Pushing the Limits of Deep CNNs for Pedestrian Detection

Abstract

Compared to other applications in computer vision, convolutional neural networks have under-performed on pedestrian detection. A breakthrough was made very recently by using sophisticated deep CNN models, with a number of hand-crafted features, or explicit occlusion handling mechanism. In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labelling may be simply combined with a detector to boost the detection performance. By adding complementary hand-crafted features such as optical flow, the DCNN based detector can be further improved. We set a new record on the Caltech pedestrian dataset, lowering the log-average miss rate from $11.7\%$ to $8.9\%$, a relative improvement of $24\%$. We also achieve a comparable result to the state-of-the-art approaches on the KITTI dataset.

arXiv commentFixed some typos

References in corpus (8)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Conditional Random Fields as Recurrent Neural Networks
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Discriminatively Trained And-Or Graph Models for Object Shape Detection
• Efficient piecewise training of deep structured models for semantic segmentation
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Object Detection Networks on Convolutional Feature Maps

Cited by in corpus (2)

• CityPersons: A Diverse Dataset for Pedestrian Detection
• Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection