Taking a Deeper Look at Pedestrians

Abstract

In this paper we study the use of convolutional neural networks (convnets) for the task of pedestrian detection. Despite their recent diverse successes, convnets historically underperform compared to other pedestrian detectors. We deliberately omit explicitly modelling the problem into the network (e.g. parts or occlusion modelling) and show that we can reach competitive performance without bells and whistles. In a wide range of experiments we analyse small and big convnets, their architectural choices, parameters, and the influence of different training data, including pre-training on surrogate tasks. We present the best convnet detectors on the Caltech and KITTI dataset. On Caltech our convnets reach top performance both for the Caltech1x and Caltech10x training setup. Using additional data at training time our strongest convnet model is competitive even to detectors that use additional data (optical flow) at test time.

Cited by in corpus (23)

• Scale-aware Fast R-CNN for Pedestrian Detection
• Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
• How Far are We from Solving Pedestrian Detection?
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Multispectral Deep Neural Networks for Pedestrian Detection
• Learning Cross-Modal Deep Representations for Robust Pedestrian Detection
• Repulsion Loss: Detecting Pedestrians in a Crowd
• Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
• Grid Loss: Detecting Occluded Faces
• PCN: Part and Context Information for Pedestrian Detection with CNNs
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
• Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset
• Is Faster R-CNN Doing Well for Pedestrian Detection?
• Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
• Deep Multi-camera People Detection
• $\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
• Real-Time Resource Allocation for Tracking Systems
• Convolutional Channel Features
• Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
• Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection