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 calledGraphMapTR, 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; andDeformable 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 thatGraphMapTRsignificantly 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.

The online vectorized map construction technique employs a neural network model to forecast the vectorized representation of a specific region around automobiles, using data obtained from sensors mounted on automobiles. Due to advances in end-to-end object detection with transformers framework, the research on query-based online mapping has attracted substantial attention. However, the fixed number of queries and the random initialization of query embeddings constrain the model's performance. Moreover, the transformer architecture for object detection is based on the assumption that queries are identically distributed and independent, a premise that is not entirely applicable to map point queries which possess established subordinate relationships with map element instances. To address these issues, we initially incorporate a simplified transformer layer that utilizes semantic priors in bird's-eye view features for query initialization. The queries are then sent to a transformer-based map decoder for optimization and combined with a dynamic query management mechanism to eliminate low-confidence queries, hence maintaining computational efficiency. Furthermore, to guarantee that point queries within each instance preserve a consistent representation and avoid feature confusion among map element instances, we proposed an instance internal consistency map decoder. We conduct extensive experiments on commonly used map construction datasets to evaluate the proposed method. The experimental results demonstrate that our proposed method achieves state-of-the-art performance on the nuScenes and Argoverse 2 datasets.

LiDAR point clouds 3D semantic segmentation enables efficient and accurate environmental sensing for intelligent vehicles and autonomous robots, greatly advancing these domains. Existing advanced methods that use 3D sparse convolutional often suffer from a small Effective Receptive Field (ERF), which limits context sensing and challenging highperformance segmentation. Building on this observation, we propose MDC-Seg for efficient ERF enlargement. We design Multi-directional Convolution (MDConv), which simultaneously performs sparse feature encoding on the Bird's Eye View (BEV) and Range View (RV) planes to enlarge the ERF of 3D sparse convolution. To enhance feature fusion in MDConv, we introduce an attention mechanism and design an efficient multifeature fusion (EMFF) module suitable for both 3D and 2D sparse features. To improve segmentation accuracy, we design a point-voxel constraint (PVC) module to handle edge voxels containing multiple point cloud categories, optimizing the final inference results. These modules add minimal memory and inference time but significantly improve performance compared to the baseline. Extensive experiments on the SemanticKITTI benchmark demonstrate MDC-Seg's excellent performance, with supplementary tests on nuScenes further confirming its superiority by yielding good results. The source code is available at https://github.com/OYgreat-river/MDC-Seg.

Current research on autonomous driving trajectory prediction algorithms continues to face challenges. One key issue is that the encoding of road topology may fail to simultaneously capture both local detail and global representation. Secondly, the separate processing of spatial and temporal information for traffic participants can result in the loss of critical temporal feature information. To address these issues, we propose a trajectory prediction algorithm named TrajPred-MSM using the high-definition map by multi-scale. The core idea of this algorithm is to encode high-definition maps at two scales: nodes for local representation and lane segments for global representation. The designed dual-scale approach captures fine-grained microscopic connection relationships in local areas while preserving macroscopic connections from a global perspective. Experimental results on the Argoverse dataset demonstrate that TrajPred-MSM, by effectively extracting map information, outperforms traditional trajectory prediction algorithms.

Vision-based 3D semantic occupancy is a crucial task in autonomous driving perception. 3D semantic occupancy, compared with Bird’s Eye View(BEV) approaches, enhances supplements the limitations of BEV by incorporating essential height information, which significantly enhances the capacity for comprehensive scene analysis and understanding via leveraging 2D images to predict the 3D geometry and semantic in various scenes. However, most existing approaches rely heavily on complex models to aggregate voxel features, while overlooking important contextual and prior information. In this study, we propose a novel network architecture based on complex prior queries, referred to as MPFormer, a multi-prior transformer for vision-based scene understanding in autonomous driving. Concretely, we introduce densification of sparse features, query fusion of random queries, instance queries and voxel queries, and integration of self-attention mechanisms with geometric priors to optimize scene understanding comprehensively. MPFormer, in comparison to the baseline, demonstrates a 7% improvement in mIoU on the SemanticKITTI dataset, validating the effectiveness of the proposed method.

