Automation in Automobiles: Power Seat
28 Dec 2009-pp 158-160
TL;DR: This paper deals with automating the seat of an automobile through the use of a microcontroller and image processing toolkit of Matlab thereby reducing manual effort in adjusting the seat.
Abstract: The current seat adjustment mechanism in automobiles is quite tedious and outdated and has its toll on the body of the person while adjusting the seat to his/her comfortable position. Every person has his/her comfortable seat position, so every time a person sits in an automobile, adjustment of the seat has to be done according to the comfort of the individual, this is tiresome and at times annoying. This paper deals with automating the seat of an automobile through the use of a microcontroller and image processing toolkit of Matlab thereby reducing manual effort in adjusting the seat. The adjustment of the seat can be done horizontally, vertically as well as the inclination of the seat can be changed by controlling the direction of rotation and speed of the motors provided in the seat. The parameters of the comfortable position for different individuals are stored in the database and the seat is adjusted to a person’s comfortable position by using face recognition algorithm which is used to link the parameters of a person’s comfortable position stored in the database to his/her face.
Citations
More filters
01 Feb 2020
TL;DR: Reducing manual effort in seat adjustment by automating the seat adjustment process by using face recognition, which deals with the movement of the seat in horizontal, vertical and inclination directions by rotating the motors fitted within the seat.
Abstract: The existing mechanism of driver seat adjustment in the automobile industry is outdated. It adversely affects the body of the driver when he/she adjusts the seat for a comfortable position. The comfortable seat position is different for each person. This research work explains about reducing manual effort in seat adjustment by automating the seat adjustment process by using face recognition. The seat adjustment process deals with the movement of the seat in horizontal, vertical and inclination directions by rotating the motors fitted within the seat. The comfort seat position of a driver contains three parameters for three directions of seat movement. Those parameters are different for different drivers and they are stored in the memory. When the camera recognizes a face, the seat is adjusted to his/her comfortable position which is saved in the database.
6 citations
Cites methods from "Automation in Automobiles: Power Se..."
...Akshay Lahiry developed a Seat adjustment system using Face recognition [1]....
[...]
01 May 2017
TL;DR: A CAN-LIN bridge is proposed that will connect two chips of above mentioned protocols by providing passenger comfort and Driver Assistance using MCP2021 & MCP2551.
Abstract: The expansion of automation in automobiles have paved way for connecting subsystems by using communication protocols CAN and LIN. CAN provides serial communication that efficiently supports distributed real time support with a high level of security. LIN is designed to communicate at low data rates at low cost. The main contribution of this paper is that a CAN-LIN bridge is proposed that will connect two chips of above mentioned protocols. There by providing passenger comfort (back rest lean forward-backward and seat slide forward-backward) and Driver Assistance (wiper operation) using MCP2021 & MCP2551.
3 citations
Cites background or methods from "Automation in Automobiles: Power Se..."
...The parameters of [3] that are related to comfort ability of different...
[...]
...The seat adjustment mechanism presented in [3] deals with automating the seat of an automobile through the use of microcontroller and image processing toolkit of MATLAB....
[...]
References
More filters
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.
Abstract: We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image space-if the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions. The eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the eigenface technique for tests on the Harvard and Yale face databases.
11,674 citations
15 Apr 1996
TL;DR: A face recognition algorithm which is insensitive to gross variation in lighting direction and facial expression is developed and the proposed “Fisherface” method has error rates that are significantly lower than those of the Eigenface technique when tested on the same database.
Abstract: We develop a face recognition algorithm which is insensitive to gross variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face under varying illumination direction lie in a 3-D linear subspace of the high dimensional feature space — if the face is a Lambertian surface without self-shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's Linear Discriminant and produces well separated classes in a low-dimensional subspace even under severe variation in lighting and facial expressions. The Eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed “Fisherface” method has error rates that are significantly lower than those of the Eigenface technique when tested on the same database.
2,428 citations