Application of Deep Learning Based Object Detection on Unmanned Aerial Vehicle

机译：基于深度学习的目标检测在无人机中的应用

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Object recognition can be seen in every field thanks to today's high computation power. It has become possible to extract information from the images with high accuracy in different areas such as human, animal, vehicle, traffic signs and MR images. In this study, plastic water bottle detection was applied by using Inception v2, MobileNet v2 and ResNet50 architectures to be used in the Scientific and Technological Research Council of Turkey (TUBITAK) International Unmanned Aerial Vehicle Competition. Cloud based training applied to locate very small objects from up to 5 meters high. In the present study, the Single Shot Detector (SSD) ResNet50 model yielded the best results for mAP@0.75 and final loss. It was also determined that SSD Inception v2 model gave better results than SSD MobileNet v2 model. When the processing times were considered, it was determined that models could not work at Raspberry Pi 3 Model B+ equipment at sufficient speed. However, these results have shown that the Jetson Nano card can be operated correctly on a drone. In the next stage of this study, the aim will be determining environmental pollution level by detecting objects such as plastic bags, bottles and fruits on the streets.

机译：由于当今的强大计算能力，在每个领域都可以看到对象识别。在诸如人类，动物，车辆，交通标志和MR图像的不同区域中从图像中提取信息成为可能。在这项研究中，通过使用Inception v2，MobileNet v2和ResNet50体系结构来应用塑料水瓶检测，以在土耳其科学技术研究理事会（TUBITAK）国际无人机竞赛中使用。基于云的培训适用于定位高达5米高的非常小的物体。在本研究中，单发检测器（SSD）ResNet50模型对于mAP@0.75和最终损失产生了最佳结果。还确定了SSD Inception v2模型比SSD MobileNet v2模型提供了更好的结果。考虑到处理时间后，确定模型无法在Raspberry Pi 3 Model B +设备上以足够的速度工作。但是，这些结果表明，Jetson Nano卡可以在无人机上正确操作。在本研究的下一阶段，目标是通过检测街道上的塑料袋，瓶子和水果等物体来确定环境污染水平。

著录项

来源
《International Conference on Computer Science and Engineering》|2020年|1-5|共5页
会议地点
作者
Burak Ipek; Mustafa Akpinar;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
convolutional neural networks; motion detection; neural net architecture;

机译：卷积神经网络;运动检测;神经网络架构;

相似文献

外文文献
中文文献
专利

1. RAPID OBJECT DETECTION SYSTEMS, UTILISING DEEP LEARNING AND UNMANNED AERIAL SYSTEMS (UAS) FOR CIVIL ENGINEERING APPLICATIONS [J] . Griffiths D., Boehm J. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences . 2018,第1期

机译：快速对象检测系统，利用深度学习和民航系统（UAS）进行土木工程应用
2. A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms [J] . Abdelmalek Bouguettaya, Hafed Zarzour, Amine Mohammed Taberkit, Signal processing . 2022,第Jana期

机译：基于深度学习的计算机视觉算法的无人机型航空公司早期野火检测综述
3. Deep learning-based dead pine tree detection from unmanned aerial vehicle images [J] . Tao Huan, Li Cunjun, Zhao Dan, International journal of remote sensing . 2020,第21a22期

机译：基于深度学习的死松树检测无人机空中车辆图像
4. Deep Learning Based Object Detection and Recognition of Unmanned Aerial Vehicles [C] . Erdem Bayhan, Zehra Ozkan, Mustafa Namdar, International Congress on Human-Computer Interaction, Optimization and Robotic Applications . 2021

机译：基于深度学习的物体检测与识别无人航空公司
5. Application of object detection and tracking techniques from unmanned aerial vehicles. [D] . Kamate, Shreyamsh. 2015

机译：无人机的目标检测和跟踪技术的应用。
6. Application of Deep-Learning Methods to Bird Detection Using Unmanned Aerial Vehicle Imagery [O] . Suk-Ju Hong, Yunhyeok Han, Sang-Yeon Kim, 2019

机译：深度学习方法在无人机图像鸟类探测中的应用
7. Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles [O] . Christos Kyrkou, Theocharis Theocharides 2019

机译：基于深度学习的空中图像分类，用于使用无人驾驶飞行器的应急响应应用

Application of Deep Learning Based Object Detection on Unmanned Aerial Vehicle

摘要

著录项

相似文献

相关主题

期刊订阅