A Vision-Based Wayfinding System for Visually Impaired People Using Situation Awareness and Activity-Based Instructions

. 2017 Aug 16;17(8):1882. doi: 10.3390/s17081882

Algorithm 1: The proposed trajectory recording algorithm.
Input: Gyroscope sensor G, Accelerometer sensor AC, destination D
Output: Stack S that contains the set of instructions, I(A, SC, $θ_{c u r r e n t}, P)$ , where A, SC, $θ$ , P are the variables for the action, step count, compass direction, and position, respectively.
Procedure:
1.	Initialize A ← null, $θ_{p r e v i o u s}$ , $θ_{c u r r e n t} \leftarrow 0 °$ , SC ← 0, P( $P_{x}$ , $P_{y}$ ) ← (0,0);
2.	// Determine the action type If AC < 0.03, then A ← Stop
3.	else if $\| θ_{c u r r e n t} - θ_{p r e v i o u s} \| > 15 °$ then A ← Turn
4.	else A ← Go-straight
5.	//Estimate the instruction parameters according to the action type if A is Go-straight, then SC, $P_{x}$ , $P_{y}$ is updated by the following equation: $S C \leftarrow S C + 1, P_{x} \leftarrow S C \cdot \cos θ_{c u r r e n t}, P_{y} \leftarrow S C \cdot \sin θ_{c u r r e n t}$
6.	else if A is Turn, then $θ_{c u r r e n t} \leftarrow θ_{p r e v i o u s}$
7.	PushI(A, SC, $θ_{c u r r e n t}, P)$ to S
8.	//check if the current positioning information is the destination (the positioning information is obtained by recognizing the QR codes) if the current location is destination, then terminate
9.	else Go to Line 2