Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection

Abstract

We propose a deep neural network fusion architecture for fast and robust pedestrian detection. The proposed network fusion architecture allows for parallel processing of multiple networks for speed. A single shot deep convolutional network is trained as a object detector to generate all possible pedestrian candidates of different sizes and occlusions. This network outputs a large variety of pedestrian candidates to cover the majority of ground-truth pedestrians while also introducing a large number of false positives. Next, multiple deep neural networks are used in parallel for further refinement of these pedestrian candidates. We introduce a soft-rejection based network fusion method to fuse the soft metrics from all networks together to generate the final confidence scores. Our method performs better than existing state-of-the-arts, especially when detecting small-size and occluded pedestrians. Furthermore, we propose a method for integrating pixel-wise semantic segmentation network into the network fusion architecture as a reinforcement to the pedestrian detector. The approach outperforms state-of-the-art methods on most protocols on Caltech Pedestrian dataset, with significant boosts on several protocols. It is also faster than all other methods.

WACV 2017

References in corpus (6)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Ten Years of Pedestrian Detection, What Have We Learned?
• Taking a Deeper Look at Pedestrians
• Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling

Cited by in corpus (5)

• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• PCN: Part and Context Information for Pedestrian Detection with CNNs
• An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles
• Pedestrian Detection with Autoregressive Network Phases
• Feature Analysis and Selection for Training an End-to-End Autonomous Vehicle Controller Using the Deep Learning Approach