Filters








603 Hits in 7.1 sec

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining

Tianyu Tang, Shilin Zhou, Zhipeng Deng, Huanxin Zou, Lin Lei
2017 Sensors  
However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles  ...  Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster  ...  Figure 1 . 1 Two challenges for vehicle detection in aerial images. (a) small vehicles; (b) hard negative examples. Figure 2 . 2 Proposed vehicle detection framework.  ... 
doi:10.3390/s17020336 pmid:28208587 pmcid:PMC5335960 fatcat:retf5eb555hohc5jwo5cxyzfna

On the use of deep neural networks for the detection of small vehicles in ortho-images

Jean Ogier Du Terrail, Frederic Jurie
2017 2017 IEEE International Conference on Image Processing (ICIP)  
This paper addresses the question of the detection of small targets (vehicles) in ortho-images. This question differs from the general task of detecting objects in images by several aspects.  ...  This work supports an extensive study of the problems one might face when applying deep neural networks with low resolution and scarce data and proposes some solutions.  ...  The most recent articles on the subject are [23, 24] , based on handcrafted descriptors, and [25, 26, 27] using convolutional neural networks (CNNs).  ... 
doi:10.1109/icip.2017.8297076 dblp:conf/icip/TerrailJ17 fatcat:sj2hsol5rfdddorixkucsrybbu

Orientation robust object detection in aerial images using deep convolutional neural network

Haigang Zhu, Xiaogang Chen, Weiqun Dai, Kun Fu, Qixiang Ye, Jianbin Jiao
2015 2015 IEEE International Conference on Image Processing (ICIP)  
In this paper, we propose to use Deep Convolutional Neural Network (DCNN) features from combined layers to perform orientation robust aerial object detection.  ...  Detecting objects in aerial images is challenged by variance of object colors, aspect ratios, cluttered backgrounds, and in particular, undetermined orientations.  ...  A hard negative mining procedure is conducted to further improve the performance.  ... 
doi:10.1109/icip.2015.7351502 dblp:conf/icip/ZhuCDFYJ15 fatcat:wcwyvbs3arhjdcccvbevfc5vum

Salience Biased Loss for Object Detection in Aerial Images [article]

Peng Sun, Guang Chen, Guerdan Luke, Yi Shang
2018 arXiv   pre-print
In current implementations, multi-scale based and angle-based networks have been proposed and generate promising results with aerial image detection.  ...  Object detection in remote sensing, especially in aerial images, remains a challenging problem due to low image resolution, complex backgrounds, and variation of scale and angles of objects in images.  ...  Hard Example Mining In general, mining hard positives enables the model to discover and expand sparsely sampled minority class boundaries, while mining hard-negatives aims to improve the margins of minority  ... 
arXiv:1810.08103v1 fatcat:pybpmlp5c5evvarvrqezrpubtm

VEHICLE DETECTION IN REMOTE SENSING IMAGES USING DEEP NEURAL NETWORKS AND MULTI-TASK LEARNING

M. Cao, H. Ji, Z. Gao, T. Mei
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Specifically, we take advantage of deep residual network, multi-scale feature fusion, hard example mining and homography augmentation to realize vehicle detection, which almost integrates all the advanced  ...  Vehicle detection in remote sensing image has been attracting remarkable attention over past years for its applications in traffic, security, military, and surveillance fields.  ...  Moreover, many region-based methods are conducted to detect smaller aerial vehicles.  ... 
doi:10.5194/isprs-annals-v-2-2020-797-2020 fatcat:ewdicrl4dnceda7vr7hxhsajde

On Learning Vehicle Detection in Satellite Video [article]

Roman Pflugfelder, Axel Weissenfeld, Julian Wagner
2020 arXiv   pre-print
Vehicle detection in aerial and satellite images is still challenging due to their tiny appearance in pixels compared to the overall size of remote sensing imagery.  ...  Classical methods of object detection very often fail in this scenario due to violation of implicit assumptions made such as rich texture, small to moderate ratios between image size and object size.  ...  Using a convolutional neural network in combination with hard negative mining showed by a F 1 score of 0.7 reasonable results with 15 cm GSD on aerial images [15] .  ... 
arXiv:2001.10900v1 fatcat:3qxkflfsk5ed7fepmbpmzikxbi

Deep Learning-Based Bird's Nest Detection on Transmission Lines Using UAV Imagery

Jin Li, Daifu Yan, Kuan Luan, Zeyu Li, Hong Liang
2020 Applied Sciences  
In this work, we propose a deep learning-based birds' nests automatic detection framework—region of interest (ROI) mining faster region-based convolutional neural networks (RCNN).  ...  In order to ensure the safety of transmission lines, the use of unmanned aerial vehicle (UAV) images for automatic object detection has important application prospects, such as the detection of birds'  ...  Faster Region-Based Convolutional Neural Networks (RCNN) in an Automatic Detection Framework Region-based convolutional neural networks (RCNN) use a selective search to generate region proposals [15]  ... 
doi:10.3390/app10186147 fatcat:ixkm53s435c5fmmcolk3deipby

Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network

Yewei Xiao, Zhiqiang Li, Dongbo Zhang, Lianwei Teng
2021 IEEE Access  
This paper proposed a target detection method based on cascaded convolutional neural networks.  ...  First, a small-scale shallow full convolutional neural network was used to obtain the region of interest; then, a deeper convolutional neural network conducted target classification and positioning on  ...  Y.Xiao et al.: Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network  ... 
doi:10.1109/access.2021.3079172 fatcat:ktgmcvpb75exhcmkomvhy447by

An Improved FBPN-Based Detection Network for Vehicles in Aerial Images

Bin Wang, Yinjuan Gu
2020 Sensors  
By combining FBPN with modified faster region convolutional neural network (faster-RCNN), a vehicle detection framework for aerial images is proposed.  ...  The experimental results based on the VEDIA, USCAS-AOD, and DOTA datasets show that the proposed framework outperforms other state-of-the-art vehicle detection algorithms for aerial images.  ...  In 2018, Yohei Koga et al. applied hard example mining (HEM) to the training process of a convolutional neural network for vehicle detection in aerial images [2] .  ... 
doi:10.3390/s20174709 pmid:32825471 fatcat:6tztbboekbaqdcdqr45urmoxga

AUTOMATIC VEHICLE RECOGNITION FOR URBAN TRAFFIC MANAGEMENT

M. Mohammadi, F. Tabib Mahmoudi, M. Hedayatifard
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, an automatic vehicle recognition algorithm is proposed based on very high spatial resolution aerial images.  ...  The ability of online supervision on the distribution of vehicles in urban environments prevents traffic, which in turn reduces air pollution and noise.  ...  Vehicle detection in aerial images based on region convolutional neural networks and hard negative example mining. Sensors, 17(2), 336. Tayara, H., Soo, K. G., & Chong, K. T. (2018).  ... 
doi:10.5194/isprs-archives-xlii-4-w18-741-2019 fatcat:lnvzoqoeczdpbkrosknzujvql4

A feature fusion deep-projection convolution neural network for vehicle detection in aerial images

Bin Wang, Bin Xu, Hongzhi Guo
2021 PLoS ONE  
In this paper, a Feature Fusion Deep-Projection Convolution Neural Network is proposed to enhance the ability to detect small vehicles in aerial images.  ...  With the rapid development of Unmanned Aerial Vehicles, vehicle detection in aerial images plays an important role in different applications.  ...  Koga et al applied Hard Example Mining (HEM) to Stochastic Gradient Descent (SGD) in the process of training neural networks [12] .  ... 
doi:10.1371/journal.pone.0250782 pmid:33961655 fatcat:dwo35cfglffvbfyue3w4vwuc6e

Vehicle Detection in Aerial Images Based on 3D Depth Maps and Deep Neural Networks

Saleh Javadi, Mattias Dahl, Mats I. Pettersson
2021 IEEE Access  
INDEX TERMS Convolutional neural networks, 3D depth maps, object detection, aerial images.  ...  Next, a fully connected neural network (fcNN) was trained on 3D feature maps of trucks, semi-trailers and trailers. A cascade of these networks was then proposed to detect vehicles in aerial images.  ...  for their support in this work.  ... 
doi:10.1109/access.2021.3049741 fatcat:wy7sqskjpbarza6ty2ysahvipe

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

2017 Remote Sensing  
For the task of vehicle detection in aerial images, it is known that only region proposal-based networks have been investigated.  ...  Evaluation results on the public DLR Vehicle Aerial dataset and Vehicle Detection in Aerial Imagery (VEDAI) dataset demonstrate that our method can detect both the location and orientation of the vehicle  ...  The authors would like to thank Kang Liu and Gellert Mattyus, who generously provided their image dataset with the ground truth.  ... 
doi:10.3390/rs9111170 fatcat:lby5t62upbhjlcl67lbhwk3wmm

Multi-sized Object Detection Using Spaceborne Optical Imagery

Muhammad Haroon, Muhammad Shahzad, Muhammad Moazam Fraz
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The dataset images are acquired from multiple locations in the EU/US regions available in the public Google Earth satellite imagery.  ...  Specifically, it comprises 5000 images of resolution 1024 × 768 and collectively contains 45 096 objects in 15 different classes of vehicles including cars, trucks, buses, long vehicles, various types  ...  [29] also used hard negative example mining to employ hyper region proposal network in extracting vehicles with higher recall rate. Audebert et al.  ... 
doi:10.1109/jstars.2020.3000317 fatcat:fpzak4mnwfci7gjewfknh57etu

Lightweight Two-Stream Convolutional Face Detection

Paraskevi Nousi, Anastasios Tefas, Danai Triantafyllidou
2018 Zenodo  
Publication in the conference proceedings of EUSIPCO, Kos island, Greece, 2017  ...  Acknowledgments This project has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 731667 (MULTIDRONE).  ...  This process simulates hard negative example mining.  ... 
doi:10.5281/zenodo.1160102 fatcat:lq4s2zh7mjdshl2heh7z5hnvay
« Previous Showing results 1 — 15 out of 603 results