A One-and-Half Stage Pedestrian Detector

Ujjwal Ujjwal (1, 2, 3) , Aziz Dziri (3) , Bertrand Leroy (3) , Francois F Bremond (1, 2)

1 STARS - Spatio-Temporal Activity Recognition Systems
2 COMUE UCA - COMUE Université Côte d'Azur (2015-2019)
3 VeDeCom - VEhicule DEcarboné et COmmuniquant et sa Mobilité

Pedestrian detection is a specific instance of the more general problem of object detection in computer vision. A balance between detection accuracy and speed is a desirable trait for pedestrian detection systems in many applications such as self-driving cars. In this paper, we follow the wisdom of " and less is often more" to achieve this balance. We propose a lightweight mechanism based on semantic segmentation to reduce the number of anchors to be processed. We furthermore unify this selection with the intra-anchor feature pooling strategy adopted in high performance two-stage detectors such as Faster-RCNN. Such a strategy is avoided in one-stage detectors like SSD in favour of faster inference but at the cost of reducing the accuracy vis-à-vis two-stage detectors. However our anchor selection renders it practical to use feature pooling without giving up the inference speed. Our proposed approach succeeds in detecting pedestrians with state-of-art performance on caltech-reasonable and ciypersons datasets with inference speeds of ∼ 32 fps.

Domaines: Intelligence artificielle [cs.AI]

Ujjwal Ujjwal, Aziz Dziri, Bertrand Leroy, Francois F Bremond. A One-and-Half Stage Pedestrian Detector. WACV 2020 - IEEE Winter Conference on Applications of Computer Vision, Mar 2020, Snowmass Village, United States. ⟨hal-02363756⟩