Research on Autonomous Driving Performance Enhancement in Low-Light Scenarios Based on Improved Object Detection Algorithm

Xiye Luo; Shixin Li

doi:10.63313/AJET.9073

Authors

Xiye Luo Tianjin University of Technology and Education, Tianjin, 300222, China Author
Shixin Li Tianjin University of Technology and Education, Tianjin, 300222, China Author

DOI:

https://doi.org/10.63313/AJET.9073

Keywords:

Object Detection, Autonomous Driving, Low-Light Scenarios, YOLO

Abstract

In low-light scenarios, autonomous driving perception systems face problems such as weak contrast, high noise, blurred boundaries, and missing texture details, which pose great challenges to object detection tasks. Existing methods often use image enhancement as a preprocessing step to improve detection performance; however, such methods usually require additional computational overhead and struggle to simultaneously meet the requirements of detection accuracy and real-time performance. To address these issues, this paper takes YOLOv8n as the baseline model and proposes an improved object detection algorithm, BiF-VoV-YOLO, for low-light autonomous driving scenarios. First, a lightweight feature fusion module, VoVGSCSP, is introduced into the backbone network to replace the original SPPF module. Through grouped feature reuse and channel shuffling, it reduces the number of model parameters and computational cost while enhancing low-light feature representation. Second, a BiFormer fusion layer is embedded in the neck, using a content-adaptive sparse attention mechanism to filter low-light background noise and improve global dependency modeling and detection accuracy. Finally, the upsampling node nn.Upsample is reconfigured and added in the neck. To address the lack of content-awareness in original upsampling, which leads to the loss of small-object details, this design improves information fidelity during the upsampling stage. The synergistic effect of the three modules significantly alleviates missed detection and false detection of multi-scale objects in low-light scenarios on the DarkFace dataset while maintaining the model's real-time inference capability. Experimental results show that the improved model achieves an [email protected] of 53.9%, an improvement of 8.9 percentage points over the YOLOv8n baseline, and a reduction of about 0.05MB in parameter count. It achieves the best detection accuracy among various classic models and state-of-the-art models, verifying the effectiveness and generalization of the proposed algorithm in low-light autonomous driving object detection.

References

[1] Abdullah D M, Abdulazeez A M. Machine learning applications based on SVM classification a review[J]. Qubahan Academic Journal, 2021, 1(2): 81-90.

[2] Al-Refai G, Elmoaqet H, Al-Refai A, et al. Two-stage object detection in low-light environments using deep learning image enhancement[J]. PeerJ Computer Science, 2025, 11: e2799.

[3] Wei S, Yu S. Improvement of nighttime vehicle detection algorithm based on YOLOv8n[C]//Proceedings of the 2024 International Conference on Computer and Multimedia Technology. 2024: 430-436.

[4] Zhu Y, Zhu W, Wang L. GLAM-YOLO: An Illumination-Calibrated and Global–Local Attention Enhanced YOLOv11 for Low-Light Object Detection[C]//2025 5th International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC). IEEE, 2025: 267-271.

[5] Ci W, Hou H, Lu S, et al. Multi-module enhanced low-light object detection: From image enhancement to adaptive feature fusion[J]. Advanced Engineering Informatics, 2026, 69: 104097.

[6] Zhao D, Shao F, Zhang S, et al. Advanced Object Detection in Low-Light Conditions: Enhancements to YOLOv7 Framework[J]. Remote Sensing, 2024, 16(23).

[7] Acharya U R, Oh S L, Hagiwara Y, et al. A deep convolutional neural network model to classify heartbeats[J]. Computers in biology and medicine, 2017, 89: 389-396.

[8] Bharati P, Pramanik A. Deep learning techniques—R-CNN to mask R-CNN: a survey[J]. Computational Intelligence in Pattern Recognition: Proceedings of CIPR 2019, 2019: 657-668.

[9] Ren Y, Zhu C, Xiao S. Object detection based on fast/faster RCNN employing fully convolutional architectures[J]. Mathematical Problems in Engineering, 2018, 2018(1): 3598316.

[10] Nakahara H, Yonekawa H, Fujii T, et al. A lightweight YOLOv2: A binarized CNN with a parallel support vector regression for an FPGA[C]//Proceedings of the 2018 ACM/SIGDA International Symposium on field-programmable gate arrays. 2018: 31-40.

[11] Wang C Y, Liao H Y M. YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems[J]. arXiv preprint arXiv:2408.09332, 2024.

[12] Loh Y P, Chan C S. Getting to know low-light images with the exclusively dark dataset[J]. Computer vision and image understanding, 2019, 178: 30-42.