422 Hits in 4.9 sec

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

Saleh Javadi, Mattias Dahl, Mats I. Pettersson
2021 IEEE Access  
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.  ...  These results indicate the importance of 3D features utilization to improve object detection in aerial images for future research.  ...  like thank the Port of Karlshamn, the Port of Karlskrona, NetPort Science Park, the Municipality of Karlshamn, the Swedish Transport Agency, and the Swedish Transport Administration for their support in  ... 
doi:10.1109/access.2021.3049741 fatcat:wy7sqskjpbarza6ty2ysahvipe

Detection, Tracking, and Geolocation of Moving Vehicle from UAV Using Monocular Camera

Xiaoyue Zhao, Fangling Pu, Hangzhi Wang, Hongyu Chen, Zhaozhuo Xu
2019 IEEE Access  
First, the method based on YOLOv3 was employed for vehicle detection due to its effectiveness and efficiency for small object detection in complex scenes.  ...  Unmanned aerial vehicles (UAVs) have been widely used in urban traffic supervision in recent years.  ...  The moving vehicle with a small pixel size in the video is detected based on the model trained by YOLOv3.  ... 
doi:10.1109/access.2019.2929760 fatcat:uohkugw65zdrtkcjw3hjjks7h4

Vehicle Detection Using Different Deep Learning Algorithms from Image Sequence

Sumeyye Cepni, Muhammed Enes Atik, Zaide Duran
2020 Baltic Journal of Modern Computing  
Object detection, one of the new subjects of deep learning, is applied to high resolution aerial or remote sensing images to ex.tract information from these images.  ...  The comparison of YOLO models trained on COCO data was performed on the video obtained separately from a UAV and the terrestrial camera to identify the vehicles.  ...  Fig. 4 .Fig. 5 : 45 Detection of vehicles by YOLOv3, YOLOv3-spp and YOLOv3-tiny method on UAV image (top to bottom) Detection of vehicles YOLOv3 YOLOv3-spp and YOLOv3-tiny methods on terrestrial videos  ... 
doi:10.22364/bjmc.2020.8.2.10 fatcat:3zkeriw4u5hkpchx643eqh2iri

Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3

Bilel Benjdira, Taha Khursheed, Anis Koubaa, Adel Ammar, Kais Ouni
2019 2019 1st International Conference on Unmanned Vehicle Systems-Oman (UVS)  
In this paper, we investigate the performance of two state-of-the art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images.  ...  One of the major challenges is to use aerial images to accurately detect cars and count-them in real-time for traffic monitoring purposes.  ...  INTRODUCTION Unmanned aerial vehicles (UAVs) are being more and more adopted in surveillance and monitoring tasks due to their flexibility and great mobility.  ... 
doi:10.1109/uvs.2019.8658300 fatcat:5wrbqfil6jbo7kzv5ymozbmkty

A YOLO-Based Target Detection Model for Offshore Unmanned Aerial Vehicle Data

Zhenhua Wang, Xinyue Zhang, Jing Li, Kuifeng Luan
2021 Sustainability  
Herein, a YOLO-based detection model (YOLO-D) was proposed for target detection in offshore unmanned aerial vehicle data.  ...  Based on the YOLOv3 network, the residual module was improved by establishing dense connections and adding a dual-attention mechanism (CBAM) to enhance the use of features and global information.  ...  In this study, we proposed a target detection model for target detection in offshore unmanned aerial vehicle data based on the improved YOLOv3 (YOLO-D) network.  ... 
doi:10.3390/su132312980 fatcat:j6qhbb5ohfeepf4y6tp24ivr7u

Multiple-Object-Tracking Algorithm Based on Dense Trajectory Voting in Aerial Videos

Tao Yang, Dongdong Li, Yi Bai, Fangbing Zhang, Sen Li, Miao Wang, Zhuoyue Zhang, Jing Li
2019 Remote Sensing  
Based on this, we trained the neural network model by using a deep-learning method to detect vehicles in aerial videos.  ...  In this paper, we propose a multiple-object-tracking algorithm based on dense-trajectory voting in aerial videos.  ...  The vehicle size in these images was medium, similar to aerial images taken by UAVs at low altitude. Based on this training dataset, we chose a YOLOv3 network model for training.  ... 
doi:10.3390/rs11192278 fatcat:zxucyks3ijhw5g6y5pr55x3d64

SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes

Murari Mandal, Manal Shah, Prashant Meena, Santosh Kumar Vipparthi
2019 2019 IEEE International Conference on Image Processing (ICIP)  
Detection of small-sized targets is of paramount importance in many aerial vision-based applications.  ...  The commonly deployed low cost unmanned aerial vehicles (UAVs) for aerial scene analysis are highly resource constrained in nature.  ...  Recent approaches [6] [7] [8] [9] [10] for aerial images have primarily used the two-stage architectures (fast/faster R-CNN [11] ) based frameworks to detect vehicles in aerial scenes.  ... 
doi:10.1109/icip.2019.8803262 dblp:conf/icip/MandalSMV19 fatcat:k33fmj3vrbgovctwrlnxra6tgi

UAV-YOLO: Small Object Detection on Unmanned Aerial Vehicle Perspective

Mingjie Liu, Xianhao Wang, Anjian Zhou, Xiuyuan Fu, Yiwei Ma, Changhao Piao
2020 Sensors  
Object detection, as a fundamental task in computer vision, has been developed enormously, but is still challenging work, especially for Unmanned Aerial Vehicle (UAV) perspective due to small scale of  ...  Based on YOLOv3, the Resblock in darknet is first optimized by concatenating two ResNet units that have the same width and height.  ...  Introduction Object detection in Unmanned Aerial Vehicle (UAV), as a kind of burgeoning technique, has numerous applications, such as aerial image analysis, intelligent surveillance, and routing inspection  ... 
doi:10.3390/s20082238 pmid:32326573 pmcid:PMC7218847 fatcat:ukc4erzm3zg3reziqcxqq56t4y

Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3 [article]

Bilel Benjdira, Taha Khursheed, Anis Koubaa, Adel Ammar, Kais Ouni
2018 arXiv   pre-print
One of the major challenges is to use aerial images to accurately detect cars and count them in real-time for traffic monitoring purposes.  ...  In this paper, we investigate the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images.  ...  INTRODUCTION Unmanned aerial vehicles (UAVs) are being more and more adopted in surveillance and monitoring tasks due to their flexibility and great mobility.  ... 
arXiv:1812.10968v1 fatcat:ximkbkljxbaebeoojpo2nrujem

An Aerial Weed Detection System for Green Onion Crops Using the You Only Look Once (YOLOv3) Deep Learning Algorithm

Addie Ira Borja PARICO, Tofael AHAMED
2020 Engineering in Agriculture Environment and Food  
In this study, YOLO-WEED, a weed detection system based on YOLOv3, was developed.  ...  The real-time object detection system You Only Look Once (specifically YOLOv3) has recently shown remarkable speed, making it potentially suitable for Unmanned Aerial Vehicle (UAV) precision spraying.  ...  To close this cost gap, unmanned aerial vehicles (UAVs), a more cost-effective remote sensing platform, is gaining momentum in precision spraying in the past decade.  ... 
doi:10.37221/eaef.13.2_42 fatcat:ugvw26nq7bd2hhtv5i3yrlunle

Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark [article]

Brian K. S. Isaac-Medina, Matt Poyser, Daniel Organisciak, Chris G. Willcocks, Toby P. Breckon, Hubert P. H. Shum
2021 arXiv   pre-print
For this reason, the automated detection and tracking of UAV is a fundamental task in aerial security systems.  ...  Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use.  ...  These methods improve detection results on well-researched objects such as faces, pedestrians and vehicles, but it is unclear whether they transfer to UAV.  ... 
arXiv:2103.13933v3 fatcat:lqfa4zvuqfgx7ggctixwpyiu6m

Comparison of YOLO Versions for Object Detection from Aerial Images

Muhammed Enes ATİK, Zaide DURAN, Roni ÖZGÜNLÜK
2022 International Journal of Environment and Geoinformatics  
In recent years, object detection by deep learning from aerial or terrestrial images has become a popular research area.  ...  YOLOv2 can detect objects in an average photograph in 43 seconds, YOLOv3 has achieved superior performance in terms of time by detecting objects in an average of 2.5 seconds.  ...  Cepni et al. (2020) compared different deep learning algorithms using terrestrial and UAV-based aerial images in their study.  ... 
doi:10.30897/ijegeo.1010741 fatcat:z6f6ywsw7nhwtkguolggyajl54

Orientation- and Scale-Invariant Multi-Vehicle Detection and Tracking from Unmanned Aerial Videos

Jie Wang, Sandra Simeonova, Mozhdeh Shahbazi
2019 Remote Sensing  
The proposed methodology is tested on a variety of real videos collected by UAVs under various conditions, e.g., in late afternoons with long vehicle shadows, in dawn with vehicles lights being on, over  ...  In this paper, we propose a deep-learning framework for vehicle detection and tracking from UAV videos for monitoring traffic flow in complex road structures.  ...  Acknowledgments: The authors would like to acknowledge that the videos captured by DJI Phantom Pro 4 used in the Experiments section are provided by Professor Dr.  ... 
doi:10.3390/rs11182155 fatcat:clszipzkabcrbfwvb4tij6yqbi

An Efficient and Scene-Adaptive Algorithm for Vehicle Detection in Aerial Images Using an Improved YOLOv3 Framework

Xunxun Zhang, Xu Zhu
2019 ISPRS International Journal of Geo-Information  
Therefore, we propose an efficient and scene-adaptive algorithm for vehicle detection in aerial images using an improved YOLOv3 framework, and it is applied to not only aerial still images but also videos  ...  Then, since complex scenes in aerial images can cause the partial occlusion of vehicles, we construct a context-aware-based feature map fusion to make full use of the information in the adjacent frames  ...  The founding sponsor has the role in the analyses, interpretation of data, and in the decision to publish the results.  ... 
doi:10.3390/ijgi8110483 fatcat:6tos2hpihrghxle3nedh3th74y

Fast Automatic Vehicle Detection in UAV Images Using Convolutional Neural Networks

Xin Luo, Xiaoyue Tian, Huijie Zhang, Weimin Hou, Geng Leng, Wenbo Xu, Haitao Jia, Xixu He, Meng Wang, Jian Zhang
2020 Remote Sensing  
Based on convolutional neural networks that utilize the YOLOv3 algorithm, this article focuses on the development of a quick automatic vehicle detection method for UAV images.  ...  Then, a novel YOLOv3 vehicle detection framework is proposed according to the following characteristics: The vehicle targets in the UAV image are relatively small and dense.  ...  Acknowledgments: We would like to thank the anonymous reviewers for their valuable and helpful comments, which substantially improved this paper and we would also like to thank all of the editors for their  ... 
doi:10.3390/rs12121994 fatcat:3kv4salxjfbc5bzx4zls2h2esy
« Previous Showing results 1 — 15 out of 422 results