Context-aware CNNs for person head detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Context-aware CNNs for person head detection

Résumé

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.

Dates et versions

hal-01237618 , version 1 (03-12-2015)

Identifiants

Citer

Tuan-Hung Vu, Anton Osokin, Ivan Laptev. Context-aware CNNs for person head detection. ICCV 2015 - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. ⟨hal-01237618⟩
126 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More