We study a graph partition problem where the input is a directed acyclic graph (DAG) representing tasks as vertices and dependencies between tasks as arcs. The goal is to assign the tasks to k heterogeneous machines in a way that minimizes the total energy consumed for completing the tasks. We first show that the problem is NP -hard. Then, we present polynomial-time algorithms for two special cases: one where there are only two machines, and another where the input DAG is a directed path. Finally, we examine a variant where there are only two machines, with one capable of executing a limited number of tasks, and demonstrate that this special case remains computationally hard.

Modern robotic systems are increasingly deployed in complex and diverse environments, and reliable localization under challenging conditions becomes crucial for the safe and efficient operation of these systems. The odometry based on LiDAR is prone to system collapse caused by computational divergence under conditions of aggressive motion and information deficiency in spatial geometry. To enhance the robustness of systems in challenging scenes, this work proposes LA-LIO, robust localizability-aware LiDAR inertial odometry. It mainly consists of three parts. Firstly, this paper presents a LiDAR degeneration detection method that enables stable degeneration assessment. Secondly, a method for segmenting LiDAR point clouds is proposed to alleviate the issue of excessive distortion in point clouds under aggressive motion scenes. The last is an Errors State Kalman Filter (ESKF) method with adaptive weights to utilize the existing spatial information as much as possible to improve the stability of the system in degenerated scenarios. The proposed method is evaluated and compared in multiple experiments, demonstrating the performance and reliability improvements of this approach in challenging environments.

As a crucial part of mobile robotics and autonomous driving, Visual Place Recognition (VPR) is usually addressed by recognizing its similar reference images from a pre-obtained database. However, VPR always suffers from environmental changes, such as weather, illumination, perceptual-aliasing and so on. To address this, we firstly introduce a robust and discriminative global descriptor aggregation technique that normalizes the spatial and channel dimensions of features. A Spatial-Channel Embedding (SCE) module is proposed to learn the spatial and scale information of features which make global features more discriminative. Meanwhile, the traditional re-ranking methods (e.g. RANSAC) for geometric consistency verification are time-consuming. Here we propose a Neighborhood Consensus Guided Matching (NCGM) module, which uses Neighborhood Consensus to filter the features from patch-level matching to achieve more accurate matching while reduces the time consumption. Through extensive experiments on multiple benchmarks, we demonstrate that our method outperforms several state-of-the-art methods while maintaining lower time consumption and storage requirements.

Cross-view geo-localization refers to the task of matching the same geographic target using images obtained from different platforms, such as drone-view and satellite-view. However, the view angle of images obtained through different platforms will vary greatly, which can bring great challenges to the cross-view geo-localization task. Therefore, we propose a multi-level feedback joint representation learning network based on adaptive area elimination to solve the cross-view geo-localization problem. In our network model, we first process the extracted global features to obtain part-level and patch-level features. We then utilize these features as feedback to the global features to extract the contextual information in the global features and improve the robustness of the extracted features. In addition, as images obtained from different platforms differ, there will always be some interference when matching images. Therefore, we introduce an adaptive area elimination strategy to erase the interference information in the global features and assist the model in obtaining crucial information. On this basis, the feature correlation loss function is designed to constrain learning when using global feature information, thereby eliminating the possible interference, which can improve the network model performance. Finally, a series of experiments is carried out using two well-known benchmarks, namely University-1652 and SUES-200, and the experimental results show that the proposed network model achieves competitive results, thereby demonstrating the effectiveness of proposed model.

