Long-Range Pedestrian Detection Using Stereo and a Cascade of Convolutional Network Classifiers

Citation

Kira, Z.; Hadsell, R.; Salgian, G.; Samarasekera, S., “Long-Range Pedestrian Detection using stereo and a cascade of convolutional network classifiers,” Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, vol., no., pp.2396,2403, 7-12 Oct. 2012

Abstract

In this paper, we present a system for detecting pedestrians at long ranges using a combination of stereo-based detection, classification using deep learning, and a cascade of specialized classifiers that can reduce false positives and computational load. Specifically, we use stereo to perform detection of vertical structures which are further filtered based on edge responses. A convolutional neural network was then designed to support the classification of pedestrians using both appearance and stereo disparity-based features. A second convolutional network classifier was trained specifically for the case of long-range detections using appearance only. We further speed up the classifier using a cascade approach and multi-threading. The system was deployed on two robots, one using a high resolution stereo pair with 180 degree fisheye lenses and the other using 80 degree FOV lenses. Results are demonstrated on a large dataset captured in a variety of environments.


Read more from SRI

  • The US Capitol Dome

    Quantum on Capitol Hill

    The SRI-managed Quantum Economic Development Consortium convened quantum innovators and members of Congress to explore the future of quantum technology.

  • Rays of light

    Building the photonic circuits of the future

    SRI’s work on DARPA’s HAPPI program seeks to measurably advance the capability of circuits that transmit information using light rather than electrons.

  • Turning AI into a problem-solving teammate

    To chart the future of human-machine teaming, SRI’s COLLEAGUE project is building an AI-based system designed to act as a true collaborative partner.