Jul 2026· The 2026 International Conference on Optical Communication and Intelligent Algorithms (OCIA 2026)· Vol 14301, pp. 143012L - 143012L-8· 0 citations· 16 references
Engineering
TL;DR
The engineering and experimental findings demonstrate that the fusion strategy developed in this work provides a practical and transferable solution for next-generation autonomous vehicle perception in real-world deployments.
Abstract
Intelligent multimodal perception is essential for the reliability and safety of autonomous driving in complex, real-world environments. This study designs and implements a real-time object detection system that tightly couples visual features from advanced YOLOv8 convolutional neural networks with spatial information extracted from LiDAR point clouds. An adaptive sensor fusion pipeline aligns and merges these heterogeneous data sources through feature- and decision-level integration, enhanced by dynamic weighting based on real-time sensor quality estimation. The system is deployed and evaluated on a synchronized hardware platform that replicates automotive deployment, with experimental protocols covering both standard benchmarks and adverse environmental scenarios. Quantitative results show that the weighted fusion approach notably improves mean average precision and maintains high throughput and low latency even under rain, low illumination, and sensor ambiguity. Analytical modeling of mAP, robustness metrics, and error propagation provides insight into the mechanisms behind the observed performance gains and system stability. Ablation studies further confirm that both the vision and LiDAR modules, as well as the adaptive weighting mechanism, are pivotal for consistent detection and operational resilience. The engineering and experimental findings demonstrate that the fusion strategy developed in this work provides a practical and transferable solution for next-generation autonomous vehicle perception in real-world deployments.
Autonomous driving has become a transformative technology poised to reshape modern transportation systems. This paper explores multimodal fusion techniques that integrate various sensors with machine vision for autonomous driving. We examine the integration of various sensor modalities, including cameras, LiDAR, and millimeter-wave radar, alongside advanced machine vision algorithms such as YOLO, Faster R-CNN, Point Pillars, and MVX-Net for environment perception. This work addresses major challenges in sensor fusion, including data synchronization, coordinate transformation, real-time computation and conflict resolution of heterogeneous sensor data. We systematically analyze three typical fusion architectures: data-level, feature-level and decision-level fusion, and compare their performance in information retention, computational efficiency and system robustness. Through representative application cases in object detection and classification, high-precision localization and mapping, and decision-making and path planning, we demonstrate how multimodal fusion significantly enhances the robustness, accuracy, and reliability of autonomous vehicle perception systems. The paper further discusses current limitations including computational overhead, adverse-weather robustness, and lack of standardized evaluation, and outlines future directions such as end-to-end learning, 4D radar integration, and V2X-enabled cooperative perception. The results prove that reliable multimodal fusion is a core prerequisite for realizing safe and stable autonomous driving.
Yu-He Lu· Applied and Computational En...· 0 citations
The commercialization of autonomous driving relies heavily on reliable environmental perception in all-weather and all-scenario conditions. Complex weather such as low-light, rain, fog, snow, and haze severely degrades the perception performance of visual sensors and LiDAR, becoming a core bottleneck restricting the robustness of object detection models. This paper systematically reviews the research progress of visual perception and 2D/3D object detection for autonomous driving in complex weather, and constructs a full-link optimization paradigm from data, feature, model, and deployment levels. At the data level, a hybrid style transfer augmentation method based on physical priors and generative AI is proposed to solve the problems of scarce complex weather samples and imbalanced distribution. At the feature level, a weather-adaptive attention mechanism and a multi-modal feature alignment module are designed to alleviate feature degradation and noise interference under low-light and rainy-foggy conditions. At the model level, a cross-modal fusion detection framework with 2D visual guidance and 3D point cloud geometric constraints is built to achieve accurate target positioning in all weather. At the deployment level, quantization distillation and dynamic inference strategies are proposed to balance accuracy and real-time performance on vehicle-mounted platforms. Extensive experiments on KITTI, NuScenes, and a self-built complex weather dataset show that the proposed framework improves 2D and 3D object detection accuracy by 9.3% and 7.8%, respectively, compared with baseline models, while keeping inference delay within 40 ms. Finally, this paper deeply analyzes the limitations of current technologies and prospects future research directions such as extreme weather perception, self-supervised learning, and multi-sensor collaboration, providing a systematic theoretical reference and engineering practice guide for the development of allweather perception systems for autonomous driving.
