Search

There are two standard methods in instance segmentation: top-down and bottom-up. The top-down approach performs object detection to generate candidate proposals and then performs pixel-level segmentation for each proposal. It is accurate and flexible, capable of handling objects of different sizes and shapes. However, it is computationally complex and relies on object detection accuracy. The bottom-up approach first performs pixel-level clustering or segmentation and then combines candidate instances to obtain the final segmentation result. It can handle overlapping cases and has lower computational complexity, but it may need to localize accurately, and segment instances, and the segmentation granularity is coarser. In this paper, the Urban Street Scene Instance Segmentation (UISNet) algorithm is proposed. Firstly, the feature extraction network is the foundation of UISNet, which uses EfficientNet as the backbone network. Secondly, MPAFPN is the feature pyramid network part of UISNet, used for multi-scale feature fusion. By using EfficientNet and MPAFPN as the backbone network and bottleneck layers, the accuracy of UISNet is improved by 4% compared to ResNet and FPN. In the inference phase, this paper introduces an innovative dual-branch design that combines top-down and bottom-up strategies. One branch is the bounding box aggregation branch, which generates highdimensional information such as the shape and orientation of bounding boxes based on the FCOS Head. The other branch is the mask decoding branch, which creates mask prediction results. These two branches are fused using the Mask FCN Header to obtain the final instance segmentation result. With this dual-branch design, the model can effectively utilize the information from both top-down and bottom-up approaches, thereby improving the accuracy and robustness of instance segmentation. Through experimental comparisons, the proposed network model in this paper achieves the best performance in terms of accuracy compared to other instance segmentation networks, with an accuracy of 36.28%. Moreover, the proposed model performs better in urban street scenes, enhancing object detection and segmentation and offering more reliable and efficient solutions for applications such as autonomous driving and intelligent transportation. [ABSTRACT FROM AUTHOR]

Pedestrian behavior exhibits high levels of dynamism, and pedestrian trajectories are influenced not only by the pedestrians themselves, but also by interactions with surrounding objects. Efficiently understanding pedestrian motion behavior and modeling its interactions play a crucial role in fields like autonomous driving. Addressing issues related to dynamic feature extraction and interaction modeling in pedestrian trajectory prediction tasks, this paper introduces the conditional pedestrian trajectory prediction network (CSGAT-Net) based on semantic segmentation maps and spatiotemporal graph attention. CSGAT-Net models the physical environment and pedestrian behavior information in the scene as a semantic map, and it leverages graph attention networks to extract pedestrian interaction features. Finally, it predicts pedestrian future trajectories using a variational autoencoder. Comparative experiments conducted on publicly available datasets, ETH and UCY, show that our model exhibits favorable objective evaluation metrics and subjective prediction performance. Particularly, in terms of ADE and FDE metrics, CSGAT-Net outperforms current state-of-the-art methods, indicating that our model can reasonably and accurately predict pedestrian trajectories in different scenarios. [ABSTRACT FROM AUTHOR]

Localization and perception play an important role as the basis of autonomous Unmanned Aerial Vehicle (UAV) applications, providing the internal state of movements and the external understanding of environments. Simultaneous Localization And Mapping (SLAM), one of the critical techniques for localization and perception, is facing technical upgrading, due to the development of embedded hardware, multi-sensor technology, and artificial intelligence. This survey aims at the development of visual SLAM and the basis of UAV applications. The solutions to critical problems for visual SLAM are shown by reviewing state-of-the-art and newly presented algorithms, providing the research progression and direction in three essential aspects: real-time performance, texture-less environments, and dynamic environments. Visual–inertial fusion and learning-based enhancement are discussed for UAV localization and perception to illustrate their role in UAV applications. Subsequently, the trend of UAV localization and perception is shown. The algorithm components, camera configuration, and data processing methods are also introduced to give comprehensive preliminaries. In this paper, we provide coverage of visual SLAM and its related technologies over the past decade, with a specific focus on their applications in autonomous UAV applications. We summarize the current research, reveal potential problems, and outline future trends from academic and engineering perspectives. [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]

