Vehicle Detection in High-Resolution Aerial Images with Parallel RPN and Density-Assigner
-
Published:2023-03-19
Issue:6
Volume:15
Page:1659
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Kong Xianghui1, Zhang Yan1, Tu Shangtan2, Xu Chang1ORCID, Yang Wen1ORCID
Affiliation:
1. School of Electronic Information, Wuhan University, Wuhan 430072, China 2. Shanghai Institute of Satellite Engineering, Shanghai 201109, China
Abstract
Vehicle detection in aerial images plays a significant role in many remote sensing applications such as city planning, road construction, and traffic control. However, detecting vehicles in aerial images remains challenging due to the existence of tiny objects, the scale variance within the same type of vehicle objects, and dense arrangement in some scenarios, such as parking lots. At present, many state-of-the-art object detectors cannot generate satisfactory results on vehicle detection in aerial images. The receptive field of the current detector is not fine enough to handle the slight scale variance. Moreover, the densely arranged vehicles will introduce ambiguous positive samples in label assignment and false predictions that cannot be deleted by NMS. To this end, we propose a two-stage framework for vehicle detection that better leverages the prior attribution knowledge of vehicles in aerial images. First of all, we design a Parallel RPN that exploits convolutional layers of different receptive fields to alleviate the scale variation problem. To tackle the densely arranged vehicles, we introduce a density-based sample assigner in the vehicle-intensive areas to reduce low-quality and occluded positive samples in the training process. In addition, a scale-based NMS is proposed to filter out redundant proposals hierarchically from different levels of the feature pyramid. Moreover, we construct two challenging vehicle detection datasets based on the AI-TOD and xView datasets which contain many tiny objects. Extensive experiments on these two datasets demonstrate the effectiveness of our proposed method.
Funder
CETC key laboratory of aerospace information applications
Subject
General Earth and Planetary Sciences
Reference47 articles.
1. Liao, W., Chen, X., Yang, J.F., Roth, S., Goesele, M., Yang, M.Y., and Rosenhahn, B. (September, January 31). LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery. Proceedings of the ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, Nice, France. 2. Ferreira de Carvalho, O.L., Abílio de Carvalho, O., Olino de Albuquerque, A., Castro Santana, N., Leandro Borges, D., Trancoso Gomes, R., and Fontes Guimarães, R. (2021). Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset. arXiv. 3. Hsieh, M.R., Lin, Y.L., and Hsu, W.H. (2017, January 22–29). Drone-Based Object Counting by Spatially Regularized Regional Proposal Network. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy. 4. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks;Ren;IEEE Trans. Pattern Anal. Mach. Intell.,2017 5. Cai, Z., and Vasconcelos, N. (2018, January 18–22). Cascade R-CNN: Delving Into High Quality Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|