Search

In smart transportation systems, obtaining timely and accurate information about the location, speed, category, and shape of traffic targets requires more than what a single sensor can offer. This shortfall has prompted increased attention and rapid development of fusion systems centered around radar and video. Radar, while effective at measuring speed, often faces issues such as false tracks, redundant tracks, and low visibility in tracking traffic targets. On the other hand, video provides high visualization but struggles with problems such as target adhesion, low detection confidence, and difficulty in speed measurement. The complementary nature of these technologies underscores the importance of fusion systems in addressing the limitations of individual sensors to improve the accuracy and reliability of smart transportation systems. This paper introduces a fusion tracking method that combines radar and video data for tracking traffic targets. By leveraging the target's morphological information at various pixel positions, this method supplements the radar data, thereby enhancing the accuracy of data association. The experimental results demonstrate that the association algorithm for optimal data fusion proposed in this paper improves performance by 3.86% and 2.13% compared with the traditional fusion method and the IOU matching fusion, respectively. In addition, it shows greater resilience to complex environments. [ABSTRACT FROM AUTHOR]

Passive radars based on FM radio signals have low detection probability, high false alarm rates and poor accuracy, presenting considerable challenges to target tracking in radar networks. Moreover, a high false alarm rate increases the computational burden and puts forward high requirements for the real-time performance of networking algorithms. In addition, low detection probability and poor azimuth accuracy result in a lack of redundant information, making measurement association and track initiation challenging. To address these issues, this paper proposes an FM-based passive radar network based on the concepts of elementary hypothesis points and elementary hypothesis track, as well as a track initiation algorithm. First, we construct possible low-dimensional association hypotheses and solve for their corresponding elementary hypothesis points. Subsequently, we associate elementary hypothesis points from different frames to form multiple possible elementary hypothesis tracks. Finally, by combining multi-frame radar network data for hypothesis track judgment, we confirm the elementary hypothesis tracks corresponding to the real targets, and eliminate the false elementary hypothesis tracks caused by incorrect associations. Result reveal that the proposed algorithm has lower computational complexity and faster track initiation speed than existing algorithms. Moreover, we verified the effectiveness of the proposed algorithm using simulation and experimental results.

To meet the requirements of autonomous detection of underwater moving targets in a strong reverberation background, a track initiation algorithm based on multiple accumulations of active sonar images was proposed to solve the problem of large amounts of data after space-time processing of active sonar echo signals. Firstly, the underwater multi-target track initiation model in the strong reverberation background of the active sonar was constructed. The range-azimuth-frame time three-dimensional sonar image was condensed into the range-azimuth two-dimensional sonar image by selecting the largest data of sonar images, and the accumulated frame information was retained. The measurement information and energy information of the target were obtained through the centroid clustering point extraction method, and the data preprocessing was completed. Secondly, the energy was accumulated in the parameter space of the Hough transform, and the initial track of multiple targets was obtained by the method of local peak detection. Finally, in order to improve the accuracy of the track, the reverberation and duplicate tracks were eliminated by using the velocity constraint and track merging method. The simulation results show that compared with conventional target tracking methods, this algorithm can effectively reduce the amount of sonar image data in the course of track initiation and can still achieve autonomous detection of underwater multiple targets with high detection probability in a strong reverberation background.

In order to select reliable tracks from the limited measurement cycles, the track initiation has been studied, which affects all subsequent stages of target tracking. Numerous false target tracks were produced by traditional logic algorithms, and the Hough transform method was sensitive to noise. Based on adaptive gates and fuzzy Hough transform, a track initiation algorithm is proposed in this paper, which combines the advantages of the two types of methods to reduce the amount of false alarm, and completes the high-quality track initiation. Firstly, an adaptive gate is designed to filter the detection clutter. And then the fuzzy theory is used to obtain the accumulated matrix in the Hough transform process. Finally, the tracks are determined by the threshold method, and the track initiation is completed. The proposed method can reduce the false track occupancy rate, and complete higher quality track initiation in short detection cycles in simulation experiments. It is more suitable for multi-target track initiation under the surroundings of intensive clutter. [ABSTRACT FROM AUTHOR]