With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%. [ABSTRACT FROM AUTHOR]

Adverse weather conditions, such as snow-covered roads, represent a challenge for autonomous vehicle research. This is particularly challenging as it might cause misalignment between the longitudinal axis of the vehicle and the actual direction of travel. In this paper, we extend previous work in the field of autonomous vehicles on snow-covered roads and present a novel approach for side-slip angle estimation that combines perception with a hybrid artificial neural network pushing the prediction horizon beyond existing approaches. We exploited the feature extraction capabilities of convolutional neural networks and the dynamic time series relationship learning capabilities of gated recurrent units and combined them with a motion model to estimate the side-slip angle. Subsequently, we evaluated the model using the 3DCoAutoSim simulation platform, where we designed a suitable simulation environment with snowfall, friction, and car tracks in snow. The results revealed that our approach outperforms the baseline model for prediction horizons ⩾ 2 seconds. This extended prediction horizon has practical implications, by providing drivers and autonomous systems with more time to make informed decisions, thereby enhancing road safety. [ABSTRACT FROM AUTHOR]

Autonomous vehicle can calculate the movement track of surrounding vehicles according to the track prediction algorithm, and make response to reduce driving risk, while the traditional track prediction model will produce large errors in the case of long-term series prediction. To address this issue, this paper proposed a trajectory prediction model based on the Informer algorithm, and used the publicly available dataset NGSIM to conduct experimental analysison. Firstly, it filtered the original data by using symmetric exponential moving average method(sEMA), and added a joint normalization layer to the original Informer encoder to extract features from different vehicles, reducing the motion error between different vehicles, and improving the prediction accuracy by considering the speed information of the vehicle itself and the vehicle movement information of the surrounding environment. Finally, it got the vehicle trajectory distribution at the future time through the decoder. The results show that the trajectory prediction error of the model is less than 0.5 m. Through the analysis of MAE and MSE results of trajectory prediction, when the prediction time exceeds 0.3 s, the trajectory prediction effect of Informer model is obviously better than other algorithms, which verifies the effectiveness of the model and algorithm. [ABSTRACT FROM AUTHOR]

3D object detection, as an essential part of perception, plays a principal role in the autonomous driving system. The cost-competitive monocular 3D object detection has drawn increasing attention recently. However, it still suffers an inferior accuracy especially for occluded objects due to the limited camera view. Inspired by compositional models, in which an object is represented as a combination of multiple components, this paper proposes a new monocular 3D object detection method that decreases the impact of occlusion by utilizing an object's front and side cues. To do this, the features are extracted from a decoupled front and side representation and then fused by an attention-based module to obtain a more consistent feature distribution. An uncertainty-guided depth ensemble based on geometry is further applied to refine the depth prediction. Experiment results demonstrate that as compared to the conventional methods, the proposed method significantly improves the detection performance for occluded objects while still satisfying real-time efficiency, with the Average Precision on 40 recall positions (AP40), respectively, increasing by 10.23% for partly occluded objects and 12.22% for mostly occluded objects in the KITTI benchmark. The codes are released at https://github.com/kagurua/Front-Side-Det [ABSTRACT FROM AUTHOR]

In recent years, 3D object detection based on LiDAR point clouds is a key component of autonomous driving. In pursuit of enhancing the accuracy of 3D point cloud feature extraction and point cloud detection, this paper introduces a novel 3D object detection model, termed as Graph Self-Attention-RCNN (GA-RCNN). This model is designed to integrate voxel information and point location information, enhancing the quality of 3D object proposals while maintaining contextual accuracy. The first stage rectifies the previous approach that relied on local features for preselected boxes, overlooking crucial global contextual information. An improved method is suggested in this work, utilizing BEV to capture long-range dependencies via a cross-attention mechanism. The second stage addresses the overreliance on local neighborhood point feature extraction. The Graph Self-Attention Pooling method is proposed, characterized by its dynamic computation of contribution weights for inputs. This enhances the model's flexibility and generalization performance. Extensive evaluations on KITTI and Waymo datasets demonstrate GA-RCNN's superior accuracy compared to other methods, affirming its efficacy in 3D object detection. [ABSTRACT FROM AUTHOR]

