Feature extraction for moving objects tracking system in indoor environments

Castro, Daniel; Nunes, Urbano; Ruano, A. E.

doi:10.1016/s1474-6670(17)31957-2

Cited by 18 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, have been detected. Here, the algorithm adopts the distance clustering procedure presented in [7]. It is based in the computation of the distance between two consecutive scan points, calculated by:…”

Section: Moving Target Detectionmentioning

confidence: 99%

“…A Kalman filter (KF) is implemented to track the extracted targets. In a different trail of thought, the authors in [16], [7] develop a feature detection system for real-time identification of geometric shapes such as lines, circles and legs from laser data and apply a KF for tracking. A similar but more sophisticated method can be found in [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tracking multiple targets from a mobile robot platform using a laser range scanner

Kondaxakis¹,

Kasderidis²,

Trahanias³

2008

IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications

View full text Add to dashboard Cite

A major issue in the field of mobile robotics today is the detection and tracking of moving objects (DATMO) from a moving observer. In dynamic and highly populated environments, this problem presents a complex and computationally demanding task. It can be divided in subproblems such as robot's relative motion compensation, feature extraction, measurement clustering, data association and targets' state vector estimation. In this paper we present an innovative approach that addresses all these issues exploiting various probabilistic and deterministic techniques. The algorithm utilizes real laser-scanner data to dynamically extract moving objects from their background environment, using a time-fading grid map method, and tracks the identified targets employing a Joint Probabilistic Data Association with Interacting Multiple Model (JPDA-IMM) algorithm. The resulting technique presents a computationally efficient approach to already existing target-tracking research for real time application scenarios.

show abstract

Section: Moving Target Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Tracking multiple targets from a mobile robot platform using a laser range scanner

Kondaxakis¹,

Kasderidis²,

Trahanias³

2008

IET Seminar on Target Tracking and Data Fusion: Algorithms and Applications

View full text Add to dashboard Cite

show abstract

“…Available methods so far, approach the problem of detecting geometric features such as lines, circles, legs by manual design and threshold hand-tuning [9]. Moreover, the extracted features are compared to objects stored in a database to recognize targets [10]. Alternatively, a more adaptive approach can be found in [11] and [12] where the authors train, in off-line mode, the AdaBoost classifier to identify peoples' legs.…”

Section: Introductionmentioning

confidence: 99%

Learning moving objects in a multi-target tracking scenario for mobile robots that use laser range measurements

Kondaxakis

Baltzakis

Trahanias

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of real-time moving-object detection, classification and tracking in populated and dynamic environments. In this scenario, a mobile robot uses 2D laser range data to recognize, track and navigate moving targets. Most previous approaches either rely on pre-defined data features or off-line training of a classifier for specific data sets, thus eliminating the possibility to detect and track different-shaped moving objects. We propose a novel and adaptive technique where potential moving objects are classified and learned in real-time using a Fuzzy ART neural network algorithm. Experimental results indicate that our method can effectively distinguish and track moving targets in cluttered indoor environments, while at the same time learning their shape.

show abstract

“…where the weights are defined in (5). Thus, the SIS algorithm consists of a recursive propagation of the weights and particles as each measurement is received.…”

Section: Particle Filtersmentioning

confidence: 99%

“…This procedure gives us a way of extracting the points corresponding to some object in the range data. For this purpose a method presented in [5] is used. After the segmentation step a set of segments is obtained, which consists of a set of points that can be represented in the same form of occupancy grids.…”

Section: Segmentationmentioning

confidence: 99%