S2DB-mmWave YOLOv8n: Multi-object detection for millimeter-wave radar using YOLOv8n with optimized multi-scale features
Open Access
- 19 September 2025
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (9) , e0332931
Abstract
Millimeter-wave (mmWave) radar has become an important research direction in the field of object detection because of its characteristics of all-time, low cost, strong privacy and not affected by harsh weather conditions. Therefore, the research on millimeter wave radar object detection is of great practical significance for applications in the field of intelligent security and transportation. However, in the multi-target detection scene, millimeter wave radar still faces some problems, such as unable to effectively distinguish multiple objects and poor performance of detection algorithm. Focusing on the above problems, a new target detection and classification framework of S2DB-mmWave YOLOv8n, based on deep learning, is proposed to realize more accuracy. There are three main improvements. First, a novel backbone network was designed by incorporating new convolutional layers and the Simplified Spatial Pyramid Pooling - Fast (SimSPPF) module to strengthen feature extraction. Second, a dynamic up-sampling technique was introduced to improve the model’s ability to recover fine details. Finally, a bidirectional feature pyramid network (BiFPN) was integrated to optimize feature fusion, leveraging a bidirectional information transfer mechanism and an adaptive feature selection strategy. A publicly available 5-class object mmWave radar heatmap dataset, including 2,500 annotated images, were selected for data modeling and method evaluation. The results show that the mean average precision (mAP), precision and recall of the S2DB-mmWave YOLOv8n model were 93.1% mAP@0.5, 55.8% mAP@0.5:0.95, 89.4% and 90.6%, respectively, which is 3.3, 1.6, 4.5 and 7.7 percentage points higher than the baseline YOLOv8n network without increasing the parameter count.Keywords
Funding Information
- Henan Province Key R&D Special Project (241111212500)
- Henan Province Key R&D and Promotion Special (232102210181)
This publication has 28 references indexed in Scilit:
- Adaptive CFAR detection for MIMO radars in Pearson clutterSignal, Image and Video Processing, 2025
- Design of Reconfigurable Radar Signal Processor for Frequency-Modulated Continuous Wave RadarIEEE Sensors Journal, 2025
- BSM-NET: multi-bandwidth, multi-scale and multi-modal fusion network for 3D object detection of 4D radar and LiDARMeasurement Science and Technology, 2025
- FADE: A Task-Agnostic Upsampling Operator for Encoder–Decoder ArchitecturesInternational Journal of Computer Vision, 2024
- mmDetect: YOLO-Based Processing of mm-Wave Radar Data for Detecting Moving PeopleIEEE Sensors Journal, 2024
- mmWave-YOLO: A mmWave Imaging Radar-Based Real-Time Multiclass Object Recognition System for ADAS ApplicationsIEEE Transactions on Instrumentation and Measurement, 2022
- Target Classification by mmWave FMCW Radars Using Machine Learning on Range-Angle ImagesIEEE Sensors Journal, 2021
- A method of radar target detection based on convolutional neural networkNeural Computing and Applications, 2021
- 2D Car Detection in Radar Data with PointNets2019
- Analysis of CFAR processors in nonhomogeneous backgroundIEEE Transactions on Aerospace and Electronic Systems, 1988