The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLII-4
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4, 351–358, 2018
https://doi.org/10.5194/isprs-archives-XLII-4-351-2018
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4, 351–358, 2018
https://doi.org/10.5194/isprs-archives-XLII-4-351-2018

  19 Sep 2018

19 Sep 2018

ROBUST FEATURES FOR LEG DETECTION IN 2D LASER RANGE DATA

D. Li1, L. Li1,2, M. Zhou3,4, and X. Zuo1 D. Li et al.
  • 1School of Resource and Environment Sciences, Wuhan University, 129 Luoyu Road, Wuhan 430079, China
  • 2Collaborative Innovation Centre of Geospatial Technology, Wuhan University, 129 Luoyu Road, Wuhan 430079, China
  • 3College of Resources and Environmental Sciences, Hunan Normal University, Changsha, 410081, China
  • 4Key Laboratory of Geospatial Big Data Mining and Application, Hunan Province, Changsha, 410081 China

Keywords: Features, Laser range data, Leg detection, Adaboost, Classifier

Abstract. People detection in 2D laser range data is widely used in many application, such as robotics, smart cities or regions, and intelligent driving. For most current methods on people detection based on a single laser range finder are actually leg detectors as the sensor are always established below the knee height. Current state-of-the-art methods share similar steps including segmentation, feature extraction and a machine learning-based classification, but use different features which have good performance on their own experimental data. For researchers, it is important and desirable to know which features are more robust. In this paper, taking advantage of the fact that effective features can be selected by AdaBoost and assembled into a strong classifier, a set of features presented in state-of-the-art methods is combined with a set of features presented by us to train a leg detector by the AdaBoost algorithm. This detector is assembling by effective features and can classify segments into leg and non-leg. Three open source data sets including simple and complex scenarios are used for the experiments to test the features and extracted the important ones. To reduce the effect of segmentation on the final results, three segmentation methods are simultaneously used for experiments and analysis to ensure the reliability and credibility of our conclusion. Finally, 10 robust features for leg detection in 2D laser range data are presented based on the results.