Performance Evaluation of Lightweight Detection Algorithms on Compact LiDAR-Camera Configurations for Freight Transportation

Article Sidebar

PDF
Published: 2026-01-18
Keywords:
lightweight neural networks, compact LiDAR, sensor fusion, freight transportation

Main Article Content

Yi Guo
Computer and Information Science, University of Pennsylvania, PA, USA

Abstract

Autonomous freight transportation faces deployment barriers due to high-cost sensor configurations. This research evaluates lightweight detection algorithms across three cost-level LiDAR-camera configurations targeting freight logistics. MobileNet-based detectors, EfficientNet-FPN architectures, and sparse convolutional networks are implemented on NVIDIA Jetson AGX Orin platforms. Experimental validation on the nuScenes dataset demonstrates mid-cost configurations achieve 5.2% mAP reduction versus the 64-channel baseline while reducing costs by 85%. Low-cost 16-channel configurations maintain 83.3% detection accuracy at 97% cost reduction. Hardware deployment reveals MobileNet-SSD achieves 28.7 FPS with a 3.2GB memory footprint. Pareto-optimal analysis identifies optimal sensor-algorithm combinations for budget-constrained scenarios, providing quantitative guidance for commercial autonomous trucking deployment.

Article Details

Issue

Vol. 1 No. 1 (2025): 2025 International Conference on Intelligent Computing and Automated Systems (ICAS 2025)

Section

Articles

How to Cite

Performance Evaluation of Lightweight Detection Algorithms on Compact LiDAR-Camera Configurations for Freight Transportation. (2026). Journal of Science, Innovation & Social Impact, 1(1), 398-409. https://sagespress.com/index.php/JSISI/article/view/62

References

1. Y. Li, F. Zeng, R. Lai, T. Wu, J. Guan, A. Zhu, and Z. Zhu, "TinyFusionDet: Hardware-Efficient LiDAR-Camera Fusion Framework for 3D Object Detection at Edge," IEEE Transactions on Circuits and Systems for Video Technology, 2025. doi: 10.1109/tcsvt.2025.3556711

2. W. Li, Y. Zhang, Y. Lv, T. Wang, S. Wang, and G. Wang, "ESO-SLAM: Tightly-Coupled and Simultaneous Estimation of Self and Multi-Object Pose via Sensor Fusion," In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October, 2024, pp. 10097-10104. doi: 10.1109/iros58592.2024.10802118

3. D. Mohammed, and B. Horváth, "Comparative analysis of following distances in different adaptive cruise control systems at steady speeds," World Electric Vehicle Journal, vol. 15, no. 3, p. 116, 2024. doi: 10.3390/wevj15030116

4. F. Cao, S. Wang, X. Chen, T. Wang, and L. Liu, "Bev-lslam: A novel and compact bev lidar slam for outdoor environment," IEEE Robotics and Automation Letters, 2025. doi: 10.1109/lra.2025.3531727

5. S. Liu, C. Li, T. Yuwen, Z. Wan, and Y. Luo, "A lightweight LiDAR-camera sensing method of obstacles detection and classification for autonomous rail rapid transit," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 12, pp. 23043-23058, 2022. doi: 10.1109/tits.2022.3194553

6. P. Hu, Y. Qian, T. Zheng, A. Li, Z. Chen, Y. Gao, and J. Luo, "t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving," IEEE Transactions on Mobile Computing, 2024. doi: 10.1109/tmc.2024.3462437

7. D. Katare, D. Perino, J. Nurmi, M. Warnier, M. Janssen, and A. Y. Ding, "A survey on approximate edge AI for energy efficient autonomous driving services," IEEE Communications Surveys & Tutorials, vol. 25, no. 4, pp. 2714-2754, 2023. doi: 10.1109/comst.2023.3302474

8. Q. Guan, Z. Sheng, and S. Xue, "HRPose: Real-time high-resolution 6D pose estimation network using knowledge distillation," Chinese Journal of Electronics, vol. 32, no. 1, pp. 189-198, 2023. doi: 10.23919/cje.2021.00.211

9. L. Y. Gao, Z. Qu, S. Y. Wang, and S. F. Xia, "A lightweight neural network model of feature pyramid and attention mechanism for traffic object detection," IEEE Transactions on Intelligent Vehicles, vol. 9, no. 2, pp. 3422-3435, 2023.

10. H. Saleem, R. Malekian, and H. Munir, "Lightweight Low-Light Image Enhancement Model Training and Design Considerations," In 2025 IEEE International systems Conference (SysCon), April, 2025, pp. 1-7. doi: 10.1109/syscon64521.2025.11014822

11. A. R. Yadulla, B. Konda, M. Yenugula, V. K. Kasula, S. B. Rakki, and R. Banoth, "Lightweight Neural Networks for Adversarial Defense: A Novel NTK-Guided Pruning Approach," In 2025 37th Conference of Open Innovations Association (FRUCT), May, 2025, pp. 331-337. doi: 10.23919/fruct65909.2025.11008002

12. Y. Zhang, B. Yang, W. Lei, and X. Pei, "Research on Multi-Modal Fusion Perception Technology for Autonomous Sweeping Vehicle," IEEE Sensors Journal, 2025.

13. Y. Zhou, C. Yang, P. Wang, C. Wang, X. Wang, and N. N. Van, "ViT-FuseNet: MultiModal fusion of vision transformer for vehicle-infrastructure cooperative perception," IEEE Access, vol. 12, pp. 31640-31651, 2024.

14. S. Liang, P. Chen, S. Wu, and H. Cao, "Complementary Fusion of Camera and LiDAR for Cooperative Object Detection and Localization in Low Contrast Environments at Night Outdoors," IEEE Transactions on Consumer Electronics, 2024. doi: 10.1109/tce.2024.3436852

15. Y. Qiu, C. Lin, J. Mei, Y. Sun, H. Lu, and J. Xu, "Lightweight cross-modal information measure and propagation for road extraction from remote sensing image and trajectory/LiDAR," IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-16, 2024. doi: 10.1109/tgrs.2024.3385667