This paper presents a fast LiDAR-inertial odometry (LIO) that is robust to aggressive motion. To achieve robust tracking in aggressive motion scenes, we exploit the continuous scanning property of LiDAR to adaptively divide the full scan into multiple partial scans (named sub-frames) according to the motion intensity. And to avoid the degradation of sub-frames resulting from insufficient constraints, we propose a robust state estimation method based on a tightly-coupled iterated error state Kalman smoother (ESKS) framework. Furthermore, we propose a robocentric voxel map (RC-Vox) to improve the system’s efficiency. The RC-Vox allows efficient maintenance of map points and k nearest neighbor (k-NN) queries by mapping local map points into a fixed-size, two-layer 3D array structure. Extensive experiments are conducted on 27 sequences from 4 public datasets, our own dataset and real-world scenes. The results show that our system can achieve stable tracking in aggressive motion scenes (angular velocity up to 21.8 rad/s) that cannot be handled by other state-of-the-art methods, while our system can achieve competitive performance with these methods in general scenes. Furthermore, thanks to the RC-Vox, our system is much faster than the most efficient LIO system currently published.

Long-term visual place recognition (VPR) has recently become a popular research topic in the field of autonomous driving. In urban scenarios, variations in scene appearance due to the change in seasons and illumination bring great challenges for scene description. Several learning-based VPR techniques can learn latent invariant descriptors for appearance variations and show excellent performance in long-term VPR tasks. However, these methods require huge datasets and computational resources (e.g., GPUs) for training and inference. Mobile platforms such as autonomous vehicles often cannot provide sufficient computing power. To address this issue, in this paper, a training-free lightweight global image descriptor named SSR-VLAD is proposed for VPR. This descriptor is able to work accurately in real-time without GPUs, even on embedded platforms. The contribution of this work has two aspects. (1) A novel semantic skeleton representation (SSR) is proposed to describe the semantic spatial distribution of scenes by using the semantic spatial context; (2) Inspired by the Vector of Locally Aggregated Descriptors (VLAD), a spatial-temporal aggregation framework for SSR features is constructed to aggregate all SSR features into one SSR-VLAD descriptor, which encodes the spatial and temporal information into a fixed-size global descriptor. SSR-VLAD shows robust performance towards the appearance variations of scenes. Specifically, on three public datasets with challenging urban scenes, experimental results show that SSR-VLAD has competitive VPR performance compared to several state-of-the-art (SoTA) VPR methods. Additionally, SSR-VLAD achieves SoTA real-time computational performance with lower RAM consumption in computationally constrained scenarios.

Curb detection can be used to determine road boundary information, which plays a crucial role in intelligent driving. In this paper, we propose an efficient 3D curb detection network combined with the Transformer (LCDeT), which realizes efficient and stable curb extraction from the mobile laser scanning data end-to-end. Different from the most existing algorithms that project the 3D point cloud to the 2D image, like height map or density map images before processing, we directly extract the point cloud features from the 3D point cloud to avoid the loss of spatial information of the 3D point cloud. Furthermore, we introduce SpatioTemporal Window(STWin) attention operations in the Transformer module to extract continuous, smooth curb features. In the temporal dimension, we perform a cross-attention operation on the point cloud of the historical frame and the point cloud of the current frame to improve the stability and continuity of the road edge detection results between the multi-frame point clouds. In the spatial dimension, we introduce the hybrid-attention operation on the point cloud of the current frame to extract spatially related features from the axial and local positions, respectively, to improve the detection accuracy. At last, to verify the performance, we firstly test it based on the only public curb dataset of 32-line LiDAR. The proposed LCDet achieves the state-of-the-art performance, an F1 score of 97.59%, with LCDet. At the same time, it is considered that the industry lacks roadside datasets for high-resolution LiDARs. We have collected, organized and published the industry's first 128-line laser roadside dataset, NRS-Dataset, which contains 6200 frames of point clouds in Urban during daytime and nighttime. And the NRS-Dataset will be available at [github11https://github.com/STWin1/curb]. Furthermore, we test the algorithm based on this dataset. The experimental results prove that our approach achieves high accuracy and recall in complex scenarios, which further shows the higher effective and robust performance of the LCDet algorithm than previous studies.

