Browsing by Author "Jiang, Pingge"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    An Extreme Learning Machine-based Pedestrian Detection Method
    (Office of the Vice Chancellor for Research, 2013-04-05) Yang, Kai; Du, Eliza Y.; Delp, Edward J.; Jiang, Pingge; Jiang, Feng; Chen, Yaobin; Sherony, Rini; Takahashi, Hiroyuki
    Pedestrian detection is a challenging task due to the high variance of pedestrians and fast changing background, especially for a single in-car camera system. Traditional HOG+SVM methods have two challenges: (1) false positives and (2) processing speed. In this paper, a new pedestrian detection method using multimodal HOG for pedestrian feature extraction and kernel based Extreme Learning Machine (ELM) for classification is presented. The experimental results using our naturalistic driving dataset show that the proposed method outperforms the traditional HOG+SVM method in both recognition accuracy and processing speed.
  • Thumbnail Image
    Item
    A new approach for pedestrian tracking and status analysis
    (2013) Jiang, Pingge; Du, Yingzi, 1975-; King, Brian; Rizkalla, Maher E.
    Pedestrian and vehicle interaction analysis in a naturalistic driving environment can provide useful information for designing vehicle-pedestrian crash warning/mitigation systems. Many researchers have used crash data to understand and study pedestrian behaviors and interactions between vehicles and pedestrian during crash. However, crash data may not provide detailed pedestrian-vehicle interaction information for us. In this thesis, we designed an automatic pedestrian tracking and status analysis method to process and study pedestrian and vehicle interactions. The proposed pedestrian tracking and status analysis method includes pedestrian detection, pedestrian tracking and pedestrian status analysis modules. The main contributions of this thesis are: we designed a new pedestrian tracking method by learning the pedestrian appearance and also their motion pattern. We designed a pedestrian status estimation method by using our tracking results and thus helped estimate the possibility of collision. Our preliminary experiment results using naturalistic driving data showed promising results.