Accurate detection of passable regions in images is important for ensuring the safe navigation of unmanned surface vehicles, especially in inland waterways with irregular waterlines and various obstacles. However, the existing methods are susceptible to environmental changes and produce high false-positive rates (FPRs) for confusable textures and complex edge details. We, therefore, propose a collision-free waterway segmentation network based on deep learning such that pixel-level classification results can be obtained. The segmentation accuracy for indistinguishable textures is improved by learning the context dependency of features through a modified context prior, and the detailed refinement of waterlines and small obstacles is achieved via an asymmetric encoder–decoder structure. To learn the features of waterways as comprehensively as possible, data integration and data augmentation are performed on three public datasets. In addition, a new annotated urban waterway dataset called the Dasha River dataset is proposed and made publicly available. The proposed model is tested and cross validated using multiple inland and maritime water segmentation datasets, the results of which show that the model achieves superior performance than the current state of the art with pixel accuracy (PA) of 97.43% and FPR of 1.37%.

Lidar-Visual-Inertial SLAM (LVINS) provides a compelling solution for accurate and robust state estimation and mapping, integrating complementary information from multi-sensor data. However, in the front-end processing of existing LVINS systems, methods based on visual line feature matching typically suffer from low accuracy and are time-consuming. Additionally, the back-end optimization of current multi-sensor fusion SLAM systems is adversely affected by feature association outliers, which constrains further enhancements in localization precision. In the loop closure process, existing lidar loop closure descriptors, relying primarily on 2D information from point clouds, often fall short in complex environments. To effectively tackle these challenges, we introduce the Multi-Modal Feature-based Lidar-Visual-Inertial SLAM framework, abbreviated as MMF-LVINS. Our framework consists of three major innovations. Firstly, we propose a novel coarse-to-fine visual line matching method that utilizes geometric descriptor similarity and optical flow verification, substantially improving both efficiency and accuracy of line feature matching. Secondly, we present a robust iterative optimization approach featuring a newly proposed adaptive loss function. This function is tailored based on the quality of feature association and incorporates graduated non-convexity, thereby reducing the impact of outliers on system accuracy. Thirdly, to augment the precision of lidar-based loop closure detection, we introduce an innovative 3D lidar descriptor that captures spatial, height, and intensity information from the point cloud. We also propose a two-stage place recognition module that synergistically combines both visual and this new lidar descriptor, significantly diminishing cumulative drift. Extensive experimental evaluations on six real-world datasets, including EuRoc, KITTI, NCLT, M2DGR, UrbanNav and UrbanLoco, demonstrate that our MMF-LVINS system achieves superior state estimation accuracy compared to existing state-of-the-art methods. These experiments also validate the effectiveness of our advanced techniques in visual line matching, robust iterative optimization, and enhanced lidar loop closure detection.

In an intelligent transportation system (ITS), the single motion model is not enough to meet the needs of simulation systems (or practical applications) and guarantee good tracking performance for multiple maneuvering extended target tracking (ETT). This paper presents multiple models Poisson multi-Bernoulli mixture (MM-PMBM) filter for extended target tracking to address this problem. To make multiple models transform in an accurate manner, the jump Markov system (JMS) is timely introduced in filtering recursion. After that, the model probability of target is recursively updated and used to estimate the target position. In addition, we derive the closed-form solution to the proposed filter based on the Gamma Gaussian inverse-Wishart (GGIW) implementation. The approach to handling the merging problem of GGIW components via Kullback-Leibler divergence (KLD) minimization is also presented, resulting in better utilization of available components. Simulation results demonstrate that the proposed filter has superior performance in comparison to several state-of-the-art multi-target filters.

In a multi-target tracking (MTT) scenario, the prior knowledge of parameters such as clutter rate and detection probability are usually uncertain or estimated offline from training data. However, significant parameters mismatch in the clutter and detection model will result in biased estimates. In such cases, the ability to adaptively online estimate clutter rate and detection probability is critical in MTT under the random finite sets (RFS) framework. In this paper, we propose a robust Poisson multi-Bernoulli mixture (PMBM) filter that can accommodate model mismatch in clutter rate and detection probability for multiple extended target tracking problems. Moreover, the closed-form solution to the proposed method is derived by the use of Beta and Gamma Gaussian inverse-Wishart (GGIW) distribution, where Beta is used to describe unknown detection probability and GGIW is used to model extended target extension as an ellipse. Simulation results are presented to verify the effectiveness of the proposed method.

The efficient exchange of perception information between vehicles and infrastructure is crucial for implementing vehicle-infrastructure (VI) collaborative intelligent driving. To address the high real-time requirements of VI communication and lack of intelligence and flexibility in VI cooperation, this study proposes an efficient collaborative perception method based on vehicle re-identification for VI collaboration scenarios. The real-time requirements of such scenarios are addressed and a lightweight vehicle re-identification network called ShuffleBNLSH is designed. This network is combined with a hash algorithm to quickly generate ID information for collaborative sensing targets. Based on the state of the VI communication channel, the network can adaptively extract the bit features of the perceived vehicle target, adjust the feature length, and quickly perform feature matching for vehicle target re-identification. To rapidly fuse the VI collaborative perception information combined with the re-identification results and LiDAR 3D perception information from the vehicle and infrastructure, we designed a mini-ICP algorithm that can automatically select feature points and perform point-cloud registration. Experimental results show that the amount of data transmitted by a single target in cooperative sensing can be as small as hundreds of bits during the fusion of sensing targets on the vehicle and infrastructure sides. This reduces the bandwidth requirements for fusing perception targets, accelerates feature transmission and matching, and expands the perception range of VI collaborative autonomous vehicles without GPS information.

On the sea, scene parsing as one of the most basic environmental perception methods for autonomous tasks, helps autonomous devices safely navigate and avoid obstacles. However, most of the existing methods lack real-time performance and have difficulty to accurately detect small obstacles and changeable textures. We therefore propose a real-time scene parsing network for autonomous maritime transportation. Specifically, we first design a lightweight model framework, and then explore three efficient loss functions, such that a balance between accuracy and real-time performance can be achieved. The first loss function is an obstacle weighted loss, which improves the extraction of small obstacles by analyzing the distribution law of obstacles at sea. The second one is a detail loss, which optimizes the detail segmentation at complex contours by emphasizing edge features. The last one is an affinity loss, utilizing the context dependency between features to accurate detect reflections, ripples, and other changeable textures. In addition, a new maritime sense parsing dataset called GBA dataset is proposed and made publicly available. We tested the proposed model on GBA dataset and MaSTr1325 dataset, and the experimental results show that the proposed method achieves superior performance in both segmentation and speed, with mIOU of 94.59%, and FPS of 39.44.