Detecting and tracking moving humans from a moving vehicle

Bodt, Barry A.; Camden, Richard

doi:10.1117/12.781864

Cited by 2 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously [3], correspondence was determined solely based on spatial constraints. One such constraint is the distance between the ground-truth and the detection data.…”

Section: Establish Object/human Correspondences Between Ground Truth mentioning

confidence: 99%

Performance measurements for evaluating static and dynamic multiple human detection and tracking systems in unstructured environments

Bodt

Camden

Scott

et al. 2009

Proceedings of the 9th Workshop on Performance Metrics for Intelligent Systems

Self Cite

View full text Add to dashboard Cite

The Army Research Laboratory (ARL) Robotics Collaborative Technology Alliance (CTA) conducted an assessment and evaluation of multiple algorithms for real-time detection of pedestrians in Laser Detection and Ranging (LADAR) and video sensor data taken from a moving platform. The algorithms were developed by Robotics CTA members and then assessed in field experiments jointly conducted by the National Institute of Standards and Technology (NIST) and ARL. A robust, accurate and independent pedestrian tracking system was developed to provide ground truth. The ground truth was used to evaluate the CTA member algorithms for uncertainty and error in their results. A real-time display system was used to provide early detection of errors in data collection.

show abstract

“…Previously [3], correspondence was determined solely based on spatial constraints. One such constraint is the distance between the ground-truth and the detection data.…”

Section: Establish Object/human Correspondences Between Ground Truth mentioning

confidence: 99%

Performance measurements for evaluating static and dynamic multiple human detection and tracking systems in unstructured environments

Bodt

Camden

Scott

et al. 2009

Proceedings of the 9th Workshop on Performance Metrics for Intelligent Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…All of the systems discussed above were evaluated in the FY2007 experiment, which was on a flat road about 250 m long with 10 moving pedestrians, four stationary mannequins, and assorted moving and stationary clutter objects1 overall the scene was relatively uncluttered. For the FY2007 experiment, the course was run 32 times to generate performance statistics for LIDAR and stereo vision-based systems1 results are discussed by Bodt (2008). The median distance to first detection of people and mannequins varied from about 25 to 45 m for LIDAR-based systems and 25 to 32 m for stereo visionbased systems.…”

Section: Robotic Vehiclesmentioning

confidence: 99%

“…In addition to testing on ground-truthed datasets, the endto-end system has been integrated into several systems for Bodt (2008). The system described here has been integrated onboard the test vehicle for an upcoming test, for which results will be published in the future.…”

Section: Semi-urban Datasetsmentioning

confidence: 99%

A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle

Bajracharya

Moghaddam

Howard

et al. 2009

The International Journal of Robotics Research

View full text Add to dashboard Cite

In this paper we describe a fully integrated system for detecting, localizing, and tracking pedestrians from a moving vehicle. The system can reliably detect upright pedestrians to a range of 40 m in lightly cluttered urban environments. The system uses range data from stereo vision to segment the scene into regions of interest, from which shape features are extracted and used to classify pedestrians. The regions are tracked using shape and appearance features. Tracking is used to temporally filter classifications to improve performance and to estimate the velocity of pedestrians for use in path planning. The end-to-end system runs at 5 Hz on 1 ,024 × 768 imagery using a standard 2.4 GHz Intel Core 2 Quad processor, and has been integrated and tested on multiple ground vehicles and environments. We show performance on a diverse set of datasets with groundtruth in outdoor environments with varying degrees of pedestrian density and clutter. In highly cluttered urban environments, the detection rates are on a par with state-of-the-art but significantly slower systems.

show abstract

Detecting and tracking moving humans from a moving vehicle

Cited by 2 publications

References 1 publication

Performance measurements for evaluating static and dynamic multiple human detection and tracking systems in unstructured environments

Performance measurements for evaluating static and dynamic multiple human detection and tracking systems in unstructured environments

A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle

Contact Info

Product

Resources

About