CityPersons: A Diverse Dataset for Pedestrian Detection

Abstract

Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Rich feature hierarchies for accurate object detection and semantic segmentation
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• Ten Years of Pedestrian Detection, What Have We Learned?
• How Far are We from Solving Pedestrian Detection?
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Filtered Channel Features for Pedestrian Detection
• Taking a Deeper Look at Pedestrians
• Amodal Instance Segmentation
• Pedestrian Detection aided by Deep Learning Semantic Tasks
• Pushing the Limits of Deep CNNs for Pedestrian Detection

Cited by in corpus (19)

• Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
• Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• Person Search via A Mask-Guided Two-Stream CNN Model
• Repulsion Loss: Detecting Pedestrians in a Crowd
• Driving Datasets Literature Review
• BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
• PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
• Vulnerable road user detection: state-of-the-art and open challenges
• Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Deep Person Detection in 2D Range Data
• A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle
• Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
• Detector-in-Detector: Multi-Level Analysis for Human-Parts
• Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection
• Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian
• GAIA: A Transfer Learning System of Object Detection that Fits Your Needs