Skip to Main content Skip to Navigation
Conference papers

A One-and-Half Stage Pedestrian Detector

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download
Contributor : Ujjwal Ujjwal <>
Submitted on : Thursday, November 14, 2019 - 3:35:46 PM
Last modification on : Monday, October 12, 2020 - 10:28:59 AM
Long-term archiving on: : Saturday, February 15, 2020 - 4:10:12 PM


Files produced by the author(s)


  • HAL Id : hal-02363756, version 1



Ujjwal Ujjwal, Aziz Dziri, Bertrand Leroy, Francois 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⟩



Record views


Files downloads