Simultaneous Localization and Mapping (SLAM) is the basis for intelligent mobile robots to work in unknown environments. However, traditional feature extraction algorithms that traditional visual SLAM systems rely on have difficulty dealing with texture-less regions and other complex scenes, which limits the development of visual SLAM. The studies of feature points extraction adopting deep learning show that this method has more advantages than traditional methods in dealing with complex scenes, but these studies consider accuracy while ignoring the efficiency. To solve these problems, this paper proposes a deep-learning real-time visual SLAM system based on multi-task feature extraction network and self-supervised feature points. By designing a simplified Convolutional Neural Network (CNN) for detecting feature points and descriptors to replace the traditional feature extractor, the accuracy and stability of the visual SLAM system are enhanced. The experimental results in a dataset and real environments show that the proposed system can maintain high accuracy in a variety of challenging scenes, run on a GPU in real-time, and support the construction of dense 3D maps. Moreover, its overall performance is better than the current traditional visual SLAM system.

同步定位和映射（SLAM）是智能移动机器人在未知环境中工作的基础。但是，传统视觉SLAM系统所依赖的传统特征提取算法难以处理无纹理区域和其他复杂场景，这限制了视觉SLAM的发展。通过深度学习进行特征点提取的研究表明，该方法在处理复杂场景方面比传统方法更具优势，但这些研究在考虑准确性的同时却忽略了效率。为了解决这些问题，本文提出了一种基于多任务特征提取网络和自我监督特征点的深度学习实时视觉SLAM系统。通过设计用于检测特征点和描述符的简化卷积神经网络（CNN）来代替传统的特征提取器，可增强视觉SLAM系统的准确性和稳定性。在数据集和真实环境中的实验结果表明，所提出的系统可以在各种具有挑战性的场景中保持高精度，可以在GPU上实时运行，并支持构建密集的3D地图。此外，其总体性能优于当前的传统视觉SLAM系统。并支持密集3D地图的构建。此外，其总体性能优于当前的传统视觉SLAM系统。并支持密集3D地图的构建。此外，其总体性能优于当前的传统视觉SLAM系统。