Context-aware CNNs for person head detection

Abstract

Person detection is a key problem for many computer vision tasks. While face detection has reached maturity, detecting people under a full variation of camera view-points, human poses, lighting conditions and occlusions is still a difficult challenge. In this work we focus on detecting human heads in natural scenes. Starting from the recent local R-CNN object detector, we extend it with two types of contextual cues. First, we leverage person-scene relations and propose a Global CNN model trained to predict positions and scales of heads directly from the full image. Second, we explicitly model pairwise relations among objects and train a Pairwise CNN model using a structured-output surrogate loss. The Local, Global and Pairwise models are combined into a joint CNN framework. To train and test our full model, we introduce a large dataset composed of 369,846 human heads annotated in 224,740 movie frames. We evaluate our method and demonstrate improvements of person head detection against several recent baselines in three datasets. We also show improvements of the detection speed provided by our model.

To appear in International Conference on Computer Vision (ICCV), 2015

References in corpus (2)

• Deep Structured Output Learning for Unconstrained Text Recognition
• Context Forest for efficient object detection with large mixture models

Cited by in corpus (7)

• Context-aware Deep Feature Compression for High-speed Visual Tracking
• A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
• FCHD: Fast and accurate head detection in crowded scenes
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture
• Tube-CNN: Modeling temporal evolution of appearance for object detection in video
• Deep, Dense, and Low-Rank Gaussian Conditional Random Fields