Abstract: A traffic light perception method, a vehicle control method, a device, a medium and a vehicle are provided to solve the problem of accurately sensing a status of a traffic light. The method includes: sensing and recognizing a current image frame of the traffic light to obtain a lamp head shape and a color of a currently lit single light in the traffic light; determining a traffic indication direction of a virtual light corresponding to the traffic light based on the lamp head shape of the single light; and determining a color of the traffic indication direction based on the color of the single light, to form a virtual light. According to the above method, a status of a traffic light can be accurately obtained without relying on a high-definition map, which improves the safety and reliability of vehicle driving.

Abstract: A method for detecting an occluded image. The method includes: after an image is captured by a camera, obtaining the image as an image to be detected; inputting the image to be detected into a trained occluded-image detection model, the occluded-image detection model is trained based on original occluded images and non-occluded images by using a trained data feature augmentation network; determining whether the image to be detected is an occluded image based on the occluded-image detection model; and outputting an image detection result.

Abstract: A method for detecting a finger occlusion image includes: N first original occlusion images and M first non-occlusion images are acquired, and first training data set is generated based on first original occlusion images and first non-occlusion images; first training is performed, based on first training data set, on neural network model for detection of finger occlusion image; L second original occlusion images and K second non-occlusion images are acquired, and second training data set is generated based on second original occlusion images and second non-occlusion images; linear classifier in neural network model having completed first training is replaced with iterative training module to form finger occlusion image detection model; second training is performed on finger occlusion image detection model based on second training data set; image to be detected is input into trained finger occlusion image detection model, to determine whether image to be detected is finger occlusion image.

Abstract: A method for detecting an occluded image. The method includes: after an image is captured by a camera, obtaining the image as an image to be detected; inputting the image to be detected into a trained occluded-image detection model, the occluded-image detection model is trained based on original occluded images and non-occluded images by using a trained data feature augmentation network; determining whether the image to be detected is an occluded image based on the occluded-image detection model; and outputting an image detection result.

Abstract: A method for detecting a finger occlusion image includes: N first original occlusion images and M first non-occlusion images are acquired, and first training data set is generated based on first original occlusion images and first non-occlusion images; first training is performed, based on first training data set, on neural network model for detection of finger occlusion image; L second original occlusion images and K second non-occlusion images are acquired, and second training data set is generated based on second original occlusion images and second non-occlusion images; linear classifier in neural network model having completed first training is replaced with iterative training module to form finger occlusion image detection model; second training is performed on finger occlusion image detection model based on second training data set; image to be detected is input into trained finger occlusion image detection model, to determine whether image to be detected is finger occlusion image.