This article investigates the problem of fuzzy adaptive predefined-time terminal sliding mode (TSM) control for a third-order heterogeneous vehicular platoon system with an unknown dead zone. For the purpose of approximating unknown nonlinear functions, fuzzy logic systems (FLSs) are utilized. In addition, the impact of the dead zone on the performance of the control may be lessened by building the dead-zone compensation. A tracking error based on the modified constant time headway policy is built to get rid of the assumption of zero initial spacing and decrease the distance between vehicles at the same time. A unique nonsingular TSM control system is then built using the predefined-time stability criterion; with the help of Lyapunov functions, it is possible to demonstrate both the individual and the string stability of the whole heterogeneous vehicle platoon in a predefined time. Finally, a series of simulations are shown to demonstrate the validity of the proposed results.

In a Simultaneous Localization and Mapping (SLAM) system, loop-closure can eliminate accumulated errors, which is accomplished by Visual Place Recognition (VPR), a task that retrieves current scene from a set of pre-stored sequential images through matching specific scene-descriptors. In urban scenes, the appearance variation caused by seasons and illumination have brought great challenges to the robustness of scene descriptors. Semantic segmentation images can not only deliver the shape information of objects, but also their categories and spatial relations that will not be affected by the appearance-variation of the scene. Innovated by the Vector of Locally Aggregated Descriptor (VLAD), in this paper, we propose a novel image descriptor with aggregated semantic skeleton representation (SSR), dubbed SSR-VLAD, for the VPR under drastic appearance-variation of environments. The SSR-VLAD of one image aggregates the semantic skeleton features of each category, and encodes the spatial-temporal distribution information of the image semantic information. We conduct a series of experiments on three public datasets of challenging urban scenes. Compared with three state-of-the-art VPR methods- CoHog, NetVLAD, and Region-VLAD, VPR by matching SSR-VLAD outperforms those methods and maintains competitive real-time performance at the same time.

This article investigates the adaptive neural-network (NN) tracking optimal control problem for stochastic nonlinear systems, which contain state constraints and uncertain dynamics. First, to avoid the violation of state constraints in achieving optimal control, the novel barrier optimal performance index functions for subsystems are developed. Second, under the framework of the identifier-actor-critic, the virtual and actual optimal controllers are presented based on the backstepping technique, in which the unknown nonlinear dynamics are learned by the NN approximators. Moreover, the quartic barrier Lyapunov functions are constructed instead of square ones to cope with the Hessian term to ensure the stability of the systems with stochastic disturbance. The proposed optimal control strategy can guarantee the boundedness of closed-loop signals, and the output can follow the given reference signal. Meanwhile, the system states are restricted within some preselected compact sets all the while. Finally, both numerical and practical systems are carried out to further illustrate the validity of the proposed optimal control approach.

In this work, an adaptive neural network (NN) optimized output-feedback control problem is studied for a class of stochastic nonlinear systems with unknown nonlinear dynamics, input saturation, and state constraints. A nonlinear state observer is designed to estimate the unmeasured states, and the NNs are used to approximate the unknown nonlinear functions. Under the framework of the backstepping technique, the virtual and actual optimal controllers are developed by employing the actor-critic architecture. Meanwhile, the tan-type Barrier optimal performance index functions are developed to prevent the nonlinear systems from the state constraints, and all the states are confined within the preselected compact sets all the time. It is worth mentioning that the proposed optimized control is clearly simple since the reinforcement learning (RL) algorithm is derived based on the negative gradient of a simple positive function. Furthermore, the proposed optimal control strategy ensures that all the signals in the closed-loop system are bounded. Finally, a practical simulation example is carried out to further illustrate the effectiveness of the proposed optimal control method.

The adaptive neural network (NN) output-feedback optimal control issue has been investigated for a quarter-car active electric suspension systems, where the suspension stiffness is unknown and partial state variables are unavailable for measurement. NNs are utilized to identify unknown nonlinearities, and an NN state observer is devised to estimate the unmeasurable states. For each backstepping step, via reinforcement learning (RL), a critic–actor architecture is designed to get the approximation solution of Hamilton–Jacobi–Bellman (HJB) equations and actual and virtual optimization controllers are designed, in which the input saturation constraint and road interference are considered. It is analytically proved that all controlled system signals remain bounded, while the power of the control input signal, as well as the amplitude of the vertical displacement, has been minimized. A comparative simulation is eventually given to elaborate the feasibility of the developed control algorithm.

