Abstract: An image processing method of the present disclosure may include receiving a scanned image, and processing the received image through an octave convolution-based neural network to output a high-quality image and an edge image for the received image. The octave convolution-based neural network may include a plurality of octave encoder blocks and a plurality of octave decoder blocks. Each octave encoder block may include an octave convolutional layer, and may be configured to output a high-frequency feature map and a low-frequency feature map for the image.

Abstract: A light detection and ranging (lidar) device includes: a lower base; an upper base; a laser emitting unit for emitting a laser in a form of a point light source; a nodding mirror for transforming the laser in the form of the point light source to a line beam pattern which is perpendicular to the lower base, wherein the nodding mirror reflects the laser emitted from the laser emitting unit; a polygonal mirror for transforming the line beam pattern to a plane beam pattern and receiving a laser reflected from an object; and a sensor unit for receiving the laser reflected from the object via the polygonal mirror.

Abstract: An image processing method of the present disclosure may include receiving a scanned image, and processing the received image through an octave convolution-based neural network to output a high-quality image and an edge image for the received image. The octave convolution-based neural network may include a plurality of octave encoder blocks and a plurality of octave decoder blocks. Each octave encoder block may include an octave convolutional layer, and may be configured to output a high-frequency feature map and a low-frequency feature map for the image.