This paper studies the problem of resolvable group target track initiation (RGTI) and proposes a novel method to obtain the discrete association vectors and continuous trajectory parameters of individual targets within the group, which benefits from the fitting representations of target tracks and the utilization of group target motion constraint. Specifically, every target track within the group is modeled as a weighted sum of a same set of time basis functions with different weights, and the aim is to solve multiple pairs of association vectors and trajectory parameters, i.e., unknown weights, according to the measurement equation and group target motion constraint. Next, a joint RGTI framework, which includes track extraction, track purification, trajectory parameter and association vector correction, is proposed to transform the original complex constraint set solving problem into multiple solvable sub-problems. And the convergence of RGTI is ensured through iterative optimization of track purification, trajectory parameter correction and association vector correction. Finally, simulation example demonstrates the superiority of the proposed method compared with existing multi-target track initiation methods. [ABSTRACT FROM AUTHOR]

In the heavy clutter environment, the information capacity is large, the relationships among information are complicated, and track initiation often has a high false alarm rate or missing alarm rate. Obviously, it is a difficult task to get a high-quality track initiation in the limited measurement cycles. This paper studies the multi-target track initiation in heavy clutter. At first, a relaxed logic-based clutter filter algorithm is presented. In the algorithm, the raw measurement is filtered by using the relaxed logic method. We not only design a kind of incremental and adaptive filtering gate, but also add the angle extrapolation based on polynomial extrapolation. The algorithm eliminates most of the clutter and obtains the environment with high detection rate and less clutter. Then, we propose a fuzzy sequential Hough transform-based track initiation algorithm. The algorithm establishes a new meshing rule according to system noise to balance the relationship between the grid granularity and the track initiation quality. And a flexible superposition matrix based on fuzzy clustering is constructed, which avoids the transformation error caused by 0-1 voting method in traditional Hough transform. In addition, the algorithm allows the superposition matrixes of nonadjacent cycles to be associated to overcome the shortcoming that the track can't be initiated in time when the measurements appear in an intermittent way. And a slope verification method is introduced to detect formation-intensive serial tracks. Last, the sliding window method is employed to feedback the track initiation results timely and confirm the track. Simulation results verify that the proposed algorithms can initiate the tracks accurately in heavy clutter. [ABSTRACT FROM AUTHOR]

Owing to the shortcomings of single view angle and insufficient information in the monostatic radar, it is difficult to effectively suppress the deception-false-target (FT) jamming. To counter the range-velocity compound deception jamming, a suppression method based on the radar position error (RPE) is proposed for active $/$ passive netted radar on different moving platforms. In this algorithm, FTs are discriminated in the two stages of track initiation and target tracking. Firstly, in the track initiation stage, the RPE is taken into consideration to construct the error covariance matrix of the Mahalanobis distance. Then, the chi-square test is used to make the measurement correlation based on the azimuth and pitch angle information, which eliminates some FTs. Secondly, the measurements in active radar, which has been successfully correlated, are regarded as the supplementary for track initiation of passive radar. The FTs are discriminated again based on the radial velocity information. Finally, in the target tracking stage, the targets are tracked independently in active radar and passive radar. The sequential track correlation method is adapted to eliminate the remaining FTs that have been maintained in active radar. Simulation results verify that the proposed method improves the discrimination probability of FTs under the condition of ensuring the high discrimination probability of the physical target (PT). [ABSTRACT FROM AUTHOR]

Track initiation is the first important step in group target tracking, and it has a direct effect on the quality of the overall procedure. Traditional radar target tracking methods only utilize information about the target position to detect group numbers, but they do not use information relating to echo amplitude. Tracks are thus easily lost, as the numbers of detected groups and equivalent measurements are inaccurate. This paper proposes a group target track initiation method aided by echo amplitude information to ameliorate these problems. In this respect, target position and echo amplitude information is used to detect the number of target groups, and equivalent measurements are then computed using amplitude weighting and position weighting. Echo amplitude information is employed in the step of detecting group target numbers and computing the equivalent measurements, and group target tracks are subsequently initialized using the modified logic method. The proposed method can be used to correctly detect the number of target groups when the number is previously unknown. Furthermore, the method reduces the rate of track loss and improves the performance of group target tracking. The effectiveness of the proposed method is validated by the simulation results.

