System and method for sensing road surface condition
Disclosed are a road surface condition sensing system and method. The road surface condition sensing system includes an acoustic sensing unit for sensing an acoustic signal of a floor of a vehicle, and a control unit for calculating a feature vector by Fourier transforming the sensed acoustic signal, comparing the calculated feature vector with a plurality of previously stored feature vectors and returning a first feature vector having the smallest relative distance to the calculated feature vector, and outputting a road surface condition corresponding to the first feature vector.
1. A road surface condition sensing system comprising:
an acoustic sensing unit sensing an acoustic signal of a lower portion of a vehicle; and
a control unit calculating a feature vector by Fourier transforming the sensed acoustic signal, selecting one feature vector having the smallest relative distance to the calculated feature vector among a plurality of previously stored feature vectors by comparing the calculated feature vector with the plurality of previously stored feature vectors, and outputting a road surface condition corresponding to the selected one feature vector,
wherein the feature vector is calculated by generating a cepstrum based on the sensed acoustic signal, extracting feature points based on the generated cepstrum, and calculating the feature vector based on the extracted feature points, and
wherein the plurality of previously stored feature vectors are stored as neurons in a database of a neuromorphic system.
2. The road surface condition sensing system according to claim 1 , wherein the control unit provides the outputted road surface condition to an autonomous drive control system of the vehicle.
3. The road surface condition sensing system according to claim 2 , wherein the autonomous drive control system of the vehicle comprises at least one of a forward collision warning system (FCW), an autonomous emergency braking system (AEBS), an adaptive cruise control system (ACC), and a rear-end collision warning system (RCW).
4. The road surface condition sensing system according to claim 1 , wherein the control unit learns the calculated feature vector and additionally input the calculated feature vector into the plurality of previously stored feature vectors.
5. A road surface condition sensing system comprising:
an acoustic sensing unit sensing an acoustic signal of a lower portion of a vehicle;
a neuromorphic system in which a plurality of neurons storing at least one pattern vector are connected by a parallel bus; and
a control unit calculating a feature vector by Fourier transforming a sensed acoustic signal, inputting the generated feature vector to the neuromorphic system, returning one feature vector having the smallest relative distance to the inputted feature vector among a plurality of neurons stored in the neuromorphic system, and outputting a road surface condition corresponding to the one feature vector,
wherein the feature vector is calculated by generating a cepstrum based on the sensed acoustic signal, extracting feature points based on the generated cepstrum, and calculating the feature vector based on the extracted feature points, and
wherein the plurality of previously stored feature vectors are stored as neurons in a database of a neuromorphic system.
6. A road surface condition sensing method comprising:
sensing, by an acoustic sensing unit, an acoustic signal of a lower portion of a vehicle;
calculating, by a control unit, a feature vector by Fourier transforming the sensed acoustic signal;
selecting, by the control unit, one feature vector having the smallest relative distance to the calculated feature vector among a plurality of previously stored feature vectors by comparing the calculated feature vector with the plurality of previously stored feature vectors; and
outputting, by the control unit, a road surface condition corresponding to the selected one feature vector,
wherein the feature vector is calculated by generating a cepstrum based on the sensed acoustic signal, extracting feature points based on the generated cepstrum, and calculating the feature vector based on the extracted feature points, and
wherein the plurality of previously stored feature vectors are stored as neurons in a database of a neuromorphic system.
7. The road surface condition sensing method according to claim 6 , further comprising providing, by the control unit, the outputted road surface condition to an autonomous drive control system of the vehicle.
8. The road surface condition sensing method according to claim 6 , further comprising:
learning, by the control unit, the calculated feature vector; and
additionally inputting, by the control unit, the calculated feature vector into the plurality of previously stored feature vectors.