MOBILITY OF VISUALLY IMPAIRED PEOPLE

Computer-vision is a field that deals with how computes can gain understanding from digital images or videos captured from cameras to obtain information about the environment. In other words, it focuses on replicating parts of the complexity of the human vision system and enabling computers to identify and process objects in images and videos in the same way that humans do.

Our sense of vision has developed over millions of years of evolution, and coupled with the visual cortex has been one of the key ingredients for the ascension of humans as the dominant species on our planet. Hence, there is a grave need for solutions which can help people with impaired vision. In the context of assistive technology, mobility takes the meaning of “moving safely, gracefully, and comfortably”. Although blind people are more in need of mobility aids, low-vision individuals may also occasionally trip onto unseen small obstacles or steps, especially in poor lighting conditions.

Computer vision based visual assistive technology is used to assist visually impaired people. The assistive technology help the visually impaired by providing them with a greater independence. By enabling them with their day-to-day activities .Computer Vision can assist blind people in overcoming their needs.

Needs of Visually Impaired Person:

Below are some requirements on what a visually impaired person needs from technology:

They need:

• To Recognize objects around them

For example: If something fell on the ground, they can’t find it easily. (example :keys on ground)

• To Recognize faces and people

When a visually impaired person enters a space they don’t know who is inside and they need to sit up for the opposite people to greet and identify themselves.

Application: SIMI is an object recognition app for the visually impaired. This app can answer questions, scan barcodes and call or send messages to emergency contacts. SIMI can not only recognise what/who is in front of you but can even recognise a familiar face. Meaning SIMI could be like “Hey James” and you’d know exactly who it was approaching you.

• Fast text reader

Imagine you’re blind and you wish to shop for milk, how would you check the expiry date, how would you create sure you didn’t pass that date later.

Application: Finger reader — it is an accurate and efficient text reading device which makes use of the computer vision technology to scan the printed text. Optical character recognition(OCR) engine is used to extract the words. OCR extracts one word at a time and uttered to the user.

• Support navigating, avoiding obstacles and crossing the road

One of the most important problems — even in top world cities

Technology support is required to assist the blind walk fast and safe to his/her target destination, specifically assistance is needed to provide warning if you’re getting ready to hit an obstacle and want to step down the curb. Another problem is knowing when to cross the road. Technology can help detecting the colour of the stoplight and also the surrounding movements to support the blind pedestrian decision.

Application: Tyflos-It is an electronic travel aid which basically consists of two mini cameras attached to a pair of conventional eye-glasses, a 2D tactile display vibration array) , attached to an elastic vest worn on the user’s abdomen, an ear-speaker and a microphone. Using Tyflos visually impaired can locate obstacles for a safe navigation.

• Scene Explainer

Ever thought if you’re blind how would you see images and videos, for those that lost their sight in their mid life and know what’s a sky and the way does a river seem like, it might be very nice for a system to be ready to explain scenes.

Do you know which is the common method used to fulfil the needs of visually impaired? Let’s have a look at this method.

A common method used to fulfil their needs is Object recognition :

Object recognition for visually impaired people(based on feature extraction)

1.Object recognition could be a classical problem for visually impaired: the task of determining if the image data contains a particular object and it’s noted that general Object recognition approaches exploit features extraction.

2. Visual substitution systems generally exploit one camera to capture image data. Recognition is then performed supported various features extracted from that data. Additionally, features extraction is the process by which certain features of interest within a picture are detected and represented for further processing. It’s a critical step in most computer vision and image processing solutions because it marks the transition from pictorial to non pictorial (alphanumerical, usually quantitative) data representation. Types of features that may be extracted from image depend upon the kind of image (e.g. binary, gray-level, or color), the amount of granularity (entire image or individual regions) desired, and therefore the context of the appliance.The features extraction process should be precise, in order that the identical features are extracted on two images showing the identical object.

The object recognition can be divided into three main categories:

1)Object detection: this function in the important goal because here we need to detect object of daily use and identify them by adding an auditory system. Below image illustrates object detection.

2) Obstacle detection: In this case, obstacle such as the wall, the table, the door,chair the bed,etc can be detected. This function can be addressed by adding sound alert. Below image illustrates obstacle detection.

3) Distance information: this function can be addressed by employing a sensor that calculates the distance between the camera and the obstacle; also we can anticipate the distance in terms of the best object detection and the position of object after several tests.

