Artificial intelligence using convolutional neural network with Hough transform

A non-transitory computer-readable medium having instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to:

• store a convolutional neural network comprising three or more convolution layers, a Hough Transform (HT) layer, and a Transposed Hough Transform (THT) layer, arranged such that a first subset of at least one of the three or more convolution layers precede the HT layer, a second subset of at least one of the three or more convolution layers follow the HT layer and precede the THT layer, and a third subset of at least one of the three or more convolution layers follow the THT layer, wherein the HT layer converts an output of the first subset from a first space into a second space, and wherein the THT layer converts an output of the second subset from the second space into the first space;
• and,
• for each of a plurality of input images, apply the convolutional neural network to the input image to perform semantic image segmentation to the input image, so as to produce an output image representing a result of the semantic image segmentation.