Share Email Print

Proceedings Paper

Multitask assessment of roads and vehicles network (MARVN)
Author(s): Fang Yang; Meng Yi; Yiran Cai; Erik Blasch; Nichole Sullivan; Carolyn Sheaff; Genshe Chen; Haibin Ling
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Vehicle detection in wide area motion imagery (WAMI) has drawn increasing attention from the computer vision research community in recent decades. In this paper, we present a new architecture for vehicle detection on road using multi-task network, which is able to detect and segment vehicles, estimate their pose, and meanwhile yield road isolation for a given region. The multi-task network consists of three components: 1) vehicle detection, 2) vehicle and road segmentation, and 3) detection screening. Segmentation and detection components share the same backbone network and are trained jointly in an end-to-end way. Unlike background subtraction or frame differencing based methods, the proposed Multitask Assessment of Roads and Vehicles Network (MARVN) method can detect vehicles which are slowing down, stopped, and/or partially occluded in a single image. In addition, the method can eliminate the detections which are located at outside road using yielded road segmentation so as to decrease the false positive rate. As few WAMI datasets have road mask and vehicles bounding box anotations, we extract 512 frames from WPAFB 2009 dataset and carefully refine the original annotations. The resulting dataset is thus named as WAMI512. We extensively compare the proposed method with state-of-the-art methods on WAMI512 dataset, and demonstrate superior performance in terms of efficiency and accuracy.

Paper Details

Date Published: 2 May 2018
PDF: 13 pages
Proc. SPIE 10641, Sensors and Systems for Space Applications XI, 106410D (2 May 2018); doi: 10.1117/12.2305972
Show Author Affiliations
Fang Yang, Temple Univ. (United States)
Meng Yi, Temple Univ. (United States)
Yiran Cai, Temple Univ. (United States)
Erik Blasch, Air Force Research Lab. (United States)
Nichole Sullivan, Intelligent Fusion Technology, Inc. (United States)
Carolyn Sheaff, Air Force Research Lab. (United States)
Genshe Chen, Intelligent Fusion Technology, Inc. (United States)
Haibin Ling, Temple Univ. (United States)

Published in SPIE Proceedings Vol. 10641:
Sensors and Systems for Space Applications XI
Khanh D. Pham; Genshe Chen, Editor(s)

© SPIE. Terms of Use
Back to Top