SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights

Milford, Michael; Wyeth, Gordon

doi:10.1109/icra.2012.6224623

Cited by 839 publications

(811 citation statements)

References 16 publications

Supporting

Mentioning

807

Contrasting

Order By: Relevance

“…Badino et al [6] also analyzed the localization performance across seasonal variations using a topometric approach. Similarly, Milford et al [17] developed a robust localization algorithm adding temporal filtering to an image template matching technique. The authors show results on data acquired over different seasons and weather conditions.…”

Section: Related Workmentioning

confidence: 99%

“…We also analyze three environmental parameters: time of day (morning, midday, afternoon, dusk), sunlight (sunny, cloudy), and environment (commercial, residential, rural). We do not consider seasonal variations and adverse weather conditions such as fog, rain, and snow, or nighttime driving, which have been studied previously [6], [17], [24].…”

Section: B Data Setsmentioning

confidence: 99%

“…For example, visual SLAM algorithms (e.g., [7], [8], [17]) use localization to dynamically build up a map and detect loop closures, while commercial automotive navigation systems and visual localization algorithms (e.g., topometric localization [6]) determine a vehicle's position with respect to a prior map.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Understanding how camera configuration and environmental conditions affect appearance-based localization

Bansal

Badino

Huber

2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

View full text Add to dashboard Cite

Abstract-Localization is a central problem for intelligent vehicles. Visual localization can supplement or replace GPSbased localization approaches in situations where GPS is unavailable or inaccurate. Although visual localization has been demonstrated in a variety of algorithms and systems, the problem of how to best configure such a system remains largely an open question. Design choices, such as "where should the camera be placed?" and "how should it be oriented?" can have substantial effect on the cost and robustness of a fielded intelligent vehicle. This paper analyzes how different sensor configuration parameters and environmental conditions affect visual localization performance with the goal of understanding what causes certain configurations to perform better than others and providing general principles for configuring systems for visual localization. We ground the investigation using extensive field testing of a visual localization algorithm, and the data sets used for the analysis are made available for comparative evaluation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: B Data Setsmentioning

confidence: 99%

See 1 more Smart Citation

Understanding how camera configuration and environmental conditions affect appearance-based localization

Bansal

Badino

Huber

2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

View full text Add to dashboard Cite

show abstract

“…In contrast, our solution is monocular and uses different cameras for acquisition and reference database. In [22], the localization is achieved by recognizing temporal coherent sequences of local best matches. These local best matches are based on a Sum of Absolute Difference (SAD) on resolution-reduced and patch-normalized images between last acquire image and M previous images.…”

Section: Related Workmentioning

confidence: 99%

Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning

Barz¹,

Thome

Cord

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

This paper addresses the problem of absolute visual ego-localization of an autonomous vehicle equipped with a monocular camera that has to navigate in an urban environment. The proposed method is based on a combination of: 1) a Hidden Markov Model (HMM) exploiting the spatio-temporal coherency of acquired images and 2) learnt metrics dedicated to robust visual localization in complex scenes, such as streets. The HMM merges odometric measurements and visual similarities computed from specific (local) metrics learnt for each image of the database. To achieve this goal, we define some constraints so that the distance between a database image and a query image representing the same scene is smaller than the distance between this query image and other neighbor images of the database. Successful experiments, conducted using a freely available geo-referenced image database, reveal that the proposed method significantly improves results: the mean localization error is reduced from 12.9m to 3.9m over a 11km path.

show abstract

“…Methods that address the LCD problem span from matching sequences of images [11,12], transforming images to becoming invariant against common scene changes such as shadows [13,14], learning how environments change over time and predicting these changes in image space [15−17], building up LCD hypotheses over time [18,19], and building a map of experiences that cover the different appearances of a place over time [20].…”

Section: Loop Closure Detectionmentioning

confidence: 99%

Matching-range-constrained real-time loop closure detection with CNNs features

Bai

Wang

Zhangt

et al. 2016

2016 IEEE International Conference on Real-Time Computing and Robotics (RCAR)

View full text Add to dashboard Cite

The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional neural networks (CNNs) have outperformed state-of-the-art solutions that use traditional hand-crafted features in many computer vision and pattern recognition applications. After the great success of CNNs, there has been much interest in applying CNNs features to robotic fields such as visual LCD. Some researchers focus on using a pre-trained CNNs model as a method of generating an image representation appropriate for visual loop closure detection in SLAM. However, there are many fundamental differences and challenges involved in character between simple computer vision applications and robotic applications. Firstly, the adjacent images in the dataset of loop closure detection might have more resemblance than the images that form the loop closure. Secondly, real-time performance is one of the most critical demands for robots. In this paper, we focus on making use of the feature generated by CNNs layers to implement LCD in real environment. In order to address the above challenges, we explicitly provide a value to limit the matching range of images to solve the first problem; meanwhile we get better results than state-of-the-art methods and improve the real-time performance using an efficient feature compression method.

show abstract

SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights

Cited by 839 publications

References 16 publications

Understanding how camera configuration and environmental conditions affect appearance-based localization

Understanding how camera configuration and environmental conditions affect appearance-based localization

Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning

Matching-range-constrained real-time loop closure detection with CNNs features

Contact Info

Product

Resources

About