In this paper, we present a novel visual speed limit signs detection and recognition system for American signs. Firstly, rectangle detector is used to search rectangle candidate. Secondly, the Improved Stroke Width Transform (ISWT) is introduced to seek stroke width inside each rectangle candidate. Thirdly, the modified Connected-Component labeling is used to group these pixels into digit candidates. Fourthly, a method is presented for segmenting the digit candidates in order to make every digit candidate contains only single digit. Finally, every segmented digit candidate is recognized respectively based on the Support Vector Machine using Majority Voting strategy (MV). We call the SVM using the MV strategy MV-SVM. And, all the recognized digits are verified whether combination of them is speed limit or not according to rule set. The presented system is tested in different conditions, including sunny, cloudy, rainy weather and night, and the experimental results demonstrate that it is much efficient for detecting and recognizing rectangular speed limit signs.

Bird’s Eye View (BEV) perception requires swift and accurate representation of real-world 3D information, and BEV-based 3D object detection and semantic segmentation are foundational for downstream autonomous tasks such as prediction and planning. Current BEV perception methods are divided into Light Detection and Ranging(LiDAR)-based and camera-based methods depending on the input data modalities. LiDAR-based methods offer precise 3D information, but are limited by high sensor costs. Conversely, camera-based methods are economical and widely researched. However, 2D image features transform into BEV space introducing feature distortion due to inaccurate 3D information, particularly in depth estimation which results in noisy projections. Denoising Diffusion Probabilistic Models (DDPM) are used to mitigate noise in BEV features. However, DDPM increases computational costs, relies on noisy images BEV features, and limits effectiveness. To address these issues, we propose a lightweight BEV perception framework (DMPG-BEV) to enhance the performance of camera-based methods. This framework employs Denoising Diffusion Implicit Models (DDIM) to generate point cloud features with 3D information, while reducing computational demands by fewer denoising steps. We also introduce a lightweight feature fusion module which integrates point cloud BEV features with image BEV features to incorporate 3D information and reduce noise. The refined BEV features are also well-suited for multi-task networks involving detection and segmentation tasks. Additionally, a lightweight view transformation module is included to further reduce computational costs. Extensive experiments on the nuScenes benchmark demonstrate better performance of our proposed model with reduced computation, highlighting its value in BEV perception.

High-definition (HD) maps play a crucial role in autonomous driving by providing a reliable foundation for behavior prediction and path planning. Recent methods model map elements as point sets and employ Transformer-based detection frameworks for end-to-end vectorized map construction. However, these approaches do not fully exploit geometric structural properties, thereby limiting the accuracy of predicting the shape and position of map elements. To address this limitation, we propose a novel method called GraphMapTR, which models map elements as graph structures. Each map element is represented as a subgraph where key points serve as nodes and edges capture structural continuity. To optimize the node query embeddings within subgraphs, we design a Graph Transformer-based decoder comprising three core components: Multi-head Self-Attention Between Subgraphs (MHSA-BSG), which facilitates efficient feature interaction across different subgraphs while enhancing node attention to their respective subgraph regions; Local Geometric-aware Self-Attention Within Subgraphs (LGSA-WSG), which dynamically aggregates global node relationships and local edge structures to enrich node representations; and Deformable Cross-Attention (DCA-BEV), which refines node embeddings through interaction with BEV features. In LGSA-WSG, priors from the rasterized map segmentation branch are incorporated to generate local geometric consistency scores (LGC-scores), which constitute edge structural bias. Extensive experiments demonstrate that GraphMapTR significantly outperforms state-of-the-art methods. In particular, it outperforms the state-of-the-art algorithm MapTRv2 by 5.0% mAP and 3.4% mAP on the nuScenes and Argoverse2 datasets, respectively.