Indoor assistance for visually impaired people using a RGB-D camera

Vlaminck, Michiel; Hiep, Quang Luong; Hoang, Van Nam; Vu, Hai; Veelaert, Peter; Philips, Wilfried

doi:10.1109/ssiai.2016.7459200

Cited by 15 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In work [7], deep learning technique is used to classify obstacles using Convolutional Neural Network (CNN). In [8], RGBD camera is used to observe the environment whereself-localization is implemented by a novel camera tracking approach usingdepth and color information in an ICP-based algorithm. In this work, the obstacle classification is performed by extractinggeometrical properties of the obstacles.…”

Section: State Of Art On Obstacle Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Multi-Layer Perceptron-Based Obstacle Classification Method From Partial Visual Information: Application to the Assistance of Visually Impaired People

2020

View full text Add to dashboard Cite

How to navigate safely, recognize encountered obstacles, and move independently from one location to another in unknown environments are some of the challenges that face visually impaired people. By proposing a solution towards overcoming these challenges, this work will be of most importance to visually impaired people. In this work, we propose a consistent, reliable and robust smartphone-based method to classify obstacles in unknown environments from partial visual information based on computer vision and machine learning techniques. Our proposed method handles high levels of noise and bad resolution in frames captured from a phone camera. In addition, our proposed method offers maximum flexibility to users and use the least expensive equipment possible. Moreover, by leveraging on deep-learning techniques, the proposed method enables semantic categorization in order to classify obstacles and increase the awareness of the explored environment. The efficiency of the work has been experimentally measured on a variety of experiments studies on different complex scenes. It records high accuracy of [90.2 % ]. INDEX TERMS Image analysis, image classification, supervised learning, mobile applications.

show abstract

Section: State Of Art On Obstacle Classificationmentioning

confidence: 99%

“…As for [12], its major drawback is that it considers only static obstacles. The systems in [6]- [8], [10], [12] use Kinect sensor which must be mounted on the body of the user. On the contrary, our proposed method will not impose any extra load on the user other than the use of a smartphone.…”

Section: State Of Art On Obstacle Classificationmentioning

confidence: 99%

Deep Multi-Layer Perceptron-Based Obstacle Classification Method From Partial Visual Information: Application to the Assistance of Visually Impaired People

2020

View full text Add to dashboard Cite

show abstract

“…Ultrasonic signals are sent in three directions (left, right, front). Vlaminck et al [9] have used RGB-D camera to perceive environment. They implement three things: obstacle detection, obstacle classification and self-localization.…”

Section: Related Workmentioning

confidence: 99%

Obstacle Detection in Indoor Environment for Visually Impaired Using Mobile Camera

Rahman

Ullah

2018

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Abstract. Obstacle detection can improve the mobility as well as the safety of visually impaired people. In this paper, we present a system using mobile camera for visually impaired people. The proposed algorithm works in indoor environment and it uses a very simp le technique of using few p re-stored floor images. In indoor environ ment all unique floor types are considered and a single image is stored for each unique floor type. These floor images are considered as reference images. The algorithm acquires an input image frame and then a region of interest is selected and is scanned for obstacle using pre-stored floor images. The algorithm compares the present frame and the next frame and co mpute mean square error of the two frames. If mean square error is less than a threshold value α then it means that there is no obstacle in the next frame. If mean square error is greater than α then there are t wo possibilit ies; either there is an obstacle or the floor type is changed. In order to check if the floor is changed, the algorithm co mputes mean square error of next frame and all stored floor types. If minimu m of mean square error is less than a threshold value α then flour is changed otherwise there exist an obstacle. The proposed algorithm works in real-time and 96% accuracy has been achieved.

show abstract

“…In order to process image information from a unknown environment, knowledge of the ground plane, and hence the position and orientation of the camera, is fundamental [16]- [20]. Indeed, most computer vision algorithms implicitly assume knowledge of the ground plane (e.g., that the ground is at the ''bottom'' of the scene [17], [21], [22] or is the largest plane [23], [25], [26]). However, in complex environments with unknown sensor placement, the ground plane may not be the largest visible plane (e.g., many objects on the ground) or at the ''bottom'' of the scene (e.g., overhead perspectives).…”

Section: Introductionmentioning

confidence: 99%

Perspective Independent Ground Plane Estimation by 2D and 3D Data Analysis

Zhang

Czarnuch

2020

IEEE Access

View full text Add to dashboard Cite

Identifying the orientation and location of a camera placed arbitrarily in a room is a challenging problem. Existing approaches impose common assumptions (e.g. the ground plane is the largest plane in the scene, the camera roll angle is zero). We present a method for estimating the ground plane and camera orientation in an unknown indoor environment given RGB-D data (colour and depth) from a camera with arbitrary orientation and location assuming that at least one person can be seem smoothly moving within the camera field of view with their body perpendicular to the ground plane. From a set of RGB-D data trials captured using a Kinect sensor, we develop an approach to identify potential ground planes, cluster objects in the scenes and find 2D Scale-Invariant Feature Transform (SIFT) keypoints for those objects, and then build a motion sequence for each object by evaluating the intersection of each object's histogram in three dimensions across frames. After finding the reliable homography for all objects, we identify the moving human object by checking the change in the histogram intersection, object dimensions and the trajectory vector of the homgraphy decomposition. We then estimate the ground plane from the potential planes using the normal vector of the homography decomposition, the trajectory vector, and the spatial relationship of the planes to the other objects in the scene. Our results show that the ground plane can be successfully detected, if visible, regardless of camera orientation, ground plane size, and movement speed of the human. We evaluated our approach on our own data and on three public datasets, robustly estimating the ground plane in all indoor scenarios. Our successful approach substantially reduces restrictions on a prior knowledge of the ground plane, and has broad application in conditions where environments are dynamic and cluttered, as well as fields such as automated robotics, localization and mapping.

show abstract

Indoor assistance for visually impaired people using a RGB-D camera

Cited by 15 publications

References 10 publications

Deep Multi-Layer Perceptron-Based Obstacle Classification Method From Partial Visual Information: Application to the Assistance of Visually Impaired People

Deep Multi-Layer Perceptron-Based Obstacle Classification Method From Partial Visual Information: Application to the Assistance of Visually Impaired People

Obstacle Detection in Indoor Environment for Visually Impaired Using Mobile Camera

Perspective Independent Ground Plane Estimation by 2D and 3D Data Analysis

Contact Info

Product

Resources

About