0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
U-Net-based Automotive Radar Target Detection and Recognition
نویسندگان :
Jamal Kazazi
1
Seyyed Mohammad Matin AleMohammad
2
Mahmoud Kamarei
3
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
کلمات کلیدی :
FMCW radar،U-Net،Target Detection،Automotive Radar،Deep Learning
چکیده :
In this paper, we have designed a CNN-based neural network, to detect targets using a FMCW radar more accurately than traditional methods. We have also shown that using this approach will enable us to not only detect targets but also it can categorize them, by their size, with high accuracy. Training of such a network requires a large amount of data, so one of the most challenging parts of this research was to simulate and generate suitable radar data to train the network. The detection rate of targets is reported for different SNRs and it increased by 40 percent on average, in comparison with CFAR methods.
لیست مقالات
لیست مقالات بایگانی شده
Enhancing SCGAN’s Disentangled Representation Learning with Contrastive SSIM Similarity Constraints
Iman Yazdanpanah - Ali Eslamian
Modeling Data Communications of Wireless Sensor Networks Based on MFM Model and Analyzing Its Stability Using Wave Advanced Model (WAM)
Saeedreza Tofighi - Masoud Shafiee
A Novel Method to Estimate Thevenin Equivalent Circuit Using Local Measurements
Pouria Akbarzadeh Aghdam - Hamid Khoshkhoo
بهبودی بر مساله تشخیص اشیا برجسته درتصاویر مبتنی بر یادگیری عمیق
مهران طاهری - محمد صادق هل فروش - کامران کاظمی
Flexible Microgrid Scheduling with the Presence of Renewable Energy Resources
Mahdi Rahimi - Fatemeh Jahanbani Ardakani - Ali Reza Rahimi
A Simplified Computational Method for a Proposed mm-Wave Reconfigurable Intelligent Surface
Nima Ahmadi - Forouhar Farzaneh
بهبود بازدهی انرژی در اینترنت اشیاء باند باریک با وفقیسازی لینک به کمک یادگیری عمیق
سمانه امیریان - محمدعلی سبقتی
ارزش گذاری منابع تولید پراکنده به منظور توسعه شبکه توزیع برق به کمک نظریه بازیها
شایان مرادیان - حبیب رجبی مشهدی
MAD-TI: Meta-path Aggregated-Graph Attention Network for Drug Target Interaction Prediction
Reza Shami Tanha - Maryam Sadighian - Arash Zabihian - Mohsen Hooshmand - Mohsen Afsharchi
Real-Time Prediction of Lower Limb AngularTrajectories Using an Optimized LSTM Model withMarkerless Motion Capture
Amirhossein Jafari - Hamed Jalaly Bidgoly
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 43.6.0