Search

Pedestrian tracking is an important aspect of autonomous vehicles environment perception in a vehicle running environment. The performance of the existing pedestrian tracking algorithms is limited by the complex traffic environment, the changeable appearance characteristics of pedestrians and the frequent occlusion interaction, which leads to the insufficient accuracy and stability of tracking. Therefore, this paper proposes a detector–tracker integration framework for autonomous vehicle pedestrian tracking. Firstly, a pedestrian objects detector based on the improved YOLOv7 network was established. Space-to-Depth convolution layer was adopted to improve the backbone network of YOLOv7. Then, a novel appearance feature extraction network is proposed, which integrates the convolutional structural re-parameterization idea to construct a full-scale feature extraction block, which is the optimized DeepSORT tracker. Finally, experiments were carried out on MOT17 and MOT20 public datasets and driving video sequences, and the tracking performance of the proposed framework was evaluated by comparing it with the most advanced multi-object tracking algorithms. Quantitative analysis results show that the framework has high tracking accuracy. Compared with DeepSORT, MOTA improves by 2.3% in the MOT17 dataset and MOTA improves by 4.2% in the MOT20 dataset. Through qualitative evaluation on real driving video sequences, the framework proposed in this paper is robust in a variety of climate environments, and can be effectively applied to the pedestrian tracking of autonomous vehicles. [ABSTRACT FROM AUTHOR]

Facing the significant challenge of 3D object detection in complex weather conditions and road environments, existing algorithms based on single-frame point cloud data struggle to achieve desirable results. These methods typically focus on spatial relationships within a single frame, overlooking the semantic correlations and spatiotemporal continuity between consecutive frames. This leads to discontinuities and abrupt changes in the detection outcomes. To address this issue, this paper proposes a multi-frame 3D object detection algorithm based on a deformable spatiotemporal Transformer. Specifically, a deformable cross-scale Transformer module is devised, incorporating a multi-scale offset mechanism that non-uniformly samples features at different scales, enhancing the spatial information aggregation capability of the output features. Simultaneously, to address the issue of feature misalignment during multi-frame feature fusion, a deformable cross-frame Transformer module is proposed. This module incorporates independently learnable offset parameters for different frame features, enabling the model to adaptively correlate dynamic features across multiple frames and improve the temporal information utilization of the model. A proposal-aware sampling algorithm is introduced to significantly increase the foreground point recall, further optimizing the efficiency of feature extraction. The obtained multi-scale and multi-frame voxel features are subjected to an adaptive fusion weight extraction module, referred to as the proposed mixed voxel set extraction module. This module allows the model to adaptively obtain mixed features containing both spatial and temporal information. The effectiveness of the proposed algorithm is validated on the KITTI, nuScenes, and self-collected urban datasets. The proposed algorithm achieves an average precision improvement of 2.1% over the latest multi-frame-based algorithms. [ABSTRACT FROM AUTHOR]

Simultaneous localization and mapping (SLAM) algorithm is a prerequisite for unmanned ground vehicle (UGV) localization, path planning, and navigation, which includes two essential components: frontend odometry and backend optimization. Frontend odometry tends to amplify the cumulative error continuously, leading to ghosting and drifting on the mapping results. However, loop closure detection (LCD) can be used to address this technical issue by significantly eliminating the cumulative error. The existing LCD methods decide whether a loop exists by constructing local or global descriptors and calculating the similarity between descriptors, which attaches great importance to the design of discriminative descriptors and effective similarity measurement mechanisms. In this paper, we first propose novel multi-channel descriptors (CMCD) to alleviate the lack of point cloud single information in the discriminative power of scene description. The distance, height, and intensity information of the point cloud is encoded into three independent channels of the shadow-casting region (bin) and then compressed it into a two-dimensional global descriptor. Next, an ORB-based dynamic threshold feature extraction algorithm (DTORB) is designed using objective 2D descriptors to describe the distributions of global and local point clouds. Then, a DTORB-based similarity measurement method is designed using the rotation-invariance and visualization characteristic of descriptor features to overcome the subjective tendency of the constant threshold ORB algorithm in descriptor feature extraction. Finally, verification is performed over KITTI odometry sequences and the campus datasets of Jilin University collected by us. The experimental results demonstrate the superior performance of our method to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Accurate and comprehensive 3D objects detection is important for perception systems in autonomous driving. Nevertheless, contemporary mainstream methods tend to perform more effectively on large objects in regions proximate to the LiDAR, leaving limited exploration of long-range objects and small objects. The divergent point pattern of LiDAR, which results in a reduction in point density as the distance increases, leads to a non-uniform point distribution that is ill-suited to discretized volumetric feature extraction. To address this challenge, we propose the Foreground Voxel Proposal (FVP) module, which effectively locates and generates voxels at the foreground of objects. The outputs are subsequently merged to mitigating the difference in point cloud density and completing the object shape. Furthermore, the susceptibility of small objects to occlusion results in the loss of feature space. To overcome this, we propose the Multi-Scale Feature Integration Network (MsFIN), which captures contextual information at different ranges. Subsequently, the outputs of these features are integrated through a cascade framework based on transformers in order to supplement the object features space. The extensive experimental results demonstrate that our network achieves remarkable results. Remarkably, our approach demonstrated an improvement of 8.56% AP on the SECOND baseline for the Car detection task at a distance of more than 20 m, and 9.38% AP on the Cyclist detection task. [ABSTRACT FROM AUTHOR]

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We proposed to achieve this goal by trading off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are efficient scale-equivariant feature extraction, cross-scale upsampling through pyramidal fusion and boundary-aware learning of pixel-to-instance assignment. The proposed method is very well suited for remote sensing imagery due to the huge number of pixels in typical city-wide and region-wide datasets. We present panoptic experiments on Cityscapes, Vistas, COCO, and the BSB-Aerial dataset. Our models outperformed the state-of-the-art on the BSB-Aerial dataset while being able to process more than a hundred 1MPx images per second on an RTX3090 GPU with FP16 precision and TensorRT optimization. [ABSTRACT FROM AUTHOR]