计算机科学
块(置换群论)
人工神经网络
骨干网
障碍物
特征(语言学)
残余物
算法
极限(数学)
人工智能
模式识别(心理学)
计算机网络
数学
语言学
数学分析
哲学
法学
政治学
几何学
作者
Youhua Peng,Peng Zhang,Fang Zheng,Dongxu Xing,Zhu Ming Guo,Shuaijie Zheng
摘要
Aiming at the complex and changeable driving scenarios of intelligent vehicles and the need to quickly and accurately identify obstacles, an improved YOLOV4 algorithm is proposed. To limit the number of neural network parameters, the CSP-darknet53 backbone of the original YOLOV4 was replaced with the Ghostnet backbone. In addition, to improve the neural network's accuracy, a lightweight attention mechanism ECA is added to the three effective feature layers generated by the backbone using residual block connections. Experiments have shown that the improved YOLOV4 has a 2.8% increase in mAP compared to the original YOLOV4. Without changing the accuracy, The network model's memory size is lowered by 39%, as well as a 50% improvement in detecting speed. Therefore, the improved YOLOV4 accuracy and real-time performance are better than the original network detection, providing a strong guarantee for intelligent vehicle obstacle avoidance.
科研通智能强力驱动
Strongly Powered by AbleSci AI