We propose an efficient solution to the state estimation problem in multi-scan multi-sensor multiple extended target sensing scenarios. We first model the measurement process by a doubly inhomogeneous-generalized shot...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
We propose an efficient solution to the state estimation problem in multi-scan multi-sensor multiple extended target sensing scenarios. We first model the measurement process by a doubly inhomogeneous-generalized shot noise Cox process and then estimate the parameters using a jump Markov chain Monte Carlo sampling technique. The proposed approach scales linearly in the number of measurements and can take spatial properties of the sensors into account, herein, sensor noise covariance, detection probability, and resolution. Numerical experiments using radar measurement data suggest that the algorithm offers improvements in high clutter scenarios with closely spaced targets over state-of-the-art clustering techniques used in existing multiple extended target tracking algorithms.
In dual-sensor multi-target dataprocessing, it is crucial to pair the measurements originating from the same target. Up to now, a number of algorithms have been developed to deal with the issue. However, the local me...
详细信息
ISBN:
(纸本)9798350367164;9798350367157
In dual-sensor multi-target dataprocessing, it is crucial to pair the measurements originating from the same target. Up to now, a number of algorithms have been developed to deal with the issue. However, the local methods among them perform poorly in dense target scenarios, while common global algorithms are difficult to implement because of their huge computational complexity. In this paper, an efficient global method is proposed to deal with the measurement pairing of dense targets in a dual-sensor system. Referring to maximum a posterior probability(MAP) criterion, we show that the optimal pairing scheme is the one that minimizes the quadratic sum of the Euclidean distances between the paired measurements. Therefore, we convert measurement pairing into an assignment problem, which is a typical NP-hard issue in combinatorial optimization. The Hungarian algorithm is adopted to solve the converted problem and the simulation results verify the effectiveness of the proposed method.
The current street scene is becoming more and more complex, with high pedestrian and vehicular traffic and a large number of targets. Aiming at the problems that the accuracy of the current complex street scene-orient...
详细信息
In the process of radar multi-target radar tracking, a variety of multiple targets will lead to a large amount of data to be processed, which increases the complexity of dataprocessing and the computational load. At ...
详细信息
In this paper, we introduce a novel neural network (NN)-based algorithm that significantly improves the target number detection in frequency modulated continuous wave (FMCW) radar systems. By integrating the mathemati...
详细信息
In this paper, we introduce a novel neural network (NN)-based algorithm that significantly improves the target number detection in frequency modulated continuous wave (FMCW) radar systems. By integrating the mathematical processes of Hankelization and singular value extraction, we can perform input data manipulation for effective target number detection, resulting in constructing an efficient NN framework. This is based on the following mathematical properties: 1) A sequence obtained by uniform sampling of the superposition of K radio waves can be represented as a superposition of K geometric sequences;2) A Hankelized matrix formed by the superposition of K geometric sequences exhibits low-rank characteristics;and 3) In an FMCW radar system with K targets, if the received signal, which is represented as a matrix, is ideal, the vectors obtained by extracting this matrix in row, column, diagonal, and anti-diagonal patterns can all be modeled as a superposition of K geometric sequences. The proposed NN framework showcases remarkable improvements in accuracy and efficiency for target number detection, leveraging a small sized dataset and a compact NN design to achieve unprecedented performance levels. Numerical results validate the superiority of our method across various scenarios, establishing a new benchmark for low-dimensional data representation in radar systems.
Due to the inherent weakness and difficulty in extracting features of infrared smalltargets, there is a risk of information loss in the deep layers of the *** propose a new network model called U-Convnext. Specifical...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
Due to the inherent weakness and difficulty in extracting features of infrared smalltargets, there is a risk of information loss in the deep layers of the *** propose a new network model called U-Convnext. Specifically, we design a novel multi-scale Convnext module (Mcnt) based on the Convnext network, aiding in better feature extraction of infrared smalltargets. To mitigate deep-layer information loss, we introduce parallel dilated convolution module (Pdconv) and serial dilated convolution module (Sdconv). Pdconv captures surrounding information from multiple scales during downsampling, while Sdconv enables finer processing in the deep layers of the network. Experimental results demonstrate the superiority of the U-Convnext network over other methods.
In low-altitude airspace surveillance scenarios, accurately distinguishing between birds and unmanned aerial vehicles (UAVs) is of vital importance. However, the high similarity in flight altitude and speed between bi...
详细信息
Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation ...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation is limited because most existing works focus on mixes with predominantly sound events, and small training datasets also limit its potential for supervised learning. Here, we study a single general audio source separation (GASS) model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset. We assess GASS models on a diverse set of tasks. Our strong in-distribution results show the feasibility of GASS models, and the competitive out-of-distribution performance in sound event and speech separation shows its generalization abilities. Yet, it is challenging for GASS models to generalize for separating out-of-distribution cinematic and music content. We also fine-tune GASS models on each dataset and consistently outperform the ones without pre-training. All fine-tuned models (except the music separation one) obtain state-of-the-art results in their respective benchmarks.
We consider the problem of tracking the velocity profile of a target or phenomenon, which is distributed across its range, such as atmospheric wind velocity across altitudes from radar measurements. Typical pulsed rad...
详细信息
We consider the problem of tracking the velocity profile of a target or phenomenon, which is distributed across its range, such as atmospheric wind velocity across altitudes from radar measurements. Typical pulsed radars apply spectral techniques on the matched filtered samples collected from the return echoes at each range bin. Both the true signal as well as the false targets can lead to prominent peaks in the spectral domain, and the recovery algorithms should identify the true profile across range bins. When the measurements in adjacent range bins are correlated, a dynamic program-based data association turns out to be highly suitable. This algorithm is popularly known as the Viterbi data Association (VDA). While VDA has good performance when the true signal is present along with a small number of competing false spectral peaks in each range bin, poor SNRs from high altitude reflections may trigger several false peaks, considerably deteriorating the performance of the VDA. The main contribution of the current paper is in incorporating frequency domain subspace methods (in particular, Frequency selective ESPRIT) to iteratively refine the measurements such that the VDA can further improve the best-identified track so far. When data from multiple sensors are available, the proposed Iterative VDA (IVDA) algorithm can be further reinforced using multi-sensor fusion techniques, which we call the Reinforced IVDA. Both of the proposed algorithms demonstrate significant performance improvements in estimating target velocity at altitudes with low SNRs. In addition to simulations, the proposed algorithms are validated on field data collected from a Mesosphere Stratosphere Troposphere (MST) wind profiling radar.
Detecting small objects in Unmanned Aerial Vehicle (UAV) images is pivotal for a multitude of applications. Given the high-altitude perspective of UAVs, the images they capture often feature intricate backgrounds, pro...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Detecting small objects in Unmanned Aerial Vehicle (UAV) images is pivotal for a multitude of applications. Given the high-altitude perspective of UAVs, the images they capture often feature intricate backgrounds, pronounced object heterogeneity, and a plethora of sparsely situated smalltargets. These characteristics pose significant challenges to conventional detection algorithms. In response, we introduce an enhanced YOLOv7-based technique specifically tailored for small object detection in UAV images. Our approach adds more layers dedicated to small object detection and leverages the Bi-directional Feature Pyramid Network (BiFPN) to extract features across diverse scales. Furthermore, we enhance the detection heads by standardizing channel configurations and incorporate attention mechanisms through the dynamic head framework (DyHead). This allows the model to adaptively modify the detection head structure, catering to varying scales, tasks, and features. Preliminary results on the VisDrone2019 dataset indicate that our method surpasses existing state-of-the-art algorithms in UAV-based small object detection.
暂无评论