In the research of robot systems, path planning and obstacle avoidance are important research directions, especially in unknown dynamic environments where flexibility and rapid decision makings are required. In this paper, a state attention network (SAN) was developed to extract features to represent the interaction between an intelligent robot and its obstacles. An auxiliary actor discriminator (AAD) was developed to calculate the probability of a collision. Goal-directed and gap-based navigation strategies were proposed to guide robotic exploration. The proposed policy was trained through simulated scenarios and updated by the Soft Actor-Critic (SAC) algorithm. The robot executed the action depending on the AAD output. Heuristic knowledge (HK) was developed to prevent blind exploration of the robot. Compared to other methods, adopting our approach in robot systems can help robots converge towards an optimal action strategy. Furthermore, it enables them to explore paths in unknown environments with fewer moving steps (showing a decrease of 33.9%) and achieve higher average rewards (showning an increase of 29.15%). [ABSTRACT FROM AUTHOR]

Object detection is a crucial component of the perception system in autonomous driving. However, the road scene presents a highly intricate environment where the visibility and characteristics of traffic targets are susceptible to attenuation and loss due to various complex road scenarios such as lighting conditions, weather conditions, time of day, background elements, and traffic density. Nevertheless, the current object detection network must exhibit more learning capabilities when detecting such targets. This also exacerbates the loss of features during the feature extraction and fusion process, significantly compromising the network's detection performance on traffic targets. This paper presents a novel methodology by which to overcome the concerns above, namely HRYNet. Firstly, a dual fusion gradual pyramid structure (DFGPN) is introduced, which employs a two-stage gradient fusion strategy to enhance the generation of more comprehensive multi-scale high-level semantic information, strengthen the interconnection between non-adjacent feature layers, and reduce the information gap that exists between them. HRYNet introduces an anti-interference feature extraction module, the residual multi-head self-attention mechanism (RMA). RMA enhances the target information by implementing a characteristic channel weighting policy, thereby reducing background interference and improving the attention capability of the network. Finally, the detection performance of HRYNet was evaluated by utilizing three datasets: the horizontally collected dataset BDD1000K, the UAV high-altitude dataset Visdrone, and a custom dataset. Experimental results demonstrate that HRYNet achieves a higher mAP_0.5 compared with YOLOv8s on the three datasets, with increases of 10.8%, 16.7%, and 5.5%, respectively. To optimize HRYNet for mobile devices, this study presents Lightweight HRYNet (LHRYNet), which effectively reduces the number of model parameters by 2 million. The results demonstrate that LHRYNet outperforms YOLOv8s in terms of mAP_0.5, with improvements of 6.7%, 10.9%, and 2.5% observed on the three datasets, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we propose a 3D object detection method called MMAF-Net that is based on the multi-view and multi-stage adaptive fusion of RGB images and LiDAR point cloud data. This is an end-to-end architecture, which combines the characteristics of RGB images, the front view of point clouds based on reflection intensity, and the bird's eye view of point clouds. It also adopts a multi-stage fusion approach of "data-level fusion + feature-level fusion" to fully exploit the strength of multimodal information. Our proposed method addresses key challenges found in current 3D object detection methods for autonomous driving, including insufficient feature extraction from multimodal data, rudimentary fusion techniques, and sensitivity to distance and occlusion. To ensure the comprehensive integration of multimodal information, we present a series of targeted fusion methods. Firstly, we propose a novel input form that encodes dense point cloud reflectivity information into the image to enhance its representational power. Secondly, we design the Region Attention Adaptive Fusion module utilizing an attention mechanism to guide the network in adaptively adjusting the importance of different features. Finally, we extend the 2D DIOU (Distance Intersection over Union) loss function to 3D and develop a joint regression loss based on 3D_DIOU and SmoothL1 to optimize the similarity between detected and ground truth boxes. The experimental results on the KITTI dataset demonstrate that MMAF-Net effectively addresses the challenges posed by highly obscured or crowded scenes while maintaining real-time performance and improving the detection accuracy of smaller and more difficult objects that are occluded at far distances. • A novel object detection method is proposed integrating RGB images and LiDAR data. • This study tests the method on the KITTI dataset. • This method tackles highly obscured or crowded scenes for autonomous driving. • This method improves the detection accuracy of smaller and occluded targets far away. [ABSTRACT FROM AUTHOR]

