Scale-aware Fast R-CNN for Pedestrian Detection

Abstract

In this work, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intra-category variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in sub-networks which detect pedestrians with scales from disjoint ranges. Outputs from all the sub-networks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech, INRIA, and ETH, and obtains competitive results on KITTI.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Scale-Invariant Convolutional Neural Networks
• Ten Years of Pedestrian Detection, What Have We Learned?
• Filtered Channel Features for Pedestrian Detection
• Taking a Deeper Look at Pedestrians
• Learning Sampling Distributions for Efficient Object Detection
• Computational Baby Learning

Cited by in corpus (18)

• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• Deep Learning for Beamspace Channel Estimation in Millimeter-Wave Massive MIMO Systems
• Learning Multilayer Channel Features for Pedestrian Detection
• Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
• Object Detection with Deep Learning: A Review
• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• Multispectral Deep Neural Networks for Pedestrian Detection
• Dual Semantic Fusion Network for Video Object Detection
• Fused Deep Neural Networks for Efficient Pedestrian Detection
• Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
• Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
• Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection
• An Analysis of Scale Invariance in Object Detection - SNIP
• Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
• A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
• Pedestrian Detection with Autoregressive Network Phases
• Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge
• What Can Help Pedestrian Detection?