Vehicle Trajectory Estimation Based on Fusion of Visual Motion Features and Deep Learning

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle’s trajectory using sparse optical flow and tracks vehicles in the surrounding environment using convolutional neural networks. Optical flow is used to measure the linear and angular velocity of the host vehicle. The convolutional neural networks are used to measure target vehicles’ positions relative to the host vehicle using image-based detections. Finally, the system fuses host and target vehicle trajectories in the world coordinate system using the velocity of the host vehicle and the target vehicles’ relative positions with the aid of an Extended Kalman Filter (EKF). We implement and test our model quantitatively in simulation and qualitatively on real-world test video. The results show that the algorithm is superior to state-of-the-art sequential state estimation methods such as visual SLAM in performing accurate global localization and trajectory estimation for host and target vehicles.

Globolocalization versus Russophony: the search for an alternative to hybridity and cross-cultural situation

The relevance of the research topic is due to social contradictions caused by the proliferation of glovolocalization, transculturation and translocality projects in the global culture, associated with the active implementation of the manipulative practices of adaptation of linguistic and cultural locuses to the global market. Hybridity as a basic property of postmodernity requires the interpretation of these projects on the basis of new methodological premises: philosophy of media, structuralism and poststructuralism, critical theory. The neoliberal hehemony lays in the basis of these projects an imaginary tolerant cross-cultural phenomenon, which often makes it difficult to identify the deepest paradoxes of their repressiveness. The central project of cross-culture today is glocalism. The aim of the research is to carry out a comparative analysis of global localization and Russophony as alternative (pragmatic and ethical) ways of resolving hybrid conflicts between cultures and finding ways of dialogue at the global (world) and local (Russian) levels. As a result of the analysis of materials on glocalization, the author comes to the conclusion about the existence of a number of legitimate contradictions in glocalism, the main ones of which are: the contradiction between capital and labor, time and space; the contradiction between ethical universalism and the economic particularism of the market; the contradiction between the imaginary freedom of horizontal communication and the asymmetric governing structure of organized haos; the contradiction between transnational companies and the state, which risks losing its national and civilizational subjectivity; the contradiction between the promises to the regions from transnational companies and the real possibilities of the regions; double codes in relation to protest movements in globalist and anti-globalist regions. As an alternative to glocalization in relation to Russia and a number of other countries, including Ukraine, we propose a solidarity project of Russophony as a mechanism of linguistic solidarization of cultural subjects on civilizational, cultural and symbolic grounds.

Explicit feature disentanglement for visual place recognition across appearance changes

In the long-term deployment of mobile robots, changing appearance brings challenges for localization. When a robot travels to the same place or restarts from an existing map, global localization is needed, where place recognition provides coarse position information. For visual sensors, changing appearances such as the transition from day to night and seasonal variation can reduce the performance of a visual place recognition system. To address this problem, we propose to learn domain-unrelated features across extreme changing appearance, where a domain denotes a specific appearance condition, such as a season or a kind of weather. We use an adversarial network with two discriminators to disentangle domain-related features and domain-unrelated features from images, and the domain-unrelated features are used as descriptors in place recognition. Provided images from different domains, our network is trained in a self-supervised manner which does not require correspondences between these domains. Besides, our feature extractors are shared among all domains, making it possible to contain more appearance without increasing model complexity. Qualitative and quantitative results on two toy cases are presented to show that our network can disentangle domain-related and domain-unrelated features from given data. Experiments on three public datasets and one proposed dataset for visual place recognition are conducted to illustrate the performance of our method compared with several typical algorithms. Besides, an ablation study is designed to validate the effectiveness of the introduced discriminators in our network. Additionally, we use a four-domain dataset to verify that the network can extend to multiple domains with one model while achieving similar performance.

