target’s energy, suppress the strong spatially nonstationary clutter, and detect dim small targets. Experimental results show that using the small IOU strategy and IFEA mechanism, the proposed multiple frame-based detection framework performs better than some popular deep learning (DL)-based detection algorithms.

The detection and tracking of small targets under low signal-to-clutter ratio (SCR) has been a challenging task for infrared search and track (IRST) systems. Track-before-detect (TBD) is a widely-known algorithm which can solve this problem. However, huge computation costs and storage requirements limit its application. To address these issues, a dynamic programming (DP) and multiple hypothesis testing (MHT)-based infrared dim point target detection algorithm (DP–MHT–TBD) is proposed. It consists of three parts. (1) For each pixel in current frame, the second power optimal merit function-based DP is designed and performed in eight search areas to find the target search area that contains the real target trajectory. (2) In the target search area, the parallel MHT model is designed to save the tree-structured trajectory space, and a two-stage strategy is designed to mitigate the contradiction between the redundant trajectories and the requirements of more trajectories under low SCR. After constant false alarm segmentation of the energy accumulation map, the preliminary candidate points can be obtained. (3) The target tracking method is designed to eliminate false alarms. In this work, an efficient second power optimal merit function-based DP is designed to find the target search area for each pixel, which greatly reduces the trajectory search space. A two-stage MHT model, in which pruning for the tree-structured trajectory space is avoided and all trajectories can be processed in parallel, is designed to further reduce the hypothesis space exponentially. This model greatly reduces computational complexity and saves storage space, improving the engineering application of the TBD method. The DP–MHT–TBD not only takes advantage of the small computation amount of DP and high accuracy of an exhaustive search but also utilizes a novel structure. It can detect a single infrared point target when the SCR is 1.5 with detection probability above 90% and a false alarm rate below 0.01%.

The Bernoulli filters are a class of the optimal single-target Bayesian filter. In the classical Bernoulli filter, the clutter process can be arbitrary but the target must be a point target. However, if the target is an extended target or there are multiple propagation paths between the sensor and the target, the measurement process becomes more complicated and single target may produce multiple detections at one scan. Unlike the classical Bernoulli filter, the extended target Bernoulli filter and the multipath Bernoulli filter can be applied to a scenario in which a single target produces multiple detections. However, the clutter process is assumed to be Poisson in these filters. In this letter, the general Bernoulli filter, in which both the clutter and target measurement processes are allowed to be arbitrary, is proposed. The derivation of the filter is on the basis of the probability generating functional in the finite set statistics. In specific circumstances, the general Bernoulli filter can reduce to the classical Bernoulli filter or the multipath Bernoulli filter. In simulation, the measurement model of over-the-horizon radar is used. Simulation results show that the proposed filter can be applied to more general tracking scenarios.

When a target generates multiple detections, standard tracking algorithms are not applicable. Unlike extended target tracking, which has received considerable attention, studies on generalised multiple‐detection tracking (MDT) are still scarce. MDT algorithms proposed in recent years suffer from high computational complexity. In this work, based on distance partitioning, the authors propose a generalised distance partitioning (GD partitioning) algorithm to reduce the number of partitions, and thus decrease the computational complexity of MDT filters. In the algorithm, after defining a multi‐detection distance and calculating the corresponding distance threshold, the authors calculate the original partition of measurement set by using distance partitioning. Subsequently, on the basis of original partition, they can obtain informative subsets to replace all subsets in a multiple‐detection Bernoulli filter, as well as a collection of partitions to replace all partitions in multiple‐detection probability hypothesis density filter. Simulations show that the algorithm can notably reduce the number of subsets and partitions. Thus, by means of a partitioning algorithm, computational complexity of random finite set‐based MDT filters is decreased successfully, which implies that a GD partitioning algorithm may play an important part in real‐time MDT systems.

The issue of extended target multipath tracking has been studied. Based on the geometry model on the sea surface, a novel extended target multipath tracking algorithm is proposed under the random finite sets (RFS) framework. In the algorithm, extended target probability hypothesis density (ET‐PHD) filter is used as a pre‐processor, and multipath Bernoulli filter (MPBF) is used as main processor. The outputs of the ET‐PHD filter are treated as pseudo‐measurements and fed into the MPBF. At last, probability of existence and target state are estimated from the outputs of MPBF. In contrast with the existing extended target filter and multipath filter, the proposed algorithm does not attempt to get the rigorous solution and avoids the high computational complexity. In order to get the solution of the algorithm, its particle filter implementation has been proposed. Results of simulation show that the proposed algorithm estimates target state accurately. Comparing with extended target Bernoulli filter, the proposed algorithm has good tracking performance at the presence of multipath effect.