Vehicular vision system with trailer assist and traffic detection functions
A vehicular trailer assist system includes a camera disposed at a rear portion of a vehicle and viewing at least rearward of the vehicle, and an electronic control unit (ECU), which includes an image processor for processing image data captured by the camera. The ECU executes a deep neural network (DNN) to determine presence of a trailer in image data captured by the camera. The DNN, responsive to processing of image data captured by the camera, determines a position of a trailer in the captured image data. The DNN, responsive to determining the position of the trailer, classifies the trailer into a trailer category. The ECU, responsive to the DNN determining the position of the trailer and based on the classification, generates an output to autonomously control the vehicle to align the vehicle with the trailer and navigate the vehicle toward the trailer.
1. A vehicular trailer assist system, the vehicular trailer assist system comprising:
a camera disposed at a rear portion of a vehicle equipped with the vehicular trailer assist system, the camera viewing at least rearward of the vehicle;
an electronic control unit (ECU) comprising electronic circuitry and associated software;
wherein the electronic circuitry of the ECU comprises an image processor for processing image data captured by the camera;
wherein the ECU executes a deep neural network (DNN) to determine, via processing image data captured by the camera, presence of a trailer rearward of the vehicle and viewed by the camera;
wherein the DNN, with the trailer not currently hitched to the vehicle and spaced from the vehicle, and responsive to processing image data captured by the camera, determines a position of the trailer relative to the vehicle;
wherein the DNN, responsive to determining the position of the trailer, classifies the trailer into one of a plurality of trailer categories; and
wherein the ECU, responsive to the DNN determining the position of the trailer relative to the vehicle, generates an output based on the trailer classification to autonomously control the vehicle to align the vehicle with the trailer and navigate the vehicle toward the trailer.
2. The vehicular trailer assist system of claim 1 , wherein the DNN comprises a single-shot detection deep convolutional neural network.
3. The vehicular trailer assist system of claim 1 , wherein the DNN is trained to classify the trailer into one of the plurality of trailer categories via image data representative of trailer categories comprising at least one selected from the group consisting of (i) box trailers, (ii) horse trailers, (iii) camper trailers, and (iv) utility trailers.
4. The vehicular trailer assist system of claim 1 , wherein the DNN is trained to determine the presence of the trailer via image data representative of trailers with orientations between 60 degrees and −60 degrees with respect to the vehicle.
5. The vehicular trailer assist system of claim 1 , wherein the DNN is trained to determine the presence of the trailer via image data representative of trailers at distances between 0 meters and 10 meters from the vehicle.
6. The vehicular trailer assist system of claim 1 , wherein the DNN is trained to determine the presence of the trailer via processing of image data captured by the camera in different environments.
7. The vehicular trailer assist system of claim 6 , wherein the different environments comprise at least two selected from the group consisting of (i) a sunny environment, (ii) a cloudy environment, (iii) a rainy environment and (iv) a shadowy environment.
8. The vehicular trailer assist system of claim 1 , wherein the DNN is trained to determine the presence of the trailer via image data representative of road types comprising at least one selected from the group consisting of (i) asphalt roads, (ii) concrete roads, (iii) snowy roads, (iv) dry roads, and (v) wet roads.
9. The vehicular trailer assist system of claim 1 , comprising a second camera disposed at a front portion of the vehicle, the second camera viewing at least forward of the vehicle;
wherein the DNN is trained to determine presence of a traffic light in image data captured by the second camera;
wherein the DNN, responsive to processing image data captured by the second camera, determines a position of a traffic light in the captured image data; and
wherein the DNN, responsive to determining the position of the traffic light, determines a status of the traffic light.
10. The vehicular trailer assist system of claim 9 , wherein the status of the traffic light comprises at least one selected from the group consisting of (i) an illuminated color of the traffic light, (ii) an illuminated symbol of the traffic light, and (iii) an orientation of the traffic light with respect to the vehicle.
11. The vehicular trailer assist system of claim 9 , wherein the ECU, responsive to receiving the status of the traffic light from the DNN, determines presence of a traffic jam.