Feature extraction for moving objects tracking system in indoor environments

Castro, D.; Nunes, U.; Ruano, Antonio

http://hdl.handle.net/10400.1/2261

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
IAV04_329.pdf		171.29 KB	Adobe PDF	Download

Send Feedback

Authors

Castro, D.

Nunes, U.

Ruano, Antonio

Abstract(s)

In this paper a feature extraction and classification methodology for a laser based detection and tracking of moving objects (DATMO) system in indoors environments is presented. The sensory perception is based in a SICK Laser Measurement System (LMS). An adaptation of the Hough Transform is used in the feature extraction procedure to interpret scanned segments, as primitive features, defined by geometric evidence (points, lines, circles and blobs), and high-level features, generally referred to as landmarks (corners, columns, doors, etc.). The classification system uses features data, some heuristic rules, and data from a Kalman filter based tracking system to classify multiple objects. Real and simulated results are presented to verify the effectiveness of the proposed DATMO system in unknown environments with multiple moving objects.

Keywords

Autonomous mobile robots Detection algorithms

URI

http://hdl.handle.net/10400.1/2261

Citation

Castro, D.; Nunes, U.; Ruano, A. E. Feature Extraction for Moving Objects Tracking System in Indoor Environments, Trabalho apresentado em 5th IFAC Symposium on Intelligent Autonomous Vehicles, In 5th IFAC Symposium on Intelligent Autonomous Vehicles, Lisbon, 2004.