To systematically summarize the research status of multi-source fusion environmental perception technology for intelligent vehicles, this paper compares and analyzes the principles and characteristics of various sensors including cameras, Light Detection and Ranging (LiDAR), and millimeter-wave radar. The environmental perception technologies based on single-sensor approaches (such as camera-based object detection and LiDAR point cloud processing) and multi-sensor fusion strategies (data-level, feature-level, and decision-level) are reviewed with their technical bottlenecks and challenges. Typical algorithm cases are also discussed to explore their application effectiveness. The research findings indicate that: single sensors exhibit inherent limitations, such as cameras’ dependency on illumination conditions and LiDAR’s high cost with insufficient semantic information acquisition capability, as well as multi-sensor fusion technology significantly enhances environmental perception robustness through complementary advantages, yet challenges like data heterogeneity and insufficient real-time performance still remain unresolved. To meet the perception demands of complex scenarios, future development will focus on intelligent multi-modal fusion algorithms, cost-effective sensor integration, and V2X collaborative perception technologies.