A global screening identifies chromatin-enriched RNA-binding proteins and the transcriptional regulatory activity of QKI5 during monocytic differentiation

Background Cellular RNA-binding proteins (RBPs) have multiple roles in post-transcriptional control, and some are shown to bind DNA. However, the global localization and the general chromatin-binding ability of RBPs are not well-characterized and remain undefined in hematopoietic cells. Results We first provide a full view of RBPs’ distribution pattern in the nucleus and screen for chromatin-enriched RBPs (Che-RBPs) in different human cells. Subsequently, by generating ChIP-seq, CLIP-seq, and RNA-seq datasets and conducting combined analysis, the transcriptional regulatory potentials of certain hematopoietic Che-RBPs are predicted. From this analysis, quaking (QKI5) emerges as a potential transcriptional activator during monocytic differentiation. QKI5 is over-represented in gene promoter regions, independent of RNA or transcription factors. Furthermore, DNA-bound QKI5 activates the transcription of several critical monocytic differentiation-associated genes, including CXCL2, IL16, and PTPN6. Finally, we show that the differentiation-promoting activity of QKI5 is largely dependent on CXCL2, irrespective of its RNA-binding capacity. Conclusions Our study indicates that Che-RBPs are versatile factors that orchestrate gene expression in different cellular contexts, and identifies QKI5, a classic RBP regulating RNA processing, as a novel transcriptional activator during monocytic differentiation.

Map-less long-term localization in complex industrial environments

Purpose This paper aims to study the localization problem for autonomous industrial vehicles in the complex industrial environments. Aiming for practical applications, the pursuit is to build a map-less localization system which can be used in the presence of dynamic obstacles, short-term and long-term environment changes. Design/methodology/approach The proposed system contains four main modules, including long-term place graph updating, global localization and re-localization, location tracking and pose registration. The first two modules fully exploit the deep-learning based three-dimensional point cloud learning techniques to achieve the map-less global localization task in large-scale environment. The location tracking module implements the particle filter framework with a newly designed perception model to track the vehicle location during movements. Finally, the pose registration module uses visual information to exclude the influence of dynamic obstacles and short-term changes and further introduces point cloud registration network to estimate the accurate vehicle pose. Findings Comprehensive experiments in real industrial environments demonstrate the effectiveness, robustness and practical applicability of the map-less localization approach. Practical implications This paper provides comprehensive experiments in real industrial environments. Originality/value The system can be used in the practical automated industrial vehicles for long-term localization tasks. The dynamic objects, short-/long-term environment changes and hardware limitations of industrial vehicles are all considered in the system design. Thus, this work moves a big step toward achieving real implementations of the autonomous localization in practical industrial scenarios.

High-precision and robust localization system for mobile robots in complex and large-scale indoor scenes

High-precision and robust localization is the key issue for long-term and autonomous navigation of mobile robots in industrial scenes. In this article, we propose a high-precision and robust localization system based on laser and artificial landmarks. The proposed localization system is mainly composed of three modules, namely scoring mechanism-based global localization module, laser and artificial landmark-based localization module, and relocalization trigger module. Global localization module processes the global map to obtain the map pyramid, thus improve the global localization speed and accuracy when robots are powered on or kidnapped. Laser and artificial landmark-based localization module is employed to achieve robust localization in highly dynamic scenes and high-precision localization in target areas. The relocalization trigger module is used to monitor the current localization quality in real time by matching the current laser scan with the global map and feeds it back to the global localization module to improve the robustness of the system. Experimental results show that our method can achieve robust robot localization and real-time detection of the current localization quality in indoor scenes and industrial environment. In the target area, the position error is less than 0.004 m and the angle error is less than 0.01 rad.

OverlapNet: a siamese network for computing LiDAR scan similarity with applications to loop closing and localization

Localization and mapping are key capabilities of autonomous systems. In this paper, we propose a modified Siamese network to estimate the similarity between pairs of LiDAR scans recorded by autonomous cars. This can be used to address both, loop closing for SLAM and global localization. Our approach utilizes a deep neural network exploiting different cues generated from LiDAR data. It estimates the similarity between pairs of scans using the concept of image overlap generalized to range images and furthermore provides a relative yaw angle estimate. Based on such predictions, our method is able to detect loop closures in a SLAM system or to globally localize in a given map. For loop closure detection, we use the overlap prediction as the similarity measurement to find loop closure candidates and integrate the candidate selection into an existing SLAM system to improve the mapping performance. For global localization, we propose a novel observation model using the predictions provided by OverlapNet and integrate it into a Monte-Carlo localization framework. We evaluate our approach on multiple datasets collected using different LiDAR scanners in various environments. The experimental results show that our method can effectively detect loop closures surpassing the detection performance of state-of-the-art methods and that it generalizes well to different environments. Furthermore, our method reliably localizes a vehicle in typical urban environments globally using LiDAR data collected in different seasons.