ML p(r)ior | How Far are We from Solving Pedestrian Detection?

How Far are We from Solving Pedestrian Detection?

2016-02-03
Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the "perfect single frame detector". We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech dataset), and by manually clustering the recurrent errors of a top detector. Our results characterize both localization and background-versus-foreground errors. To address localization errors we study the impact of training annotation noise on the detector performance, and show that we can improve even with a small portion of sanitized training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech dataset, and provide a new sanitized set of training and test annotations.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2013-11-11

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the … show more
PDF

Highlights - Most important sentences from the article

2017-12-03
1712.00726 | cs.CV

In object detection, an intersection over union (IoU) threshold is required to define positives and … show more
PDF

Highlights - Most important sentences from the article

2013-05-20

We describe a method for visual object detection based on an ensemble of optimized decision trees or… show more
PDF

Highlights - Most important sentences from the article

2018-03-19

Recent region-based object detectors are usually built with separate classification and localization… show more
PDF

Highlights - Most important sentences from the article

2018-10-05

In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard fal… show more
PDF

Highlights - Most important sentences from the article

2015-11-24
1511.07917 | cs.CV

Person detection is a key problem for many computer vision tasks. While face detection has reached m… show more
PDF

Highlights - Most important sentences from the article

2018-06-18

We study the robustness of object detection under the presence of missing annotations. In this setti… show more
PDF

Highlights - Most important sentences from the article

2015-02-10

In this paper we consider the problem of multi-view face detection. While there has been significant… show more
PDF

Highlights - Most important sentences from the article

2019-04-16
1904.07934 | cs.CV

We tackle the problem of semantic boundary prediction, which aims to identify pixels that belong to … show more
PDF

Highlights - Most important sentences from the article

2016-03-02

Standardized benchmarks are crucial for the majority of computer vision applications. Although leade… show more
PDF

Highlights - Most important sentences from the article

2017-04-10

Standardized benchmarks are crucial for the majority of computer vision applications. Although leade… show more
PDF

Highlights - Most important sentences from the article

2018-03-14

In this paper, we introduce the Face Magnifier Network (Face-MageNet), a face detector based on the … show more
PDF

Highlights - Most important sentences from the article

2017-11-21

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians ofte… show more
PDF

Highlights - Most important sentences from the article

2017-04-08

This paper presents a novel method for detecting pedestrians under adverse illumination conditions. … show more
PDF

Highlights - Most important sentences from the article

2018-08-14

Multispectral pedestrian detection has attracted increasing attention from the research community du… show more
PDF

Highlights - Most important sentences from the article