Deep Learning-Based Obstacle Detection and Classification With Portable Uncalibrated Patterned Light

Cornacchia, Maria; Kakillioglu, Burak; Zheng, Yu; Velipasalar, Senem

doi:10.1109/jsen.2018.2865306

Cited by 31 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most common solutions is to use smartphones equipped with RGB-D or monocular cameras and position sensors (accelerometers, gyroscopes, and magnetometers), as shown in examples [27][28][29]33,42,44]. Another solution is the introduction of infra-red or laser sensors in the acquisition system, a choice made in articles [23,32,45]. For outdoor navigation, GPS is almost always chosen as the navigational support, being easily accessible, cheap, and having very wide coverage.…”

Section: Data-acquisition Toolsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Recent Advances in AI and Vision-Based Methods for Helping and Guiding Visually Impaired People

et al. 2022

View full text Add to dashboard Cite

We present in this paper the state of the art and an analysis of recent research work and achievements performed in the domain of AI-based and vision-based systems for helping blind and visually impaired people (BVIP). We start by highlighting the recent and tremendous importance that AI has acquired following the use of convolutional neural networks (CNN) and their ability to solve image classification tasks efficiently. After that, we also note that VIP have high expectations about AI-based systems as a possible way to ease the perception of their environment and to improve their everyday life. Then, we set the scope of our survey: we concentrate our investigations on the use of CNN or related methods in a vision-based system for helping BVIP. We analyze the existing surveys, and we study the current work (a selection of 30 case studies) using several dimensions such as acquired data, learned models, and human–computer interfaces. We compare the different approaches, and conclude by analyzing future trends in this domain.

show abstract

Section: Data-acquisition Toolsmentioning

confidence: 99%

“…They are often used for pre-training models, before using specific datasets created specifically for the project. This last option was chosen in [31,36,[38][39][40]42,45].…”

Section: Choices Of Datasetsmentioning

confidence: 99%

A Survey on Recent Advances in AI and Vision-Based Methods for Helping and Guiding Visually Impaired People

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the second case, the wheel and the legs are combined in such a way that they can be operated independently based on the requirement [17]. In the review of the literature, various investigations have been carried out on the navigation of mobile robots in indoor [18,19,20,21,22,23,24,25,26] and outdoor environments [20,26]. Simultaneous Localization and Mapping (SLAM) [18,19] and topological map [17] are mainly used to obtain an accurate position of the robot, using sensors, lasers [18] or cameras [24] to detect and recognize obstacles, even relying on a computer vision system such as Tensor Flow TM [19,22].…”

Section: State Of the Artmentioning

confidence: 99%

“…Simultaneous Localization and Mapping (SLAM) [18,19] and topological map [17] are mainly used to obtain an accurate position of the robot, using sensors, lasers [18] or cameras [24] to detect and recognize obstacles, even relying on a computer vision system such as Tensor Flow TM [19,22]. The projects are completely based on the open source software ROS (Robot Operating System) [19,24], some authors propose a neural network to compare images [17,18,20,22,23] by using deep learning techniques [20,23,25]. Other works use a local Wi-Fi network to determine the locations of the devices based on the connection data provided by the access points as the devices move through the environment.…”

Section: State Of the Artmentioning

confidence: 99%

A Review of Indoor Navigation Systems for a Bipedal Robot: Preliminary Results

Ortega-Palacios¹,

Guerrero-García²,

González-Calleros³

2019

RCS

View full text Add to dashboard Cite

The navigation process of human is quite different from robots. Semantic meaning is what we used to model the environment. One of the most important elements human uses to model the environment is the vision. The keyframes are the elements that human use to model the environment. Therefore, we do not need a specific coordinate to move around. We can only use vision to navigate to anywhere we want to go. To take advantage of the concept that human model the environment, we propose a method which imitates the mapping and navigation process of the human. We will use computer vision to do the mapping of the environment and wayfinding to navigate it. The environment model is created with data collected with an odometer that identifies the obstacles on the route of the robot. Our research proposal is to create an algorithm to avoid obstacles. In this paper, we focus on reviewing existing solutions to address our research problem which is a system mounted on a biped robot navigating indoor environments on its own, without having to use preset routines. We have reviewed existing literature and presented it to help future researchers who had the same goal and could be used as a starting point.

show abstract

“…Vision-based obstacle avoidance is one of the areas that can significantly benefit from the introduction of deep learning algorithms [1,2]. Vision-based obstacle avoidance systems are mostly built around classification algorithms.…”

Section: Introductionmentioning

confidence: 99%

CNN-Based Obstacle Avoidance Using RGB-Depth Image Fusion

Mechal

Idrissi

Mesbah

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

In the last few years, deep learning has attracted wide interest and achieved great success in many computer vision related applications, such as image classification, object detection, object tracking, pose estimation and action recognition. One specific application that can greatly benefit from the recent advance of deep learning is robot vision-based obstacle avoidance. Vision-based obstacle avoidance systems are mostly based on classification algorithms. Most of these algorithms use either color images or depth images as the main source of information. In this paper, the aim is to investigate whether using information extracted from both types of images simultaneously would give better performance than using each one separately. To do this, we chose the convolutional neural network (CNN) as the classifier and HSVbased method to achieve the fusion. We tested this approach using two widely used pre-trained CNN architectures, namely Resnet-50 and GoogLeNet using a dataset locally collected. The results indicate that the image fusion-based classification algorithm achieve a higher accuracy (91.3%) than the one based on depth images (80.4%) but lower than the one based on color images (93.7%). These results can be partly explained by the fact that the used classifiers were pre-trained using color image datasets.

show abstract

Deep Learning-Based Obstacle Detection and Classification With Portable Uncalibrated Patterned Light

Cited by 31 publications

References 33 publications

A Survey on Recent Advances in AI and Vision-Based Methods for Helping and Guiding Visually Impaired People

A Survey on Recent Advances in AI and Vision-Based Methods for Helping and Guiding Visually Impaired People

A Review of Indoor Navigation Systems for a Bipedal Robot: Preliminary Results

CNN-Based Obstacle Avoidance Using RGB-Depth Image Fusion

Contact Info

Product

Resources

About