In this paper we describe a fully integrated system for detecting and tracking pedestrians in a dynamic urban environment. The system can reliably detect and track pedestrians to a range of 100 m in highly cluttered environments. The system uses a highly accurate 3D LIDAR from Velodyne to segment the scene into regions of interest or blobs, from which the pedestrians are determined. The pedestrians are then tracked using probabil ity hypothesis density (PHD) filter which is based on random finite set theoretic framework. In contrast to classical approaches, this random finite set framework does not require any explicit data associations. The PHD filter is implemented using a Gaussian Mixture technique. Experimental results obtained in dynamic urban settings demonstrate the efficacy and tracking performance of the proposed approach.
The solution to the problem of mapping an environment and at the same time using this map to localize (the simultaneous localization and mapping, SLAM, problem) is a key prerequisite in the synthesis of truly autonomous vehicles. By far the most common formulation of the SLAM problem is founded on a vector based stochastic framework, where the sensor models and the vehicle models are represented in state-space form and the joint posterior or its statistics are obtained based on recursive Bayesian estimation. All of these SLAM solutions leading from the stochastic vector state-space approach require that we solve certain parallel problems in each recursion. These include effective solutions to the problems of data association, feature extraction, clutter filtering, and landmark or map management. In this paper, we propose an alternative framework based on finite set statistics (FISST), where the SLAM problem is reformulated so that the landmark map and the measurements are represented using random finite sets and the landmark map is jointly estimated with the vehicle state vector, whilst explicitly accounting for measurement detection uncertainty, data-association uncertainty, false alarms and map management in the SLAM filter framework. Similar to FastSLAM, the proposed formulation is based on a factorization of the full SLAM posterior into a product of the vehicle trajectory posterior and the landmark map posterior conditioned on the vehicle trajectory. The vehicle trajectory posterior is then estimated using a particle filter and the map posterior conditioned on the vehicle trajectory via a sequential Monte Carlo (SMC) implementation of the probability hypothesis density (PHD) filter. Simulation results of the proposed algorithm are presented and benchmarked against FastSLAM to demonstrate the effectiveness and improved performance of the FISST-SLAM in the presence of significant clutter.
Absrracr-Asonar detection scheme is presented here using Constant False Alarm Rate (CFAR) techniques. The proposed system has the following advantage. The technique yields unbiased estimates under a non-homogenous underwater environment, because the false alarm rate is maintained at a constant level while lbe threshold changes with difierent underwater environments In presence of interfering targets. A mathematical analysis is also being done for difierent CFAR processors with the interesl on the CFAR losses. In this paper, average decision threshold (ADT) is used as a measure.Index Te-CFAR, Sonar target detection scheme LINTRODUCTION An acoustic communication system, particularly one functioning in an environment with an autonomous underwater vehicle (AW), must contend with a number of man-made interference sources in addition to the more familiar ambient noise sources such as Biological noise etc. Thruster and aCNator noise often contains tonal components and therefore introduces narrow band interference to a communications receiver on board the vehicle 171. In active sonar systems, detection is the process of deciding if a target echo is present in a return. This is often accomplished by an operator who examines the sonar receiver output and decides if any portion of it is larger than the expected response due to reverberation. If so, then a target is declared to be present at the range and bearing associated with the peak in the receiver output. A typical sonar return is as shown in Fig. 1. As the receiver possesses a fixed range resolution, its output can be divided into cells of equal width in range as shown in Fig. 2.Detection may also be accomplished automatically using a processor that sets a threshold based on a sampling of the receiver output without an operator in the loop. Commonly, such processors are designed to maintain a constant probability of false alarm per display resolution cell, which is usually between IO4 to IO" and the detection probability for a single scan of the target must be on the order of 0.5 to 0.9 at maximum range [3]. Such processors use samples of the receiver output to implicitly estimate the parameters of its statistical model and appropriately set a detection threshold. The class of processors used to accomplish automatic detection is referred to as Constant False Alarm Rate (CFAR) detection processors which set the threshold adaptively based on local information of the noise power. CFAR processors are useful for detecting targets in background for 0-7803-8541 -1/04/$20.00 02004 IEEE which all parameters in the statistical distribution are not known and may be non stationary. The signal r e h " from targets are usually buried in noise and clutter, which refers to any undesired signal echo that is reflected back to the receiver. Since the clutter-plus-noise power is not known at any given location, a fixed threshold detection scheme cannot be applied to the sonar returns in individual range cells if the false alarm rate is to be controlled.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.