Shaojie Weng· International Conference on...· 1 citation
This paper presents a multi-sensor fusion architecture with camera data segmentation. Robust perception is a fundamental prerequisite for the safety of autonomous vehicles, particularly in dynamic environments and varying weather conditions. Multi-sensor fusion approaches, integrating camera and LiDAR data, have emerged as the reference solution for 3D object detection, thanks to the complementary information provided by each modality. However, most existing work validates their architectures on static benchmarks such as the KITTI dataset, which do not allow for the evaluation of the system's robustness under controlled and reproducible variations in environmental conditions. In this work, we propose to deploy and evaluate a multi-sensor fusion pipeline in the CARLA nearrealistic simulator, which offers a dynamic, configurable, and physically realistic environment that faithfully reproduces realworld driving conditions. The adopted architecture is based on a fusion at the intermediate representation level, combining features from the camera, after segmentation of the raw data, and from LiDAR. The results obtained show that the simulation in CARLA constitutes a complementary and rigorous evaluation framework, bridging the gap between laboratory validation and deployment in real-world conditions.
Rihem Sebai, A. Sahbani, T. Bejaoui· International Conference on...· 0 citations
Since the technology of autonomous driving is gaining momentum in its implementation in real-life conditions with multifaceted and complicated road conditions, the weaknesses of single sensors in the context of sensing accuracy, stability, and adaptability to the environment become more evident. To improve the robustness and security of autonomous driving systems in compound environments, in this paper, the research on the multi-sensor fusion technology is put into the limelight and the value of such technology applied in autonomous driving perception systems are evaluated. Thereafter, a comparison of the perception properties, benefits, and deficits of cameras and lidar is made systematically and at the data level, the fundamental patterns of multi-sensor integration are divided into three levels, namely the feature-level, sensor-level and decision-level. This study shows that when multi-sensor fusion strategies are rationally designed, the constraints of a single sensor used to sample the environment can be addressed, and this strategy plays an important role in increasing the resilience of the system as well as its ability to understand its surrounding. The discussion made in this paper offers a useful source of information when it comes to the design and implementation of multi-sensors fusion systems within the engineering field.
Zhixiang Xu· MATEC Web of Conferences· 0 citations
With the rapid development of intelligent connected vehicles and autonomous driving technology in recent years, environmental perception has gradually been added to ensure the safety and reliability of autonomous driving; now, automotive LiDAR is one of the required sensors in the perception system because it has high-precision 3D space detection and strong anti-interference ability. The point cloud data obtained by LiDAR is often affected by internal hardware faults and various complicated external environmental factors; therefore, there is a lot of noise that can damage the operation of autonomous driving perception. Research on the Development of Automotive LiDAR Systems and Denoising Technology for Multi-sensor Fusion. It systematically introduces the working principle and range mechanism of ToF and FMCW, the technical development path of automotive LiDAR, typical point cloud noise sources, relevant denoising methods, etc. At the same time, it will also study how the hardware characteristics of LiDAR are related to multi-sensor fusion denoising and explore the advantages of vehicle-road cooperative perception. This paper will introduce the current situation of research at home and abroad on technical progress and provide theoretical support for the engineering optimisation and application of automotive LiDAR perception technology.
Sensor fusion plays a critical role in enabling reliable perception for autonomous driving systems by integrating heterogeneous data from multiple sensors such as cameras, LiDAR, radar, and inertial units. However, inconsistencies in spatial alignment, temporal synchronisation, and data representation present significant challenges to achieving a unified understanding of the driving environment. This paper proposes a conceptual framework that interprets sensor fusion as a reconstructive process, transforming diverse sensory inputs into a coherent environmental model. The study systematically analyses three levels of fusion: data-level, feature-level, and decision-level, and examines how artificial intelligence enhances each stage through learned alignment, cross-modal feature representation, and uncertainty-aware decision making. Furthermore, the paper connects fusion strategies to key autonomous driving tasks, including object detection, tracking, localisation, and planning, highlighting the relationship between task requirements and fusion architecture design. Finally, major challenges such as domain shift, long-tail scenarios, sensor failure, and interpretability are discussed. This work provides a structured perspective on AI-driven sensor fusion and its role in building robust and adaptive intelligent driving systems.