We propose a RANdom SAmple Consensus(RANSAC) method using signal intensity for the track initiation of small target detection. The use of a low constant false-alarm rate threshold to detect a small radar cross-section target can cause numerous false alarms. Consequently, the optimal initialization of the target can be difficult. To solve this issue, we propose a sample-splitting RANSAC (S-RANSAC) method, which compensates for the accuracy degradation due to the lack of inlier data in the RANSAC. The key idea of our approach is to split the received plot data according to signal intensity. We compared the performance of the S-RANSAC method with those of a logic-based algorithm, the Hough transform, and the RANSAC method. Consequently, the S-RANSAC method demonstrated a better track initiation performance than the other methods under the given scenario. [ABSTRACT FROM AUTHOR]

A neutrosophic Hough transform-based track initiation method (NHT-TI) is proposed to solve the uncertain track initiation problem in a complex surveillance environment. In the proposed method, a neutrosophic set is employed to describe the uncertain association of a measurement with different targets, which is divided into three categories, including the association with real targets, uncertain targets, and false targets, respectively. On this basis, the neutrosophic Hough transform (NHT) method is developed in the framework of the standard Hough transform (HT) method. Based on the sequential processing mode of the sensors, candidate temporary tracks are further defined to directly calculate the parameter points in the parameter space, which are utilized to calculate the contribution for the corresponding vote cells in the accumulation matrix by using the Gaussian membership function. Based on the scheme, the NHT method can avoid large traversal operations and reduce computation complexity of the HT method. Moreover, considering the effects of noises and clutters on track initiation, two constraint conditions related to the velocity information of moving targets and the time information of measurement sequences are introduced to suppress false tracks and reduce vote times. Finally, the real tracks can be determined by detecting the peaks of the global accumulation matrix. The performance of the proposed NHT-TI method is evaluated by using two experiments with simulated data and real data in two complex surveillance environments. The results are found to be better than those of the standard HT-based track initiation (HT-TI) method, the modified HT-TI method based on candidate temporary tracks and the improved HT-TI method in detection reliability and computational complexity.

Copyright of Transactions of Beijing Institute of Technology is the property of Beijing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

There is a large error in the actual radar trajectory tracking process. Track initiation is the primary problem in trajectory tracking and the first step in target tracking. The current track initiation algorithms are greatly affected by heavy clutter environments, so it is necessary to propose an algorithm to solve the problem of low track initiation efficiency. This paper presents a track initiation algorithm using a residual threshold in heavy clutter environments. The falling probability of measured value and decision threshold are used to determine the correlation window. The angle limiting condition is added to establish the track association, and the residual threshold is used to further eliminate the false tracks. The initial track experiment with the trajectory data in the sea near Rizhao Port shows that the algorithm is superior to the traditional logic method and Kalman filter method in track quality. The experiment uses the AIS buffer zone to calculate track initiation probability and uses the multi-region AIS trajectory data for verification. The experimental result shows that track initiation probability with the proposed algorithm in this paper can reach 92.31%.

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A novel efficient track initiation method is proposed for the harsh underwater target tracking environment (heavy clutter and large measurement errors): track splitting, evaluating, pruning and merging method (TSEPM). Track initiation demands that the method should determine the existence and initial state of a target quickly and correctly. Heavy clutter and large measurement errors certainly pose additional difficulties and challenges, which deteriorate and complicate the track initiation in the harsh underwater target tracking environment. There are three primary shortcomings for the current track initiation methods to initialize a target: (a) they cannot eliminate the turbulences of clutter effectively; (b) there may be a high false alarm probability and low detection probability of a track; (c) they cannot estimate the initial state for a new confirmed track correctly. Based on the multiple hypotheses tracking principle and modified logic-based track initiation method, in order to increase the detection probability of a track, track splitting creates a large number of tracks which include the true track originated from the target. And in order to decrease the false alarm probability, based on the evaluation mechanism, track pruning and track merging are proposed to reduce the false tracks. TSEPM method can deal with the track initiation problems derived from heavy clutter and large measurement errors, determine the target’s existence and estimate its initial state with the least squares method. What's more, our method is fully automatic and does not require any kind manual input for initializing and tuning any parameter. Simulation results indicate that our new method improves significantly the performance of the track initiation in the harsh underwater target tracking environment. [ABSTRACT FROM AUTHOR]

The probability hypothesis density (PHD) filter and marginal distribution Bayes (MDB) filter are two efficient Bayes approaches for multi-target tracking. However, these two filters fail to provide the state estimation of a target during its initial times due to the poor capability of the two filters on the target detection. To enhance the capability of the MDB filter on the target detection, we present a method for the target detection based on the rule-based track initiation technique, and develop a multi-target Bayes filter with the target detection by applying this target detection method to the MDB filter. Simulation results indicate that this filter has a stronger detecting and tracking capability of the target than the existing PHD and MDB filters. [ABSTRACT FROM AUTHOR]

