High-level Semantic Feature Detection:A New Perspective for Pedestrian Detection

04/05/2019
by   Wei Liu, et al.
0

Object detection generally requires sliding-window classifiers in tradition or anchor-based predictions in modern deep learning approaches. However, either of these approaches requires tedious configurations in windows or anchors. In this paper, taking pedestrian detection as an example, we provide a new perspective where detecting objects is motivated as a high-level semantic feature detection task. Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited. However, unlike these traditional low-level features, the proposed detector goes for a higher-level abstraction, that is, we are looking for central points where there are pedestrians, and modern deep models are already capable of such a high-level semantic abstraction. Besides, like blob detection, we also predict the scales of the pedestrian points, which is also a straightforward convolution. Therefore, in this paper, pedestrian detection is simplified as a straightforward center and scale prediction task through convolutions. This way, the proposed method enjoys an anchor-free setting. Though structurally simple, it presents competitive accuracy and good speed on challenging pedestrian detection benchmarks, and hence leading to a new attractive pedestrian detector. Code and models will be available at <https://github.com/liuwei16/CSP>.

READ FULL TEXT
research
02/04/2019

Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge

The main essence of this paper is to investigate the performance of Reti...
research
01/10/2022

Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond

Pedestrian detection is the cornerstone of many vision based application...
research
08/19/2020

Anchor-free Small-scale Multispectral Pedestrian Detection

Multispectral images consisting of aligned visual-optical (VIS) and ther...
research
02/20/2020

Adapted Center and Scale Prediction: More Stable and More Accurate

Pedestrian detection benefits from deep learning technology and gains ra...
research
11/29/2014

Pedestrian Detection aided by Deep Learning Semantic Tasks

Deep learning methods have achieved great success in pedestrian detectio...
research
03/22/2021

Anchor-Free Person Search

Person search aims to simultaneously localize and identify a query perso...
research
07/14/2014

Spatiotemporal Stacked Sequential Learning for Pedestrian Detection

Pedestrian classifiers decide which image windows contain a pedestrian. ...

Please sign up or login with your details

Forgot password? Click here to reset