Featureless Visual Processing for SLAM in Changing Outdoor Environments

Milford, Michael; George, Ashley

doi:10.1007/978-3-642-40686-7_38

Cited by 14 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The descriptor type was based on the local feature descriptor BRISK • The training-free localization system was compared to FAB-MAP on a benchmark FAB MAP dataset [4] to ensure a fair comparison between whole-image and local feature methods The descriptor type GIST [17] was used • The probabilistic vs. non-probabilistic was performed on a dataset that demonstrated highly variable conditions [27] including sun, rain and darkness. Images were compared using absolute differences (SAD) between pixels.…”

Section: Methodsmentioning

confidence: 99%

“…Localization algorithms need to be able to operate online, using only data that has already been observed to draw conclusions about place recognition matches. In practice, this means that a heuristic model such as [27] must preto determine whether two images represent the same location or not. Figure 5 displays the precision against threshold for the incremental probabilistic lines) and a heuristic model (blue lines).…”

Section: Probabilistic Vs Non-probabilistic Localizationmentioning

confidence: 99%

“…was originally presented in [27] and images captured by a webcam mounted on a that was driven around a varied environment of parkland and university campus. The route different and challenging environmental conditions: sunrise, sunny weather, rainy for sample images).…”

Section: Probabilistic Localization Incremental Probability Localizatmentioning

confidence: 99%

“…The images were processed in the same manner as described in the original paper [27] cropped to the upper half only and resolution reduced to 48×24 pixels. The images were patch normalized over To process the St Lucia images, the whole-image was used, but using the in place of BRIEF.…”

Section: Probabilistic Vs Non-probabilistic Localizationmentioning

confidence: 99%

“…he images were processed in the same manner as [27]. The images were cropped to the upper half only and resolution reduced to ixels.…”

Section: Probabilistic Localization Incremental Probability Localizatmentioning

confidence: 99%

See 4 more Smart Citations

Towards training-free appearance-based localization: Probabilistic models for whole-image descriptors

Lowry

Wyeth

Milford

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Whole image descriptors have been shown to be remarkably robust to perceptual change especially compared to local features. However, whole-image-based localization systems typically rely on heuristic methods for determining appropriate matching thresholds in a particular environment. These environment-specific tuning requirements and the lack of a meaningful interpretation of arbitrary thresholds limit the general applicability of these systems. In this paper we present a Bayesian model of probability for whole-image descriptors that can be seamlessly integrated into localization systems designed for probabilistic visual input. We demonstrate this method using CAT-Graph, an appearance-based visual localization system originally designed for a FAB-MAP-style probabilistic input. We show that using whole-image descriptors as visual input extends CAT-Graph's functionality to environments that experience a greater amount of perceptual change. We also present a method of estimating whole-image probability models in an online manner, removing the need for a prior training phase. We show that this online, automated training method can perform comparably to pretrained, manually tuned local descriptor methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Probabilistic Vs Non-probabilistic Localizationmentioning

confidence: 99%

Section: Probabilistic Localization Incremental Probability Localizatmentioning

confidence: 99%

Section: Probabilistic Vs Non-probabilistic Localizationmentioning

confidence: 99%

“…he images were processed in the same manner as [27]. The images were cropped to the upper half only and resolution reduced to ixels.…”

Section: Probabilistic Localization Incremental Probability Localizatmentioning

confidence: 99%

See 3 more Smart Citations

Towards training-free appearance-based localization: Probabilistic models for whole-image descriptors

Lowry

Wyeth

Milford

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

Bioinspired Spike‐Based Hippocampus and Posterior Parietal Cortex Models for Robot Navigation and Environment Pseudomapping

Casanueva-Morato,

Ayuso-Martinez,

Dominguez-Morales

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

The brain has great capacity for computation and efficient resolution of complex problems, far surpassing modern computers. Neuromorphic engineering seeks to mimic the basic principles of the brain to develop systems capable of achieving such capabilities. In the neuromorphic field, navigation systems are of great interest due to their potential applicability to robotics, although these systems are still a challenge to be solved. This work proposes a spike‐based robotic navigation and environment pseudomapping system formed by a bioinspired hippocampal memory model connected to a posterior parietal cortex (PPC) model. The hippocampus is in charge of maintaining a representation of an environment state map, and the PPC is in charge of local decision‐making. This system is implemented on the SpiNNaker hardware platform using spiking neural networks. A set of real‐time experiments are applied to demonstrate the correct functioning of the system in virtual and physical environments on a robotic platform. The system is able to navigate through the environment to reach a goal position starting from an initial position, avoiding obstacles and mapping the environment. To the best of the authors’ knowledge, this is the first implementation of an environment pseudomapping system with dynamic learning based on a bioinspired hippocampal memory.

show abstract

Vision‐based Simultaneous Localization and Mapping in Changing Outdoor Environments

Milford

Vig

Scheirer

et al. 2014

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

For robots operating in outdoor environments, a number of factors, including weather, time of day, rough terrain, high speeds, and hardware limitations, make performing vision‐based simultaneous localization and mapping with current techniques infeasible due to factors such as image blur and/or underexposure, especially on smaller platforms and low‐cost hardware. In this paper, we present novel visual place‐recognition and odometry techniques that address the challenges posed by low lighting, perceptual change, and low‐cost cameras. Our primary contribution is a novel two‐step algorithm that combines fast low‐resolution whole image matching with a higher‐resolution patch‐verification step, as well as image saliency methods that simultaneously improve performance and decrease computing time. The algorithms are demonstrated using consumer cameras mounted on a small vehicle in a mixed urban and vegetated environment and a car traversing highway and suburban streets, at different times of day and night and in various weather conditions. The algorithms achieve reliable mapping over the course of a day, both when incrementally incorporating new visual scenes from different times of day into an existing map, and when using a static map comprising visual scenes captured at only one point in time. Using the two‐step place‐recognition process, we demonstrate for the first time single‐image, error‐free place recognition at recall rates above 50% across a day‐night dataset without prior training or utilization of image sequences. This place‐recognition performance enables topologically correct mapping across day‐night cycles.

show abstract

Featureless Visual Processing for SLAM in Changing Outdoor Environments

Cited by 14 publications

References 18 publications

Towards training-free appearance-based localization: Probabilistic models for whole-image descriptors

Towards training-free appearance-based localization: Probabilistic models for whole-image descriptors

Bioinspired Spike‐Based Hippocampus and Posterior Parietal Cortex Models for Robot Navigation and Environment Pseudomapping

Vision‐based Simultaneous Localization and Mapping in Changing Outdoor Environments

Contact Info

Product

Resources

About