It is a challenging task for self-driving vehicles in Real-World traffic scenarios to find a trade-off between the real-time performance and the high accuracy of the detection, recognition, and tracking in videos. This issue is addressed in this paper with an improved YOLOv3 (You Only Look Once) and a multi-object tracking algorithm (Deep-Sort). First, data augmentation is employed for small sample traffic signs to address the problem of an extremely unbalanced distribution of different samples in the dataset. Second, a new architecture of YOLOv3 is proposed to make it more suitable for detecting small targets. The detailed method is (1) removing the output feature map corresponding to the 32-times subsampling of the input image in the original YOLOv3 structure to reduce its computational costs and improve its real-time performances; (2) adding an output feature map of 4-times subsampling to improve its detection capability for the small traffic signs; (3) Deep-Sort is integrated into the detection method to improve the precision and robustness of multi-object detection, and the tracking ability in videos. Finally, our method demonstrated better detection capabilities, with respect to state-of-the-art approaches, which precision, recall and mAP is 91%, 90%, and 84.76% respectively.

The accuracy of localization and mapping of automated guided vehicles (AGVs) using visual simultaneous localization and mapping (SLAM) is significantly reduced in a dynamic environment compared to a static environment due to incorrect data association caused by dynamic objects. To solve this problem, a robust stereo SLAM algorithm based on dynamic region rejection is proposed. The algorithm first detects dynamic feature points from the fundamental matrix of consecutive frames and then divides the current frame into superpixels and labels its boundaries with disparity. Finally, dynamic regions are obtained from dynamic feature points and superpixel boundaries types; only the static area is used to estimate the pose to improve the localization accuracy and robustness of the algorithm. Experiments show that the proposed algorithm outperforms ORB-SLAM2 in the KITTI dataset, and the absolute trajectory error in the actual dynamic environment can be reduced by 84% compared with the conventional ORB-SLAM2, which can effectively improve the localization and mapping accuracy of AGVs in dynamic environments.

The traditional simultaneous localization and mapping (SLAM) system uses static points of the environment as features for real-time localization and mapping. When there are few available point features, the system is difficult to implement. A feasible solution is to introduce line features. In complex scenarios containing rich line segments, the description of line segments is not strongly differentiated, which can lead to incorrect association of line segment data, thus introducing errors into the system and aggravating the cumulative error of the system. To address this problem, a point-line stereo visual SLAM system incorporating semantic invariants is proposed in this paper. This system improves the accuracy of line feature matching by fusing line features with image semantic invariant information. When defining the error function, the semantic invariant is fused with the reprojection error function, and the semantic constraint is applied to reduce the cumulative error of the poses in the long-term tracking process. Experiments on the Office sequence of the TartanAir dataset and the KITTI dataset show that this system improves the matching accuracy of line features and suppresses the cumulative error of the SLAM system to some extent, and the mean relative pose error (RPE) is 1.38 and 0.0593 m, respectively.