Are you ABLE to perform a life-long visual topological localization?

Structure-Aware Feature Disentanglement With Knowledge Transfer for Appearance-Changing Place Recognition

Long-term visual place recognition (VPR) is challenging as the environment is subject to drastic appearance changes across different temporal resolutions, such as time of the day, month, and season. A wide variety of existing methods address the problem by means of feature disentangling or image style transfer but ignore the structural information that often remains stable even under environmental condition changes. To overcome this limitation, this article presents a novel structure-aware feature disentanglement network (SFDNet) based on knowledge transfer and adversarial learning. Explicitly, probabilistic knowledge transfer (PKT) is employed to transfer knowledge obtained from the Canny edge detector to the structure encoder. An appearance teacher module is then designed to ensure that the learning of appearance encoder does not only rely on metric learning. The generated content features with structural information are used to measure the similarity of images. We finally evaluate the proposed approach and compare it to state-of-the-art place recognition methods using six datasets with extreme environmental changes. Experimental results demonstrate the effectiveness and improvements achieved using the proposed framework. Source code and some trained models will be available at http://www.tianshu.org.cn.

A Systematic Review of Urban Navigation Systems for Visually Impaired People

Blind and Visually impaired people (BVIP) face a range of practical difficulties when undertaking outdoor journeys as pedestrians. Over the past decade, a variety of assistive devices have been researched and developed to help BVIP navigate more safely and independently. In addition, research in overlapping domains are addressing the problem of automatic environment interpretation using computer vision and machine learning, particularly deep learning, approaches. Our aim in this article is to present a comprehensive review of research directly in, or relevant to, assistive outdoor navigation for BVIP. We breakdown the navigation area into a series of navigation phases and tasks. We then use this structure for our systematic review of research, analysing articles, methods, datasets and current limitations by task. We also provide an overview of commercial and non-commercial navigation applications targeted at BVIP. Our review contributes to the body of knowledge by providing a comprehensive, structured analysis of work in the domain, including the state of the art, and guidance on future directions. It will support both researchers and other stakeholders in the domain to establish an informed view of research progress.

Visual Localizer: Outdoor Localization Based on ConvNet Descriptor and Global Optimization for Visually Impaired Pedestrians

Localization systems play an important role in assisted navigation. Precise localization renders visually impaired people aware of ambient environments and prevents them from coming across potential hazards. The majority of visual localization algorithms, which are applied to autonomous vehicles, are not adaptable completely to the scenarios of assisted navigation. Those vehicle-based approaches are vulnerable to viewpoint, appearance and route changes (between database and query images) caused by wearable cameras of assistive devices. Facing these practical challenges, we propose Visual Localizer, which is composed of ConvNet descriptor and global optimization, to achieve robust visual localization for assisted navigation. The performance of five prevailing ConvNets are comprehensively compared, and GoogLeNet is found to feature the best performance on environmental invariance. By concatenating two compressed convolutional layers of GoogLeNet, we use only thousands of bytes to represent image efficiently. To further improve the robustness of image matching, we utilize the network flow model as a global optimization of image matching. The extensive experiments using images captured by visually impaired volunteers illustrate that the system performs well in the context of assisted navigation.

Long-Term Ensemble Learning for Cross-Season Visual Place Classification

This paper addresses the problem of cross-season visual place classification (VPC) from the novel perspective of long-term map learning. Our goal is to enable transfer learning efficiently from one season to the next, at a small constant cost, and without wasting the robot’s available long-term-memory by memorizing very large amounts of training data. To achieve a good tradeoff between generalization and specialization abilities, we employ an ensemble of deep convolutional neural network (DCN) classifiers and consider the task of scheduling (when and which classifiers to retrain), given a previous season’s DCN classifiers as the sole prior knowledge. We present a unified framework for retraining scheduling and we discuss practical implementation strategies. Furthermore, we address the task of partitioning a robot’s workspace into places to define place classes in an unsupervised manner, as opposed to using uniform partitioning, so as to maximize VPC performance. Experiments using the publicly available NCLT dataset revealed that retraining scheduling of a DCN classifier ensemble is crucial in achieving a good balance between generalization and specialization. Additionally, it was found that the performance is significantly improved when using planned scheduling.