Intelligent vehicle environment perception algorithm based on bubble sort data processing and data fusion

The environment perception system of intelligent vehicles, as a key component of intelligent vehicle systems, has become a major focus of attention among researchers worldwide. However, traditional perception algorithms for intelligent vehicles often face limitations in data processing capabilities. To address this issue, this study puts forward an environment perception algorithm for intelligent vehicles that combines bubble sort data processing and data fusion. This algorithm integrates the strengths of both methods to process data from multiple sensors. In addition, it applies the particle filter algorithm to further optimize its performance. Experimental results show that the algorithm achieves an object recognition accuracy of 96.7% and a sample recognition accuracy of 87%, demonstrating strong environment perception capabilities. In real-world applications, the algorithm maintains an accuracy rate of over 85% across different targets and environments. Even in extreme conditions where the targets are occluded, the success rate still reaches 61.7%. These findings indicate that the proposed algorithm can accurately identify and track obstacle objects around intelligent vehicles with high efficiency. This study contributes to the future implementation of precise environment perception under complex road conditions and promotes further intelligent development in the field of autonomous driving.