F-DSNet: A Frustum-guided Lightweight 3D Object Detection Method in Complex Scenes
- 18 March 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (7)
Abstract
Balancing lightweight model design with detection accuracy remains a major challenge in 3D object detection. To address this issue, we propose a novel Frustum DeepScaleNet (F-DSNet) based on the Frustum ConvNet framework. F-DSNet integrates a Res2Net-style hierarchical residual multi-scale design by embedding hierarchical residual connections into the convolutional layers and replacing each single convolution branch with parallel multi-scale pathways. This design enhances context aggregation with an enlarged effective receptive field while reducing parameter redundancy in the feature extraction stage, enabling architectural-level model compression. Additionally, we propose a bounding-box quality estimation module. This module jointly models classification confidence and center localization error to boost contributions from high-quality bounding boxes, suppress adverse effects from low-quality boxes, and improve both classification and localization performance. Experimental results on the SUN RGB-D and KITTI datasets show that the 4-layer F-DSNet reduces the number of parameters by 32.23% and FLOPs by 0.73%, while achieving a 0.4% improvement in mAP over the baseline F-ConvNet. Furthermore, its 3-layer variant achieves a 61.91% reduction in parameters and a 4.41% reduction in FLOPs, while maintaining comparable detection accuracy.Keywords
Funding Information
- National Natural Science Foundation of China (62276042)
- The Basic Scientific Research Program of the Department of Education of Liaoning Province (LJKMZ20220838)
This publication has 16 references indexed in Scilit:
- Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR2025
- RailVoxelDet: A Lightweight 3-D Object Detection Method for Railway Transportation Driven by Onboard LiDAR DataIEEE Internet of Things Journal, 2025
- Enhanced frustrum multi-scale VoteNet for 3D object detection in cluttered indoor sceneApplied Intelligence, 2025
- DSPDet3D: 3D Small Object Detection with Dynamic Spatial Pruning2024
- A comprehensive survey of deep learning-based lightweight object detection models for edge devicesArtificial Intelligence Review, 2024
- Survey and systematization of 3D object detection models and methodsThe Visual Computer, 2023
- 3D object detection algorithm based on multi-sensor segmental fusion of frustum association for autonomous drivingApplied Intelligence, 2023
- A survey on RGB-D datasetsComputer Vision and Image Understanding, 2022
- IoU-aware single-stage object detector for accurate localizationImage and Vision Computing, 2020
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016