1-Day Learning, 1-Year Localization: Long-Term LiDAR Localization Using Scan Context Image

Kim, Giseop; Park, Byungjae; Kim, Ayoung

doi:10.1109/lra.2019.2897340

Cited by 122 publications

(81 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3), which is available in the NCLT dataset [4]. Similar with the recently developed scan context technique [1], a 2D grid (spatial resolution: 0.05m×0.05m) is imposed on the horizontal plane and datapoints that belong to each grid cell are represented by their maximum normalized truncated height (MNTH). That is, height values of the datapoints are truncated in range [0.5, 1.5], normalized to the range [0, 1], and then max pooled.…”

Section: A Experimental Systemmentioning

confidence: 99%

“…Deep convolutional neural network (DCN) has become a common approach in visual robot self-localization. In a typical self-localization system, a DCN is trained as a visual place classifier from past visual experiences in the target environment [1]. However, its classification performance can be deteriorated when it is tested in a different domain (e.g., times of day, weathers, seasons), due to environmental and optical effects, such as occlusions, dynamic objects, and confusing features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosing Deep Self-localization Network: Accelerated Model-free Subimage-level Diagnosis via Image Synthesis and Relevance Feedback

Kanji¹

2020

Preprint

View full text Add to dashboard Cite

Deep convolutional neural network (DCN) has become a common approach in visual robot self-localization. In a typical self-localization system, a DCN is trained as a visual place classifier from past visual experiences in the target environment. However, its classification performance can be deteriorated when it is tested in a different domain (e.g., times of day, weathers, seasons), due to domain shifts. Therefore, an efficient domain-adaptation (DA) approach to suppress per-domain DA cost would be desired. In this study, we address this issue with a novel ``domain-shift localization (DSL)" technique that diagnosis the DCN classifier with the goal of localizing which region of the robot workspace is significantly affected by domain-shifts. In our approach, the DSL task is formulated as a fault-diagnosis (FD) problem, in which the deterioration of DCN-based self-localization for a given query image is viewed as an indicator of domain-shifts at the imaged region. In our contributions, we address the following non-trivial issues: (1) We address a subimage-level fine-grained DSL task given a typical coarse image-level DCN classifier, in which the target DCN system is queried with a region-of-interest (RoI) masked synthesized query image to diagnosis the RoI region; (2) We extend the DSL task to a relevance feedback (RF) framework, to perform a further query and return improved diagnosis results; and (3) We implement the proposed framework on 3D point cloud imagery -based self-localization and experimentally demonstrate the effectiveness of the proposed algorithm.

show abstract

Section: A Experimental Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Diagnosing Deep Self-localization Network: Accelerated Model-free Subimage-level Diagnosis via Image Synthesis and Relevance Feedback

Kanji¹

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In this line of researches, it is straightforward to train a deep convolutional neural network (DCN), as a visual place classifier, as demonstrated in our previous study [12]. More recently, in [13], DCN has been successfully used for visual place classification in an alternative context of 3D point cloud -based self-localization with the scan-context image representation. However, the current study is different from these existing studies in the following two aspects.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Transfer from Map to DNN: Use of Graph Convolutional Neural Network for Augmenting Visual Robot Self-localization System

takeda¹,

Kanji²

2020

Preprint

View full text Add to dashboard Cite

Graph-based scene model has been receiving increasing attention as a flexible and descriptive scene model for visual robot self-localization. In a typical self-localization application, objects, object features, and object relationship in an environment map are described respectively by nodes, node features, and edges in a scene graph, which are then matched against a query scene graph by a graph matching engine. However, its overhead for computation, storage, and communication, is proportional to the number and feature dimensionality of graph nodes, and can be significant in large-scale applications. In this study, we observe that graph-convolutional neural network (GCN) has a potential to become an efficient tool to train and predict with a graph matching engine. However, it is non-trivial to translate a given visual feature to a proper graph feature that contributes to good self-localization performance. To address this issue, we introduce a new knowledge transfer (KT) framework, which introduces an arbitrary self-localization model as a teacher to train the student, GCN-based self-localization system. Our KT framework enables lightweight storage/communication by using compact teacher's output signals as training data. Results on RobotCar datasets show that the proposed method outperforms existing comparing methods as well as the teacher self-localization system.

show abstract

“…As a key advantage, the outputs of a DCN classifier can be viewed as an extremely compact (i.e., log N -bit), discriminative and semantic description of the input image, which can be directly used for performing database indexing and information retrieval. Recently, the PCD model has achieved considerable success in several state-of-the-art VPR systems [6]. Although the PCD model is effective, it might require a significant maintenance cost in the long-term VPR scenario.…”

Section: Introductionmentioning

confidence: 99%

“…(1) Unlike PCD, an LCD can distinguish exponentially large numbers of different places by combining multiple landmarks. (2) An LCD inherits the discriminative power of an DCN, as evident from previous PCD approaches [6]. (3) The landmark ID is an extremely compact, discriminative, and semantic representation.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Learning and Network Architecture Search for Domain-Adaptive Landmark Detector

Kanji¹

2020

Preprint

View full text Add to dashboard Cite

Fine-tuning a deep convolutional neural network (DCN) as a place-class detector (PCD) is a direct method to realize domain-adaptive visual place recognition (VPR). Although the PCD model is effective, a PCD model requires considerable amount of class-specific training examples and class-set maintenance in long-term large-scale VPR scenarios. Therefore, we propose to employ a DCN as a landmarkclass detector (LCD), which allows to distinguish exponentially large numbers of different places by combining multiple landmarks, and furthermore, allows to select a stable part of the scenes (such as buildings) as landmark classes to reduce the need for class-set maintenance. However, the following important questions remain. 1) How we should mine such training examples (landmark objects) even when we have no domain-specific object detector? 2) How we should fine-tune the architecture and parameters of the DCN to a new domainspecific landmark set? To answer these questions, we present a self-supervised landmark mining approach for collecting pseudo-labeled landmark examples, and then consider the network architecture search (NAS) on the LCD task, which has significantly larger search space than typical NAS applications such as PCD. Extensive verification experiments demonstrate the superiority of the proposed framework to previous LCD methods with hand-crafted architectures and/or non-adaptive parameters, and 90% reduction in NAS cost compared with the naive NAS implementation.

show abstract

1-Day Learning, 1-Year Localization: Long-Term LiDAR Localization Using Scan Context Image

Cited by 122 publications

References 16 publications

Diagnosing Deep Self-localization Network: Accelerated Model-free Subimage-level Diagnosis via Image Synthesis and Relevance Feedback

Diagnosing Deep Self-localization Network: Accelerated Model-free Subimage-level Diagnosis via Image Synthesis and Relevance Feedback

Knowledge Transfer from Map to DNN: Use of Graph Convolutional Neural Network for Augmenting Visual Robot Self-localization System

Self-Supervised Learning and Network Architecture Search for Domain-Adaptive Landmark Detector

Contact Info

Product

Resources

About