Depth completion method and apparatus using a spatial-temporal
Provided are a depth completion method and apparatus using spatial-temporal information. The depth completion apparatus according to the present invention comprises a processor; and a memory connected to the processor, wherein the memory stores program instructions executable by the processor for performing operations comprising receiving an RGB image and a sparse image through a camera and LiDAR, generating a dense first depth map by processing color information of the RGB image through a first branch based on an encoder-decoder, generating a dense second depth map by up-sampling the sparse image through a second branch based on an encoder-decoder, generating a third depth map by fusing the first depth map and the second depth map, and generating a final depth map including a trajectory of a moving object included in an RGB image continuously captured during movement by inputting the third depth map to a convolution long term short memory (LSTM).
1. A depth completion apparatus using spatial-temporal information comprising:
a processor; and
a memory connected to the processor,
wherein the memory stores program instructions executable by the processor for performing operations comprising:
receiving an RGB image and a sparse image through a camera and LiDAR,
generating a dense first depth map by processing color information of the RGB image through a first branch based on an encoder-decoder,
generating a dense second depth map by up-sampling the sparse image through a second branch based on an encoder-decoder,
generating a third depth map by fusing the first depth map and the second depth map, and
generating a final depth map including a trajectory of a moving object included in an RGB image continuously captured during movement by inputting the third depth map to a convolution long-term short memory (LSTM).
2. The depth completion apparatus of claim 1 , wherein a first encoder of the first branch and a second encoder of the second branch include a plurality of layers,
wherein the first and second encoders include a convolutional layer and a plurality of residual blocks having a skip connection.
3. The depth completion apparatus of claim 2 , wherein each layer of the first encoder is connected to each layer of the second encoder to help preserve rich features of the RGB image.
4. The depth completion apparatus of claim 1 , wherein the convolution LSTM calculates a future state of an input pixel according to a past state of a corresponding local neighboring pixel in a previous frame of the RGB image.
5. The depth completion apparatus of claim 4 , wherein the convolutional LSTM calculates a hidden state and cell statistics in the previous frame, and calculates a future state of a cell using a window sliding the RGB image to obtain a trajectory of a moving object.
6. A depth completion method using spatial-temporal information in an apparatus including a processor and a memory comprising:
receiving an RGB image and a sparse image through a camera and LiDAR;
generating a dense first depth map by processing color information of the RGB image through a first branch based on an encoder-decoder;
generating a dense second depth map by up-sampling the sparse image through a second branch based on an encoder-decoder;
generating a third depth map by fusing the first depth map and the second depth map; and
generating a final depth map including a trajectory of a moving object included in an RGB image continuously captured during movement by inputting the third depth map to a convolution long-term short memory (LSTM).
7. A non-transitory computer-readable medium storing a program for performing the method according to claim 6 .