Pedestrian detection: A benchmark
Piotr Dollár, Christian Wojek, Bernt Schiele et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2009
Pedestrian detection is a key problem in computer vision, with several applications including robotics, surveillance and automotive safety. Much of the progress of the past few years has been driven by the availability of challenging public datasets. To continue the rapid rate of innovation, we introduce the Caltech Pedestrian Dataset, which is two orders of magnitude larger than existing datasets. The dataset contains richly annotated video, recorded from a moving vehicle, with challenging images of low resolution and frequently occluded people. We propose improved evaluation metrics, demonstrating that commonly used per-window measures are flawed and can fail to predict performance on full images. We also benchmark several promising detection systems, providing an overview of state-of-the-art performance and a direct, unbiased comparison of existing methods. Finally, by analyzing common failure cases, we help identify future research directions for the field.
Cited by 1,313 works. doi:10.1109/cvpr.2009.5206631
Authors
References
- Histograms of Oriented Gradients for Human Detection
- Robust Real-Time Face Detection
- LabelMe: A Database and Web-Based Tool for Image Annotation
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
- A discriminatively trained, multiscale, deformable part model
- One-shot learning of object categories
- Performance of optical flow techniques
- A Trainable System for Object Detection
- Detecting Pedestrians Using Patterns of Motion and Appearance
- Real-time object detection for "smart" vehicles