As a batch processing method, the Hough transform hardly overcomes the accumulation phenomenon of single-scan data sets for it gets confused with the time sequence information of measurements. To solve this nonlinear problem, a track initiation method based on the parallel Hough transform that changes the processing structure of the Hough transform and the accumulating manner of the counter is proposed. After mapping sets of different time measurements to the parameter space separately, the accumulated result of the measurement sets with the same index constitute an accumulated vector. According to the rules, the value of the accumulator can be obtained using the sliding window method. Finally, we make a decision on whether to initiate a track or not through threshold detection. Simulation experiment results of track initiation problems with different scan times under heavy clutters show the efficiency of the parallel Hough transform.

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Most radar systems employ a feed-forward processing chain in which they first perform some low-level processing of received sensor data to obtain target detections and then pass the processed data on to some higher-level processor such as a tracker, which extracts information to achieve a system objective. System performance can be improved using adaptation between the information extracted from the sensor/processor and the design and transmission of subsequent illuminating waveforms. As such, cognitive radar systems offer much promise. In this paper, we develop a general cognitive radar framework for a radar system engaged in target tracking. The model includes the higher-level tracking processor and specifies the feedback mechanism and optimization criterion used to obtain the next set of sensor data. Both target detection (track initiation/termination) and tracking (state estimation) are addressed. By separating the general principles from the specific application and implementation details, our formulation provides a flexible framework applicable to the general tracking problem. We demonstrate how the general framework may be specialized for a particular problem using a distributed sensor model in which system resources (observation time on each sensor) are allocated to optimize tracking performance. The cognitive radar system is shown to offer significant performance gains over a standard feed-forward system. [ABSTRACT FROM PUBLISHER]

According to the feature that the measurements of the same target at the same time have spherical shape, an algorithm of track initiation based on adaptive K-means clustering and modified logic-based approach is proposed in this paper. The improved K-means clustering algorithm can determine the cluster number and the initial cluster centers adaptively. Then the center of each cluster is found and taken as the measurement of the targets at this moment. By doing so, the track initiation process is simplified. According to the target's movement characteristic, a modified logic-based method is used to initiate the target track. Simulation results show that the improved K-means clustering algorithm can recognize the number of targets correctly and the recognized targets are close to the true targets; the modified logic-based approach can effectively suppresses clutter and reduces the probability of false alarm. [ABSTRACT FROM AUTHOR]

Aimed at the problem that the traditional track initiation method can not initiate the near space hypersonic target track effectively, this paper proposed one kind of track initiation method on the basis of variable wave gate. On the basis of analyzing the characters of the near space hypersonic target, and it set up sector gate, ellipse gate and partial circle gate exclusively aiming at the near space hypersonic target, and set up ellipse gate according to the previous locality and velocity information when there was no effective measurement in the sector gate, it set up the partial circle gate according to the hypothesis that the target changed its movement mode at earlier time if there was no effective measuring in the ellipse gate, to make sure that the target real measurement was in the gate, and initiated the target track by the fuzzy decision-making method. The simulation results show that this new method can initiate tracks of near space hypersonic targets effectively and improve the target track initiation rate, it has engineering application meaning. [ABSTRACT FROM AUTHOR]

The Radar/IR integrated detector has become an important stream of combined precision guided technology. For track initialization caused by systematic error and different measurement spaces of 2D radar/IR sensors, a new fuzzy track initialization method based on measurement combination for heterogeneous sensors is proposed. In this proposed method, through extracting topology sequences of azimuth angle from each sensor in the same period, measurements of different dimension are classified with the topology sequence method and they are fused with the weighted average method. And a set of candidate targets' measurements is built by cumulating combined measurements in several periods. Finally, a fuzzy Hough transform (FHT) method is utilized to detect targets' tracks. In track detection, measurements' sequence time information and targets' kinematics information are utilized sufficiently. Furthermore, the influences of both measuring system uncertainties and fixing track rules on track initialization are considered. Experimental results illustrate that the proposed method can realize track initialization for heterogeneous sensors effectively. It achieves less computation load and higher accuracy of line tracks extraction than the traditional Hough transform (HT) method. [ABSTRACT FROM AUTHOR]