Indoor navigation:

Indoor navigation is a major challenge for people with visual impairments, who often lack access to visual cues such as informational signs, landmarks and structural features that people with normal vision rely on for wayfinding. Visually Impaired (VI) and blind people always need assistance and walking support systems in their daily life.

Computer vision provides a reliable solution to assist visually impaired in their indoor navigation providing them a correct route with obstacle avoidance.

Wearable SLAM system:

It is intend to use the SLAM problem from mobile robots for pedestrians (visually impaired and blind). In this case the problem has to be addressed in a different manner, due to the different movement conditions. Pedestrians have a much more complex odometry than mobile robots. They differ in the type of movements and degrees of freedom. The laser scanner position with mobile robots is stable compared to the surface. This cannot be guaranteed for human beings. Furthermore, the human body is specific to each person, as is motion. Thus, the challenge is to extract the odometry for each pedestrian and to obtain stable laser scanner data. To extract precise pedestrian odometry, step length and orientation, a foot mounted PDR will be used. The pedestrian is exploring an unknown environment, so there won’t be a fixed starting point. For land marks observations the pedestrian will be equipped with a short range laser scanner in the low back area. The decision to place it in this body regions is due to, its stability and to avoid interference from the hand by using the white cane. To obtain horizontal laser scans, the raw data requires processing with the IMU data and projection onto the horizontal plane. With the recollected data from the sensors it is possible, by using the Extended Kalman Filter, to achieve a precise localization. Simultaneously with the scanner reading a map of the environment will be construct by using the above mentioned grid mapping. The pedestrian can also interact with the system, by adding important landmarks or preferred locations in the environment, mean while he is exploring it. Once the user has a map and his position is been tracked in the before unknown environment. The visually impaired person is able to navigate through it, by receiving commands via audio from the system. Data processing will be accomplished with wearable computing devices, so there will be total independence of any main computer or network.

Have you ever heard assistive technology is helping blind people in mobility? let’s know about this with the help of examples.

Orientation and mobility (O&M) are a vital component for daily and independent living in people with visual loss. Few example are as follows:

1. Walking or long cane: it’s designed primarily for mobility tool to spot objects within the path of the users. The length of the cane depends upon the height of the user, and frequently, it extends from the ground up to between sternum and under the chin when user is standing upright.

2. Children’s walking cane: This cane works same as long walking cane but designated to be used by children. it’s shorter than long cane.

3. Symbol or identification cane: Symbol cane is primarily accustomed notify the public that the person encompasses a low vision person. It’s often shorter and lighter than others. It intends to not be used as a body support or to detect obstacles on the ground or as a mobility tool. Red and white color banded symbol cane highlight visual impairment.

4. Guide cane: This can be a short and thin cane but longer than symbol cane usually extending from the ground to the user’s waist when standing upright with more limited mobility function. The guide cane is used to scan for kerbs and steps by individual with some residual visual function. it’s usually used diagonally across the body for defence and warning the user of obstacles in low contrast or in dark.

5. Support cane: The white support cane is meant to supply physical support to the user. This tool is heavy and strong and has limited role as a mobility device.

6. Green cane: it’s utilized in some countries to designate the user as low vision while the white cane user is blind.

Image Courtesy:

[1] https://www.intechopen.com/ [2]https://images.app.goo.gl/EMGUsPkuLMNBwQEW7 [3]https://images.app.goo.gl/xcUUAmSaL64Tg8GK9

REFERENCES:

[1] Balu N. Ilag and Yogesh Athave, “A Design review of Smart Stick for the Blind Equipped with Obstacle Detection and Identification using Artificial Intelligence” in International Journal of Computer Applications, Volume 182 — №49

[2] Akshay Santosh Jadhav, Pooja Chandrakant Jadhav, Vrushikesh Madhukar Patil, “Blind Guider — A Smart Blind Stick” in International Journal of Engineering Research in Computer Science and Engineering, Volume 5, Issue 4

[3] Ram Tirlangi and Ch. Ravi Sankar, “Electronic Travel Aid for Visually Impaired People based on Computer Vision and Sensor Nodes using Raspberry Pi” in Indian Journal of Science and Technology, Vol 9(47)

[4]https://3sidedcube.com/object-recognition-app-sight-loss/

AUTHORS: Rujuta Kumbhare, Ankita Karwankar,Shraddha kshirsagar, Riya kaktikar.

We hope you’ve enjoyed reading this blog. In case of queries, Please feel free to drop your queries in the comment section.