Localization of Mobile Robots with Topological Maps and Classification with Reject Option using Convolutional Neural Networks in Omnidirectional Images

Silva, Suane Pires P. da; Nóbrega, Raul Victor Medeiros da; Medeiros, Aldísio G.; Marinho, Leandro Balby; Almeida, Jefferson S.; Gupta, Deepak

doi:10.1109/ijcnn.2018.8489328

Cited by 8 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Garcia-Fidalgo and Ortiz [15] presented a review about the main approaches considered to carry out topological mapping and localization through visual information in the last years. recently, da Silva et al [16] propose a localization and navigation approach for mobile robots using topological maps and using CNN to obtain descriptors from omnidirectional images.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Localization in Topological Models Under Varying Illumination Using Holistic Visual Descriptors

et al. 2019

View full text Add to dashboard Cite

In this paper, a hierarchical localization framework within indoor environments is proposed and evaluated, considering severe variations of the illumination conditions. The only source of information both to build a model of the environment and to solve the localization problem is a catadioptric vision system, which is mounted on the mobile robot. The images captured by this system are processed globally to obtain holistic descriptors. The position of the robot is estimated by comparing these descriptors with the information contained in a topological visual model, which is previously created using a clustering approach and is composed of a hierarchy of layers. Compacting the information via clustering proves to be an efficient alternative to estimate the position of the robot hierarchically and with robustness. The proposed localization strategy is tested with some sets of panoramic images, captured in large indoor environments under real operating conditions, including illumination changes that change substantially the appearance of the scenes. The results show a reasonable tradeoff computation time-accuracy when the localization is addressed in a hierarchical way.

show abstract

Section: Introductionmentioning

confidence: 99%

Hierarchical Localization in Topological Models Under Varying Illumination Using Holistic Visual Descriptors

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Pais et al [30] used reinforcement learning to predict pedestrians’ positions by projecting the 3D bounding boxes of pedestrians onto panoramic images. There are also methods which only use adequate planar convolutional filters to fit the rotation distortions [31,32].…”

Section: Related Workmentioning

confidence: 99%

Grid Based Spherical CNN for Object Detection from Panoramic Images

2019

Sensors

View full text Add to dashboard Cite

Recently proposed spherical convolutional neural networks (SCNNs) have shown advantages over conventional planar CNNs on classifying spherical images. However, two factors hamper their application in an objection detection task. First, a convolution in S2 (a two-dimensional sphere in three-dimensional space) or SO(3) (three-dimensional special orthogonal group) space results in the loss of an object’s location. Second, overlarge bandwidth is required to preserve a small object’s information on a sphere because the S2/SO(3) convolution must be performed on the whole sphere, instead of a local image patch. In this study, we propose a novel grid-based spherical CNN (G-SCNN) for detecting objects from spherical images. According to input bandwidth, a sphere image is transformed to a conformal grid map to be the input of the S2/SO3 convolution, and an object’s bounding box is scaled to cover an adequate area of the grid map. This solves the second problem. For the first problem, we utilize a planar region proposal network (RPN) with a data augmentation strategy that increases rotation invariance. We have also created a dataset including 600 street view panoramic images captured from a vehicle-borne panoramic camera. The dataset contains 5636 objects of interest annotated with class and bounding box and is named as WHU (Wuhan University) panoramic dataset. Results on the dataset proved our grid-based method is extremely better than the original SCNN in detecting objects from spherical images, and it outperformed several mainstream object detection networks, such as Faster R-CNN and SSD.

show abstract

“…Hence, the proposed scheme is liable to be faster than Zhang et al 24 Figure 11(a) suggests that the proposed method follows the shortest path as compared to Li et al 33 Learning-based approaches are presented to localize and navigate a mobile robot in refs. [25][26][27][28][29][30]. In contrast to these work, this paper provides a unique solution to achieve both estimation (all three body-to-camera parameters) and robot control in a single loop.…”

Section: Comparisonmentioning

confidence: 99%

“…Machine learning-based approaches for mobile robot localization are presented in refs. [25][26][27][28][29][30]. Marinho et al 26 present an approach to localize the mobile robot via a classifier with reject option.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Position-Based Visual Servoing of a Mobile Robot with an Automatic Extrinsic Calibration Scheme

Sharma¹,

Shukla²,

Behera³

et al. 2019

Robotica

View full text Add to dashboard Cite

SUMMARYIn this paper, we present and implement a novel approach for position-based visual servoing. The challenge of controlling the mobile robot while simultaneously estimating the camera to mobile robot transformation is solved. This is achieved using gradient descent (GD)-based estimation and the sliding-mode approach. The GD approach allows online parameter estimation for controlling the robot to achieve a desired position and orientation. The adaptive nature of the parameters demonstrates the robustness of the system. In contrast to existing work, the proposed technique achieves both estimation and control tasks in a single experiment. Simulation and experimental results are provided to validate the performance of the proposed scheme.

show abstract

Localization of Mobile Robots with Topological Maps and Classification with Reject Option using Convolutional Neural Networks in Omnidirectional Images

Cited by 8 publications

References 35 publications

Hierarchical Localization in Topological Models Under Varying Illumination Using Holistic Visual Descriptors

Hierarchical Localization in Topological Models Under Varying Illumination Using Holistic Visual Descriptors

Grid Based Spherical CNN for Object Detection from Panoramic Images

Position-Based Visual Servoing of a Mobile Robot with an Automatic Extrinsic Calibration Scheme

Contact Info

Product

Resources

About