The radar data of multi-period is regarded as binary image by the gaining enlightenment from the man-made track initiation method. A track initiation algorithm is proposed based on the Hough transform and dilation on morphology to improve the efficiency of track initiation methods under heavy- clutter environment. Firstly a pre-processing method is proposed to filter the image and to delete the false alarm point based on the association gate formed by the maximum velocity and the radar scan period. An approximate method is proposed to describe the distribution of the target position by analyzing the effect of measurement error on target position. And then the structural element is formed to dilate the binary image so as to emphasize the linear characteristic of the true tracks. Hough transform is used to detect the lines on the binary image. The simulation experiment presents the output of each step, and the results show the efficiency of the proposed pre-processing method and the initiation algorithm. [ABSTRACT FROM AUTHOR]

Abstract: Inspired from various colors of ants in organized insect communities, we propose a novel ant system with a “subtractive” color mixing model of three primary colors for jointly estimating the number of tracks to be initiated and their individual tracks in the multi-sensor multi-target system. Firstly, each ant is assumed to deposit only one type of colored pheromones all the time, namely, cyan, magenta, or yellow, and ant’s decision depends on the colored pheromone similarity comparison with candidates to be visited. Then a mixture optimization function on a three-dimensional parameter space is proposed to exploit best solutions by the following ants, which results in a group of nearly cyan, magenta, or yellow tracks of interest. Finally, a new track initiation evaluation metric, i.e., Optimal Sub-Pattern Assignment (OSPA) distance, is introduced for the unknown number of tracks. Simulation results indicate favorable performance both in clutter-free and cluttered environment. [Copyright &y& Elsevier]

To solve the problem of peak clustering in Hough transform for track initiation of dim targets, an improved track initiation algorithm based on subtractive clustering is proposed. First, Hough transform is used to obtain the votes whose value exceeds the threshold in parametric space, and then a subtractive clustering method is applied to get the final result corresponding to the obtained parameters. Experimental results show that the proposed approach can achieve significant improvement in reducing the peak clustering, and has strong robustness to clutter, especially in complex environment. [ABSTRACT FROM AUTHOR]

Track initiation for dim small moving target particularly in a heavy clutter environment is a theoretical and technological challenge for diverse tracking systems. The different spatial-temporal characteristics presenting in sequence scans are utilized to recognize target and initialize track in this paper. In spatial domain, the small target mapped in the image is a uniform gray spot other than pixel-sized object with high congregated degree, whereas, the false alarm is independent, irrelative and lower congregated degree. In temporal domain, the target's trajectory projected on image sequence is continuous for the continuity of target motion and will appear in the neighborhood at consecutive instants with the maximum probability, on the contrary, the false alarm is disorderly, and occurs in the neighborhood at consecutive instants is impossible. Based on the spatial-temporal characteristics mentioned above, a track initiation algorithm for dim small moving target based on spatial-temporal hypothesis testing, which consists of neighborhood clustering and trajectory continuity, is derived and analyzed in detail. The theory analysis and experimental results show that this method could effectively initialize the track for dim small moving target in heavy clutter environment. [ABSTRACT FROM AUTHOR]

Abstract: A novel track initiation method using ants of different tasks, a kind of ant colony optimization (ACO) algorithm, is developed in this paper. For the proposed system of ants of different tasks, we assume that the number of tracks to be initiated equals the one of tasks, and moreover, ants of the same task search for a given track by collaboration, while ants of different tasks will compete with each other during the search process. In order to fulfill such behaviors, the pheromone model is established, and the corresponding objective function to be optimized is also presented. Numerical simulation results indicate that, for the case of bearings-only multi-sensor-multi-target tracking, the track initiation performance for the proposed system of ants of different tasks performs well compared to other track initiation methods. [Copyright &y& Elsevier]

Abstract: We consider the problem of initializing the tracking filter of a target moving with nearly constant velocity when position- only (1D,2D,or3D) measurements are available. It is known that the Kalman filter is optimal for such a problem, provided it is correctly initialized. We compare a single-point and the well-known two-point difference track initialization algorithms. We analytically show that if the process noise approaches zero and the maximum speed of a target used to initialize the velocity variance approaches infinity, then the single-point algorithm reduces to the two-point difference algorithm. We present numerical results that show that the single-point algorithm performs consistently better than the two-point difference algorithm in the mean square error sense. We also present analytical results that support the conjecture that this is true in general. [Copyright &y& Elsevier]