Integrating Multiple Inferences for Vehicle Detection by Focusing on Challenging Test Sets

Jong Taek Lee, Jang Woon Baek, Kiyoung Moon, Kil Taek Lim

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

1 Scopus citations

Abstract

Due to recent advances in object detection with the help of deep convolutional neural networks and region proposal methods, object detection systems have become practical in numerous fields with high accuracy. This paper presents a method for vehicle detection in videos for automatic traffic monitoring. Compared to general object detection datasets such as the PascalVOC and MS-COCO, traffic surveillance datasets such as the UA-DETRAC dataset have different challenging issues: high variation of object size, severe occlusion, dissimilarity between training set and test set. To overcome these difficulties, we employ an unsupervised integration of multiple instances of an image by analyzing video sequences. We applied Faster R-CNN with Neural Architecture Search (NAS) framework as a base network. We achieved 85.76% mAP on the UA-DETRAC detection test set, and outperformed the winner method of the AVSS 2017 challenge on Advanced Traffic Monitoring by 9.19%.

Original languageEnglish
Title of host publicationProceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538692943
DOIs
StatePublished - 2 Jul 2018
Event15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018 - Auckland, New Zealand
Duration: 27 Nov 201830 Nov 2018

Publication series

NameProceedings of AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance

Conference

Conference15th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2018
Country/TerritoryNew Zealand
CityAuckland
Period27/11/1830/11/18

Fingerprint

Dive into the research topics of 'Integrating Multiple Inferences for Vehicle Detection by Focusing on Challenging Test Sets'. Together they form a unique fingerprint.

Cite this