Limitations are identified in the expressive capabilities of the deep feature extraction network employed in deep reinforcement learning (DRL), particularly in complex scenarios. Additionally, learning performance is negatively impacted by compound errors, with consideration given to the potential critical role of sample quality in learning outcomes. Therefore, how to improve the collision avoidance decision-making adaptive and effectiveness for autonomous ships navigating in various scenarios is crucial. To address these issues and overcome data acquisition difficulties, a method called rule-guided vision supervised learning (RGVSL) is proposed in this paper. Through a static collision avoidance decision-making task, a comparison is drawn between a deep feature extraction network and the Nature CNN in DQN, revealing shortcomings in the feature extraction of DRL. Additionally, a collision avoidance decision-making environment with the capability of generalization for maritime encounters is proposed, and the advantages of the method in terms of adaptability and learning cost are validated. Finally, it is demonstrated that the RGVSL method is equivalent to a DQN with γ set to 0, indicating a significant performance improvement without compound errors. Achieving an adaptive decision accuracy of over 90% in various encounter scenarios without retraining, this research substantially reduces learning costs. It can provide innovative and practical solutions for the technological development in the field of autonomous ship collision avoidance decision-making. • Revolutionizes DRL data by using explicit rules for diverse scenarios, boosting model performance. • Exposes Nature CNN's DQN inadequacy, emphasizing the need for effective feature expression in DRL. • RGVSL achieves 90% accuracy in diverse maritime scenarios, cutting retraining costs, enhancing performance. [ABSTRACT FROM AUTHOR]

6DoF camera localization is an important component of autonomous driving and navigation. Deep learning has achieved impressive results in localization, but its robustness in dynamic environments has not been adequately addressed. In this paper, we propose a framework based on hybrid attention mechanism which can be generally applied to existing CNN-based pose regressors to improve their robustness in dynamic environments. Specifically, we propose a novel Transformer Bottleneck (TBo) block including convolution, channel attention, and a position-aware self-attention mechanism, which extracts more geometrically robust features by capturing the corresponding long-term dependencies between pixels. Furthermore, we introduce shuffle attention (SA) before the pose regressor, which integrates feature information in both spatial and channel dimensions, forcing the network to learn geometrically robust features, reducing the effects of dynamic objects and illumination conditions to improve camera localization accuracy. We evaluate our method on commonly benchmarked indoor and outdoor datasets and the experimental results show that our proposed method can significantly improve localization performance compared compare favorably to contemporary pose regressors schemes. In addition, extensive ablation evaluations are conducted to prove the effectiveness of our proposed hybrid attention bottleneck block for pose regression networks. • We propose a novel Transformer Bottleneck block with self-attention and channel attention to overcome the limitations of convolution. This coupling allows them to be optimized in a mutually reinforcing manner, significantly improving fine-grained feature extraction for accurate localization. • We propose a novel end-to-end hybrid attention network for single image localization, which improves the accuracy and robustness of camera localization, especially in dynamic scenes. • We conduct extensive experiments in both indoor and outdoor dataset, which shows that our model performs better than the existing competitive methods. [ABSTRACT FROM AUTHOR]