不可见字符下适用于OpenDrive格式高精地图的数字水印算法

A Digital Watermark Algorithm Suitable for OpenDrive Format High Precision Maps under Invisible Characters

我国已将发展智能网联汽车、发展自动驾驶作为国家的重要战略方向,高精地图作为自动驾驶的核心基础设施具有高精度与高商业价值的特点,其安全问题不可忽视。本文基于不可见字符,在不影响高精地图数据精度与自动驾驶应用场景的前提下,提出了一种适用于OpenDrive格式标准下高精地图数据的数字水印算法。首先,构建水印信息与不可见字符的映射机制,根据原始水印信息建立包含水印比特值、比特位置信息与海明码的复合型水印字符序列,在保证水印比特与水印索引同步性的同时为算法提供一定的自纠错能力;然后,将映射后的不可见字符按照伪随机置乱后的标识符集合及其属性值的顺序嵌入到高精地图属性值中,使水印信息无规律地嵌入至数据中且分布较为均匀。检测水印时依据伪随机置乱的初始条件按照嵌入顺序提取出水印比特与其对应的索引位置,最后根据多数原则获取最终水印信息并依据海明码对错误比特进行纠正。研究表明,该算法能够抵抗平移、旋转、缩放、裁剪的攻击,在裁剪数据98元素,具有很好的鲁棒性。可为OpenDrive格式高精地图的版权保护提供参考。

The development of intelligent connected cars and autonomous driving has become an important national strategic direction of our country.As the core infrastructure of autonomous driving,high-precision maps have high commercial value,and their safety issues cannot be ignored.Based on invisible characters,this paper presents a digital watermarking algorithm for high precision maps in OpenDrive format.First,a mapping mechanism between watermark information and invisible characters is constructed,and a composite watermark character sequence containing watermark bit value,bit position information,and Hamming code is established based on the original watermark information,which ensures the synchronization of watermark bits and watermark index while providing the algorithm with a certain self-correction ability.Then,the mapped invisible characters are embedded into the high-precision map attribute values in the order of the pseudo-randomly scrambled identifier set and its attribute values,so that the watermark information is embedded into the data irregularly and distributed evenly.When detecting the watermark,the watermark bits and its corresponding position information are extracted according to the embedding sequence.The final watermark information is obtained according to the majority voting mechanism,and the error bits are corrected according to the Hamming code.Experiments show that the algorithm can fully resist the attacks of translation,rotation,and scaling while maintaining the map accuracy,and exhibits strong robustness to clipping attacks,which can be applied to the copyright protection of high precision maps in OpenDrive format.