Abstract
Nowadays, laser scanners are operated for data collection instead of video cameras. Laser scanners do not record real world videos except scanned points. Thus it takes away problems of private life conservation. Plus data processing gets very fast and easy. But from laser scanned data points, recognition of objects is a challenging task. This paper points to the usability of SVM to recognize pedestrians and vehicles from laser scanned data points. Data points from each scan are esteemed as a video frame. Moving blobs are extracted and then SVM is used to recognize each blob as either a pedestrian or a vehicle. Experimental results show that SVM can be actually and robustly used to recognize objects from laser scanned data points.