Vision‐based Simultaneous Localization and Mapping in Changing Outdoor Environments

Milford, Michael; Vig, Eleonora; Scheirer, Walter J.; Cox, David D.

doi:10.1002/rob.21532

Cited by 32 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This long‐term place recognition approach is exemplified by SeqSLAM (Milford & Wyeth, ), which matches sequences of images acquired under extremely varied conditions, matching from day to night, rain to sunshine. SeqSLAM has been extended to include better handling of different vehicle speeds (Pepperell, Corke, & Milford, ) and match‐verification (Milford, Vig, Scheirer, & Cox, ). Similarly, Naseer, Spinello, Burgard, & Stachniss () robustly select matches under severe seasonal changes using the data‐association graph for full datasets.…”

Section: Related Workmentioning

confidence: 99%

Summary Maps for Lifelong Visual Localization

et al. 2015

View full text Add to dashboard Cite

Robots that use vision for localization need to handle environments that are subject to seasonal and structural change, and operate under changing lighting and weather conditions. We present a framework for lifelong localization and mapping designed to provide robust and metrically accurate online localization in these kinds of changing environments. Our system iterates between offline map building, map summary, and online localization. The offline mapping fuses data from multiple visually varied datasets, thus dealing with changing environments by incorporating new information. Before passing these data to the online localization system, the map is summarized, selecting only the landmarks that are deemed useful for localization. This Summary Map enables online localization that is accurate and robust to the variation of visual information in natural environments while still being computationally efficient. We present a number of summary policies for selecting useful features for localization from the multisession map, and we explore the tradeoff between localization performance and computational complexity. The system is evaluated on 77 recordings, with a total length of 30 kilometers, collected outdoors over 16 months. These datasets cover all seasons, various times of day, and changing weather such as sunshine, rain, fog, and snow. We show that it is possible to build consistent maps that span data collected over an entire year, and cover day‐to‐night transitions. Simple statistics computed on landmark observations are enough to produce a Summary Map that enables robust and accurate localization over a wide range of seasonal, lighting, and weather conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Summary Maps for Lifelong Visual Localization

et al. 2015

View full text Add to dashboard Cite

show abstract

“…To evaluate the generality of the automatic coverage selection process, we performed a second set of experiments with the local feature-based technique previously described as the localization front-end. Due to the extremely challenging appearance change present in much of the Nearmaps datasets, the feature-based approach only produced competitive performance on datasets 4, 7a and 7b, a result mirroring what has been observed in a range of other feature-based localization systems [46]. However, for these environments where the underlying front-end was functional, the calibra- Fig.…”

Section: Automatic Coverage Selection Evaluation Using a Feature-bmentioning

confidence: 63%

“…shifts and is similar to the regional-MAC descriptor outlined in [45] or the patch verification technique described in [46] IV. EXPERIMENTAL SETUP This section describes the experimental setup, including the dataset acquisition and key parameter values.…”

Section: A Optimal Coverage Calibration Proceduresmentioning

confidence: 99%

Automatic Coverage Selection for Surface-Based Visual Localization

Mount

Dawes

Milford

2019

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Localization is a critical capability for robots, drones and autonomous vehicles operating in a wide range of environments. One of the critical considerations for designing, training or calibrating visual localization systems is the coverage of the visual sensors equipped on the platforms. In an aerial context for example, the altitude of the platform and camera field of view plays a critical role in how much of the environment a downward facing camera can perceive at any one time. Furthermore, in other applications, such as on roads or in indoor environments, additional factors such as camera resolution and sensor placement altitude can also affect this coverage. The sensor coverage and the subsequent processing of its data also has significant computational implications. In this paper we present for the first time a set of methods for automatically determining the trade-off between coverage and visual localization performance, enabling the identification of the minimum visual sensor coverage required to obtain optimal localization performance with minimal compute. We develop a localization performance indicator based on the overlapping coefficient, and demonstrate its predictive power for localization performance with a certain sensor coverage. We evaluate our method on several challenging real-world datasets from aerial and ground-based domains, and demonstrate that our method is able to automatically optimize for coverage using a small amount of calibration data. We hope these results will assist in the design of localization systems for future autonomous robot, vehicle and flying systems.

show abstract

“…The RatSLAM algorithm draws upon the current understanding of spatial encoding in rat brains to perform learning and recall of maps [5,6,7]. The structure of the RatSLAM system is shown in Fig.1.…”

Section: Ratslammentioning

confidence: 99%

Vision/Odometer Autonomous Navigation Based on RatSLAM for Land Vehicles

He¹,

Zhang²,

Lian³

et al. 2015

Proceedings of the 2015 International Conference on Advances in Mechanical Engineering and Industrial Informatics

View full text Add to dashboard Cite

This paper discusses the design of computer vision and odometer integrated autonomous navigation algorithm based on RatSLAM system for land vehicles. The research aims at testing the effectiveness of a vision/odometer bio-inspired navigation approach for land vehicle applications. Images and odometer measurements are inputted into the RatSLAM system. Odometer data can be used to improve the robustness of RatSLAM system significantly. The proposed system has been verified on real vision/odometer data collected in land vehicle tests. Campus round road experiments illustrate that the algorithm is effective and robust.

show abstract

Vision‐based Simultaneous Localization and Mapping in Changing Outdoor Environments

Cited by 32 publications

References 33 publications

Summary Maps for Lifelong Visual Localization

Summary Maps for Lifelong Visual Localization

Automatic Coverage Selection for Surface-Based Visual Localization

Vision/Odometer Autonomous Navigation Based on RatSLAM for Land Vehicles

Contact Info

Product

Resources

About