Conference Paper

Detecting Pedestrians by Learning Shapelet Features.

DOI: 10.1109/CVPR.2007.383134 Conference: 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 18-23 June 2007, Minneapolis, Minnesota, USA
Source: DBLP

ABSTRACT In this paper, we address the problem of detecting pedes- trians in still images. We introduce an algorithm for learn- ing shapelet features, a set of mid-level features. These fea- tures are focused on local regions of the image and are built from low-level gradient information that discriminates be- tween pedestrian and non-pedestrian classes. Using Ad- aBoost, these shapelet features are created as a combina- tion of oriented gradient responses. To train the final classi- fier, we use AdaBoost for a second time to select a subset of our learned shapelets. By first focusing locally on smaller feature sets, our algorithm attempts to harvest more use- ful information than by examining all the low-level features together. We present quantitative results demonstrating the effectiveness of our algorithm. In particular, we obtain an error rate 14 percentage points lower (at10−6 FPPW) than the previous state of the art detector of Dalal and Triggs (1) on the INRIA dataset.

  • Source
    Multimedia and Expo (ICME), 2014 IEEE International Conference on, Chen Du, China; 07/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Human detection of the infrared spectrum of the image is a very relevant area of research that potentially impacts the design of surveillance systems. There are many suggestions in the literature, but they do not have a comparative. Therefore, first and foremost in this paper we propose a common framework in which we have adapted it with a different approach, and secondly, we use this framework to provide a comparative point of view that can lead to what the details of different approaches, it is also the main challenges to be solved in the future. In summary, we expect this review useful for new and experienced researchers in this field. The first aim, as a describe overview state of the art, and second, as a way to introduce the trend and draw from this comparative study.
    International Journal Of Interactive Digital Media. 12/2013; 1(3):13-20.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an omnidirectional vision based solution to detect human beings. We first go through the conventional sliding window approaches for human detection. Then, we describe how the feature extraction step of the conventional approaches should be modified for a theoretically correct and effective use in omnidirectional cameras. In this way we perform human detection directly on the omnidirectional images without converting them to panoramic or perspective image. Our experiments, both with synthetic and real images show that the proposed approach produces successful results.
    Signal Processing and Communications Applications Conference (SIU), 2014; 04/2014


1 Download
Available from