Traffic light recognition is of great significance for driver assistance or autonomous driving. In this paper, a traffic light recognition system based on smartphone platforms is proposed. First, an ellipsoid geometry threshold model in Hue Saturation Lightness color space is built to extract interesting color regions. These regions are further screened with a postprocessing step to obtain candidate regions that satisfy both color and brightness conditions. Second, a new kernel function is proposed to effectively combine two heterogeneous features, histograms of oriented gradients and local binary pattern, which is used to describe the candidate regions of traffic light. A kernel extreme learning machine (K-ELM) is designed to validate these candidate regions and simultaneously recognize the phase and type of traffic lights. Furthermore, a spatial-temporal analysis framework based on a finite-state machine is introduced to enhance the reliability of the recognition of the phase and type of traffic light. Finally, a prototype of the proposed system is implemented on a Samsung Note 3 smartphone. To achieve a real-time computational performance of the proposed K-ELM, a CPU-GPU fusion-based approach is adopted to accelerate the execution. The experimental results on different road environments show that the proposed system can recognize traffic lights accurately and rapidly.

This paper presents a multi-type road marking recognition system by using a monocular camera on a moving platform. The system can detect various road markings. Firstly, an Inverse Perspective Mapping (IPM) transformation is introduced to suppress the perspective effect in the image, and the image slices which potentially belong to road markings are extracted based on high brightness slice filtering. Secondly, the prior knowledge of road making is applied to generate candidate road marking regions. Afterwards, a coarse-to-fine marking recognition method is presented. In the coarse recognition, an Adaboost classifier with Haar-like feature is adopted to fast eliminate non-marking candidates regions. In the fine recognition, an ELM classifier with BW-HOG feature is designed to recognize the types of markings. Finally, we introduce a spatial-temporal fusion method to further enhance the recognition accuracy and reliability of the system. Experimental results demonstrate the effectiveness of the proposed system.

This study presents a hierarchical background modelling and subtraction approach for real‐time detection of moving objects. At the first level, a novel pixel‐wise background modelling method is proposed for coarse detection. The method can dynamically assign the optimal number of components for each pixel with the borrow–lend strategy. And a flexible learning rate which is variable and different for each component is presented to adapt to scene changes. Additionally, a new mechanism using a framework of finite state machine is introduced to maintain and update the background models. At the second level, in order to deal with sudden illumination changes, a block‐wise foreground validation approach is adopted for refined detection. The authors compare the proposed approach with state‐of‐the‐art methods and experimental results under various scenes demonstrate the robustness and effectiveness of the proposed approach.

Vision-based pedestrian detection remains a challenging task, so far. The detection performance often suffers from the various appearances of pedestrians, the illumination changes, and the possible partial occlusions. Aiming at resolving these challenges, in this paper, a new linear kernel function is proposed to effectively combine two heterogeneous features, i.e., histogram of oriented gradient and local binary pattern, which enhances the pedestrian description ability to illumination conditions and cluttered background. Then, a novel multi-view-pose part ensemble (MVPPE) detector is proposed, in order to better handle pedestrian variability, views, and partial occlusions. Experimental results in public data sets demonstrate that the proposed feature combination method significantly improves the description capabilities of pedestrian features. Compared with the existing multipart ensemble approaches, the proposed MVPPE detector boosts higher detection accuracy.

There are many timing unreliable computing components in modern computer systems, which are typically forbidden in hard real-time systems due to the timing uncertainty. In this paper, we propose a computation offloading mechanism to utilise these timing unreliable components in a hard real-time system, by providing local compensations. The key of the mechanism is to decide (1) how the unreliable components are utilized and (2) how to set the worst-case estimated response time. The local compensation has to start when the unreliable components do not deliver the results in the estimated response time. We propose a scheduling algorithm and its schedulability test to analyze the feasibility of the compensation mechanism. To validate the proposed mechanism, we perform a case study based on image-processing applications in a robot system and simulations. By adopting the timing unreliable components, the system can handle higher-quality images and with better performance.

