Pedestrian Detection with Unsupervised Multi-Stage Feature Learning

2012/12/01 by Pierre Sermanet, Sermanet, Pierre, Koray Kavukcuoglu +5 · 7 citations
Computer Science · Engineering · #Video Surveillance and Tracking Methods #Advanced Neural Network Applications #Gait Recognition and Analysis

paper · pdf · doi:10.48550/arxiv.1212.0142

Abstract

Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.

Cited by

• Fully Convolutional Networks for Semantic Segmentation
• PixelNN: Example-based Image Synthesis
• Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles
• Perceptual Generative Adversarial Networks for Small Object Detection
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and\n Recurrent Neural Networks
• Contour Detection Using Cost-Sensitive Convolutional Neural Networks
• Efficient Chambolle-Pock based algorithms for Convoltional sparse representation

Related

• Pushing the Limits of Deep CNNs for Pedestrian Detection
• Taking a Deeper Look at Pedestrians
• Pedestrian Detection aided by Deep Learning Semantic Tasks
• Fused Deep Neural Networks for Efficient Pedestrian Detection
• Boosting-like Deep Learning For Pedestrian Detection