Multiple-hypothesis Algorithm Research Articles

Comparative investigation into Viterbi based and multiple hypothesis based track stitching

In this study a comparative analysis is performed between a novel Viterbi based and multiple hypothesis based track stitching algorithms. The track fragments in the Viterbi based track stitching algorithm are modelled as nodes in a trellis structure. A sequential Viterbi data association algorithm is then used to solve the trellis and associate track fragments with each other. A Kalman filter is used to determine the possible associations as well as the probabilities of the associations between the track fragments. In the multiple hypothesis track stitching algorithm, the hypothesis based multiple hypothesis tracking (MHT) algorithm is extended to perform track fragment to track fragment associations, rather than associating observations to tracks. Aspects of the developed multiple hypothesis algorithm are compared with implementations of a similar nature. Novel aspects of this research include the modification of the sequential Viterbi algorithm, as well as the extension of the MHT algorithm to solve the track stitching problem. It was found that the sequential Viterbi track stitching algorithm performed somewhat better than the multiple hypothesis track stitching algorithm for similar execution times. The Viterbi based track stitching algorithm is also shown to produce more consistently acceptable results.

Audio-Based Detection and Recognition of Conflict Species in Outdoor Environments Using Pattern Recognition Methods

<abstract> <bold><sc>Abstract.</sc></bold> Conflicts between wildlife and agriculture are increasing and may result in severe financial losses. The effectiveness of frightening devices is often highly variable, due to habituation to disruptive or disturbing stimuli. An adaptive frightening device, capable of focusing and altering the disruptive stimuli to specific species could potentially reduce the risk of habituation and thereby provide an effective tool against geese and other conflict species. Automated species detection could form a critical component of an adaptive frightening device. In this article we present a method for detection and recognition of conflict species, including rooks and three species of geese, based on their vocalizations. The detection of conflict species is based on a multiple hypothesis algorithm, where conflict species and background are statistically modeled by Gaussian Mixture Models (GMMs), which have been trained with labeled data. Subsequent individual species recognition is accomplished through maximum likelihood evaluation of GMMs trained on labeled species data. Mel Frequency Cepstral Coefficients (MFCC) are used as features for the both the detection and recognition models. The proposed detection algorithm shows strong performance, with a detection rate of 0.98 ±0.01, and the species recognition results in true positive rates from 0.87 to 0.97 amongst the four species evaluated in this article. Accuracy, precision and false alarm rates have been used to evaluate the performance of the proposed species recognition algorithm. Based on high detection rate of conflict species (0.98 ±0.01) and low false alarm rates (0.02-0.04), we conclude that it is possible to implement robust species specific detection, based on vocalizations, and as such, it can be used as an integrated part of a wildlife management system.

Multiple hypothesis tracking for data association in vehicular networks

The introduction of Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communications in Intelligent Transportation Systems of the future brings new opportunities and new challenges into the automotive scene. Vehicular communications broaden the information spectrum that is available to each vehicle, allowing the enhancement of existing applications and the introduction of new ones. Undoubtedly, the impact of this new technology in transportation safety, efficiency and infotainment is expected to be very important.A significant part of research in vehicular networks (VANETs) is dedicated to networking issues like routing and safety. However, perception systems which until now were based on onboard sensors only, need to incorporate the wirelessly received information in order to extend the situation awareness of the vehicle and the driver. This paper presents an algorithm for associating targets tracked from an onboard radar sensor with the position and motion data received from the VANET. The core of the algorithm is a track oriented multiple hypothesis tracker that is modified for incorporating information included in VANET messages. The algorithm is tested in real scenarios using two experimental vehicles and then compared with two other algorithmic approaches. One is using a simpler single hypothesis algorithm for association of VANET messages and the second is using only the onboard sensors for environment perception. As a result, the advantages of the Multiple Hypothesis Algorithm regarding association performance and the added value of wireless information in the perception system are highlighted.

Student highlight: Dynamic programming-based track-before-detect approach to multitarget tracking

In [11], we showed that an efficient DP-TBD implementation for MTT can be achieved by using the following strategies: 1. Exploiting the structure of the MTT problem: the high-dimensional maximization in DP-TBD can be solved suboptimally in a cheaper but accurate way by using the inherent structure of the tracking model [6]. When targets are clustered into well-separated groups, there is no measurement ambiguity between distant targets; therefore, the target groups can be treated independently. This idea has already been used in particle filter-based MTT methods [6-8] to enhance the sampling efficiency, but it is an unexplored area for DP-TBD. In [11], we showed that, by incorporating this idea into DP-TBD, the high-dimensional maximization can be broken down to several maximizations of lower dimension; thus, the computational cost is significantly reduced. Targets in the same cluster are still considered jointly, so the tracking performance is resilient to target interference when targets are in close proximity. 2. Generalized detection procedure: existing DP-TBD algorithms all use the same detection procedure: after DP integration, the single-target or multitarget state with the global maximum merit is selected and tested against a detection threshold. If the global maximum merit exceeds the threshold, the estimated trajectory is declared and recovered; otherwise the null hypothesis of no target is accepted. In [11], motivated by our analysis of the single-target DP merit function, a generalized detection procedure is developed. A key advantage of this detection procedure is that it requires only a single-target state DP integration without regard for how many targets exist. After the single-target DP integration, not only the global maximum but also every merit is tested against the detection threshold. All the exceeded elements are retained to form an estimation candidate group from which the partitions of the estimated multitarget state, i.e., individual target states, will be extracted recursively in the subsequent processing. The estimated number of targets is then the number of the extracted individual target states. As a result, the dimension of the multitarget state no longer needs to be predetermined during the DP implementation as in existing algorithms. Single-target and multitarget scenarios are handled within one framework instead of using a multiple hypothesis algorithm.

Detección y Seguimiento de Personas Basado en Estereovisión y Filtro de Kalman

The people counting systems are widely used in surveillance applications. This article presents an application for counting people through a stereovision system. This system obtains counting rates of people moving through the counting area, distinguishing between input and output. To achieve this aim is required two basic steps: detection and tracking. The detection step is based on correlation through a pre-processed image with various circular patterns in order to search people's heads, filtering these detections by stereovision depending on the height. The people tracking is carried out through a multiple hypothesis algorithm based on the Kalman filter. Finally, people counting is done according to the trajectory followed by the person. To validate the algorithm have been used several real videos taken from different transit areas inside buildings, reaching rates ranging between 87% and 98% accuracy depending on the number of people crossing the counting zone simultaneously. In these videos occur several adverse situations, such as occlusions, people in groups in different directions, lighting changes, etc.

A Multiple Hypothesis Approach to Satellite Navigation Integrity

A general methodology has been developed for failure mitigation in satellite-based navigation systems. This new approach is founded on the direct evaluation of integrity risk under the unified consideration of all single-element failure hypotheses and the no-failure hypothesis. It is applicable to fault-tolerant estimation and integrity monitoring. In particular, the algorithm has been investigated for application as an airborne element of the Local Area Augmentation System (LAAS) integrity monitoring architecture. In this system, GPS ranging measurements from multiple ground-based reference receivers are to be used to mitigate the effects of reference receiver failures. The multiple hypothesis algorithm has been evaluated through analysis and simulation and has been shown to provide the tightest realizable protection limits for LAAS. The operational performance of the new algorithm has been compared with that of the approach currently under consideration by RTCA Special Committee-159. The performance of the multiple hypothesis algorithm has been demonstrated using experimental data collected during a series of LAAS prototype flight tests in a Beechcraft King Air.