Skip to main navigation Skip to search Skip to main content

Object detection based on multiscale merged feature map

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In object detection, high quality feature map is of great importance for both object location and classification. This paper presents a new network architecture to get higher quality feature map, which combines the feature map from shallow convolution layers with deep convolution layers by up–sampling and concatenating. It adopts a one-stage network, which does not rely on region proposal, to directly predict the location and classification of objects using the high quality feature map. With the input images of size 300 * 300, this network can be trained efficiently to achieve solid results on well-known object detection benchmarks: 77.7% on VOC2007, outperforming a comparable state of the art SSD [1], YOLO [5] and Faster R-CNN [4] model.

Original languageEnglish
Title of host publicationImage and Graphics Technologies and Applications - 13th Conference on Image and Graphics Technologies and Applications, IGTA 2018, Revised Selected Papers
EditorsYongtian Wang, Yuxin Peng, Zhiguo Jiang
PublisherSpringer Verlag
Pages80-87
Number of pages8
ISBN (Print)9789811317019
DOIs
StatePublished - 2018
Event13th Conference on Image and Graphics Technologies and Applications, IGTA 2018 - Beijing, China
Duration: 8 Apr 201810 Apr 2018

Publication series

NameCommunications in Computer and Information Science
Volume875
ISSN (Print)1865-0929

Conference

Conference13th Conference on Image and Graphics Technologies and Applications, IGTA 2018
Country/TerritoryChina
CityBeijing
Period8/04/1810/04/18

Keywords

  • Concatenating
  • Feature map
  • Object detection
  • Up-sampling

Fingerprint

Dive into the research topics of 'Object detection based on multiscale merged feature map'. Together they form a unique fingerprint.

Cite this