In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during computation. Our method can perform accurate large-scale localization under challenging conditions while remaining the computational constraint. Extensive experiment results indicate that our method sets a new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks.

DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation

Video objection detection is a challenging task because isolated video frames may encounter appearance deterioration, which introduces great confusion for detection. One of the popular solutions is to exploit the temporal information and enhance per-frame representation through aggregating features from neighboring frames. Despite achieving improvements in detection, existing methods focus on the selection of higher-level video frames for aggregation rather than modeling lower-level temporal relations to increase the feature representation. To address this limitation, we propose a novel solution named TF-Blender,which includes three modules: 1) Temporal relation mod-els the relations between the current frame and its neighboring frames to preserve spatial information. 2). Feature adjustment enriches the representation of every neigh-boring feature map; 3) Feature blender combines outputs from the first two modules and produces stronger features for the later detection tasks. For its simplicity, TF-Blender can be effortlessly plugged into any detection network to improve detection behavior. Extensive evaluations on ImageNet VID and YouTube-VIS benchmarks indicate the performance guarantees of using TF-Blender on recent state-of-the-art methods.

TF-Blender: Temporal Feature Blender for Video Object Detection

An increasing number of studies employ virtual reality (VR) to evaluate interactions between autonomous vehicles (AVs) and pedestrians. VR simulators are valued for their cost-effectiveness, flexibility in developing various traffic scenarios, safe conduct of user studies, and acceptable ecological validity. Reviewing the literature between 2010 and 2020, we found 31 empirical studies using VR as a testing apparatus for both implicit and explicit communication. By performing a systematic analysis, we identified current coverage of critical use cases, obtained a comprehensive account of factors influencing pedestrian behavior in simulated traffic scenarios, and assessed evaluation measures. Based on the findings, we present a set of recommendations for implementing VR pedestrian simulators and propose directions for future research.

A Review of Virtual Reality Studies on Autonomous Vehicle–Pedestrian Interaction

Autonomous vehicles integrate complex software stacks for realizing the necessary iterative perception, planning, and action operations. One of the foundational layers of such stacks is the perception one which is comprised of localization, detection, and recognition algorithms for understanding the location and the driving environment around the vehicle. More precisely, localization aims to identify the location of the vehicle on a global coordinate system and is considered one of the most critical parts in the stack since its accuracy and robustness affects the subsequent algorithms of the perception layer and also the following planning and action layers. Due to the rapid and significant interest in self-driving cars, several localization techniques have been proposed with different directions and approaches. Algorithms using prior maps are currently considered the most accurate ones and found almost in all current self-driving car prototypes. Thus, in this paper, we categorize, discuss and analyze the state-of-the-art map-based localization techniques in an attempt to examine their potentials and limitations. We first present techniques and approaches that aim to match prior maps with on-board observations from different sensor modalities. We then review methods that handle the localization problem as a probabilistic one and finally, we also go through the emerging domain of deep-learning localization algorithms and examine their potential in self-driving cars. For all three categories, we provide comparison tables and necessary insights for the optimal localization system design based on different requirements, specifications, and sensor configurations. 

A Survey on Map-Based Localization Techniques for Autonomous Vehicles

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: https://github.com/YanLiqi/HAF.

Hierarchical Attention Fusion for Geo-Localization

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kinds of structures may shadow the GPS signal and lead to inaccurate location results. To address the localization challenges of urban settings, we propose a novel feature voting technique for visual localization. Different from the conventional front-view-based method, our approach employs views from three directions (front, left, and right) and thus significantly improves the robustness of location prediction. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks and modify their architectures properly so that they can be applied for vehicular operation. Extensive field test results indicate that our approach can predict location robustly even in challenging inner-city settings. Our research sheds light on using the visual localization approach to help autonomous vehicles to find accurate location information in a city maze, within a desirable time constraint. The source code is available at github.com/HappyDonkey13/Visual- Localization-for- Autonomous-Driving.

Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kinds of structures may shadow the GPS signal and lead to inaccurate location results. To address the localization challenges of urban settings, we propose a novel feature voting technique for visual localization. Different from the conventional front-view-based method, our approach employs views from three directions (front, left, and right) and thus significantly improves the robustness of location prediction. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks and modify their architectures properly so that they can be applied for vehicular operation. Extensive field test results indicate that our approach can predict location robustly even in challenging inner-city settings. Our research sheds light on using the visual localization approach to help autonomous vehicles to find accurate location information in a city maze, within a desirable time constraint.

Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze.

HAVIT: A VR-Based Platform to Support Human-Autonomous Vehicle Interaction Study

The study developed Human-Autonomous Vehicle Interaction Testbed (HAVIT), a VR-based platform that enables researchers and designers to quickly configure AV interaction scenarios and evaluate their design concepts during the design process in a holistic and consistent manner. The HAVIT presents an efficient workflow that combines the tasks of Scenario Configuration, Experimental Setting

A Virtual Reality Framework to Measure Psychological and Physiological Responses of the Self-Driving Car Passengers

Abstract Users are often interested in exploring ranks over time data to compare the performance or ranking of multiple observations with respect to each other. However, predominant visualization techniques suffer from a high cognitive load due to visual clutter. We propose Colorslope, a hybrid of Tufte’s slope graph and temporal heatmap, to depict ranks over time in one graph while maintaining an overview and details with scalability. Colorslope combines both canonical visualization methods’ complementary benefits: depicting overall trends and enabling the estimation of detailed values. We evaluated the efficacy and effectiveness of Colorslope by comparing it with a standard bump chart and temporal heatmap on various data sizes. We conclude that Colorslope contributes by (1) allowing users to identify extremes of the data and rate of change effectively in a relatively large number of series; (2) allowing the visualization to have better scalability in a larger amount of data (e.g., 30 ∼ 50) than a bump chart; and (3) allowing users to gain a better estimate of data values than a heatmap. For a certain size of ranks over time data, Colorslope provides an alternative solution to visualize multiple time series simultaneously that provides both an overview and a certain level of detail. 

https://link.springer.com/content/pdf/10.1007/s44267-023-00008-9.pdf

Colorslope: a balanced visualization of overview and details on ranks over time

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Xiaolei Guo

Author Tools

Chat about Author