Pedestrian detection exhibits important application value in driver assistance systems, The detection performance often suffers from the various appearances of pedestrians, the illumination changes and complex background. Aiming at solving these challenges, in this paper, first, a new color moments feature is presented to describe the local similarity structure of pedestrians, which reduces the influence of complicated background. A combination coefficient method is introduced to effectively fuse three heterogeneous features, COLOR, HOG, and LBP, which makes better use of each feature. Then, pedestrians of various poses and views are divided into subclasses with S-Isomap and K-means algorithm. A classifier is trained for each subclass. Finally, with respect to the output values of different subclass classifiers, an equally weighted sum based multi-pose-view ensemble detector is proposed. Experiment results on public datasets demonstrate that the proposed feature combination method significantly improves the description capabilities of pedestrian features. Compared with the existing methods, the proposed detector combining the feature and multi-pose-view ensemble detector boosts the detection accuracy effectively.

The applications of the mobile devices are increasingly being improved. They include computation-intensive tasks, such as video and audio processing. However, the mobile devices have limited resources, which may make it difficult to finish these tasks in time. Computation offloading can be used to boost the capabilities of these resource-constrained devices, where the computation-intensive tasks are moved to a powerful remote processing unit. This paper considers the computation offloading problem for sporadic real-time tasks. The total bandwidth server (TBS) is adopted on the remote processing unit (the server side) for resource reservation. On the client side, a dynamic programming algorithm is proposed to determine the offloading decision of the tasks such that their schedule is feasible (i.e., all the tasks meet their deadlines). The algorithm is evaluated using a case study of surveillance system and synthesized benchmarks.

Smart Grid is an important application in Internet Of Things (IOT). Monitoring data in large-scale smart grid are massive, real-time and dynamic which collected by a lot of sensors, Intelligent Electronic Devices (IED) and etc.. All on account of that, traditional centralized storage proposals aren't applicable to data storage in large-scale smart grid. Therefore, we propose a data-centric storage approach in support of monitoring system in large-scale smart grid: Hierarchical Extended Storage Mechanism for Massive Dynamic Data (HES). HES stores monitoring data in different area according to data types. It can add storage nodes dynamically by coding method with extended hash function for avoiding data loss of incidents and frequent events. Monitoring data are stored dispersedly in the nodes of the same player by the multi-threshold levels means in HES, which avoids load skew. The simulation results show that HES satisfies the needs of massive dynamic data storage, and achieves load balance and a longer life cycle of monitoring network.

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.

In this paper, we present a novel visual speed limit signs detection and recognition system. In detection stage, for the purpose of reducing the computational load and further decreasing the error detection rate of speed limit sign, a novel de-noising method based on HOG is presented and apply it to Fast Radial Symmetry Transform approach for circle signs detector. In recognition stage, firstly, a method of Fourier-wavelet descriptor is introduced to extract rotation invariant features which can recognize slant speed limit signs. Then the Support Vector Machines with Binary Tree Architecture are designed to identify categories of signs. Supplementary traffic signs are used to alter the meaning of speed limit signs. We propose an algorithm which is able to recognize supplementary signs with slightly rotated in a region below recognized speed limit signs. Experimental results in different conditions, including sunny, cloudy and rainy weather demonstrate that most speed limit signs and supplementary signs can be correctly detected and recognized with a high accuracy and the average processing time is less then 33ms per frame on a standard 2.8 GHz dual-core PC.

Lane recognition plays an important role in driver assistance systems. Many Lane recognition methods have been proposed until now. But most methods are used to recognize the traditional painted lines and can't work on the road where there are only raised pavement lane markers such as reflective markers and bots dots. Lane recognition on this kind of roads is a difficult problem especially in the daytime for the raised pavement markers are poorly visible and not reflected. In this paper, a novel solution for lane recognition in this case is presented. Firstly, the dot filters and the OLS templates are proposed for location of raised pavement markers. Then a line fitting method based on Hough transform and clustering is used on the accumulation image of raised pavement markers to detect the implicit lane. The experimental results under various scenes show that the proposed method is effective and can be implemented in real-time.