Appearance-based place recognition for topological localization

Ulrich, Iwan; Nourbakhsh, Illah

doi:10.1109/robot.2000.844734

Cited by 395 publications

(292 citation statements)

References 18 publications

Supporting

Mentioning

286

Contrasting

Unclassified

Order By: Relevance

“…Work on place recognition in robotics has ranged over matching SIFT features across images [37] or other derived measures of distinctiveness for places such as Fourier signatures [18], subspace representations [11], and color histograms [31]. These methods have the disadvantage of not being able to generalize and also are invariant to perspective mainly through the use of omnidirectional images.…”

Section: Related Workmentioning

confidence: 99%

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

Ranganathan¹

2010

Robotics: Science and Systems VI

View full text Add to dashboard Cite

Abstract-We present PLISS (Place Labeling through Image Sequence Segmentation), a novel technique for place recognition and categorization from visual cues. PLISS operates on video or image streams and works by segmenting it into pieces corresponding to distinct places in the environment. An online Bayesian change-point detection framework that detects changes to model parameters is used to segment the image stream. Unlike current place recognition methods, in addition to using previously learned place models for labeling, PLISS can also detect and learn a previously unknown place or place category in an online manner. Moreover, since both the inferred boundaries of places (change-points) and the place labels are fully probabilistic, they can indicate when the inference is uncertain. New places and categories are detected using a systematic statistical hypothesis testing framework. We present extensive experiments on a large and difficult image dataset. We validate our claims by comparing results obtained using different types of features and by comparing results from PLISS against the state of the art.

show abstract

Section: Related Workmentioning

confidence: 99%

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

Ranganathan¹

2010

Robotics: Science and Systems VI

View full text Add to dashboard Cite

show abstract

“…As a result, another way to estimate the distance to the end is to measure the distance between two images. A convenient way to compare two images is to measure the Jeffrey divergence [44], which is a symmetric version of the Kullback-Leibler divergence:…”

Section: Jeffrey Divergencementioning

confidence: 99%

Autonomous exploration using rapid perception of low-resolution image information

Murali

Birchfield

2011

Auton Robot

View full text Add to dashboard Cite

We present a technique for mobile robot exploration in unknown indoor environments using only a single forward-facing camera. Rather than processing all the data, the method intermittently examines only small 32 × 24 downsampled grayscale images. We show that for the task of indoor exploration the visual information is highly redundant, allowing successful navigation even using only a small fraction of the available data. The method keeps the robot centered in the corridor by estimating two state parameters: the orientation within the corridor, and the distance to the end of the corridor. The orientation is determined by combining the results of five complementary measures, while the estimated distance to the end combines the results of three complementary measures. These measures, which are predominantly information-theoretic, are analyzed independently, and the combined system is tested in several unknown corridor buildings exhibiting a wide variety of appearances, showing the sufficiency of low-resolution visual information for mobile robot exploration. Because the algorithm discards such a large percentage of the pixels both spatially and temporally, processing occurs at an average of 1000 frames per second, thus freeing the processor for other concurrent tasks.

show abstract

“…al employ formal computer vision techniques to determine the epipolar geometry relating the snapshot and current locations and move directly home [12]. Memory-based approaches represent the environment by a set of images and associated home vectors [13,14,15]. Some memory-based approaches employ panoramic imaging systems as we do here (e.g.…”

Section: Visual Homingmentioning

confidence: 99%

“…Some memory-based approaches employ panoramic imaging systems as we do here (e.g. [14,15]). If the agent never has to leave the vicinity of the goal then the feature tracking approach of [16] can be employed for homing (this approach also uses corners as we do here).…”

Section: Visual Homingmentioning

confidence: 99%

Anatomy and Physiology of an Artificial Vision Matrix

Vardy

Oppacher

2004

Biologically Inspired Approaches to Advanced Information Technology

View full text Add to dashboard Cite

Abstract. We present a detailed account of the processing that occurs within a biologically-inspired model for visual homing. The Corner Gradient Snapshot Model (CGSM) initially presented in [1] was inspired by the snapshot model [2] which provided an algorithmic explanation for the ability of honeybees to return to a place of interest after being displaced. The concept of cellular vision is introduced as a constraint on processing. A cellular vision matrix processes visual information using retinotopically arranged layers of low-level processing elements interacting locally. This style of processing reflects general principles known of visual processing throughout the animal kingdom. From a technical standpoint, this style of processing is inherently parallel. Here we describe a cellular vision matrix which implements CGSM and illustrate how this matrix obeys cellular vision. Some new comparative results are presented and it is found that CGSM's performance degrades gracefully with environmental modification and occlusion.

show abstract

Appearance-based place recognition for topological localization

Cited by 395 publications

References 18 publications

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

Autonomous exploration using rapid perception of low-resolution image information

Anatomy and Physiology of an Artificial Vision Matrix

Contact Info

Product

Resources

About