首页>
外国专利>
CNN -3D METHOD FOR DETECTING PSEUDO-3D BOUNDING BOX BASED ON CNN CAPABLE OF CONVERTING MODES ACCORDING TO POSES OF OBJECTS USING INSTANCE SEGMENTATION AND DEVICE USING THE SAME
CNN -3D METHOD FOR DETECTING PSEUDO-3D BOUNDING BOX BASED ON CNN CAPABLE OF CONVERTING MODES ACCORDING TO POSES OF OBJECTS USING INSTANCE SEGMENTATION AND DEVICE USING THE SAME
The present invention relates to a method of detecting a CNN-based Pseudo-3D bounding box capable of switching modes according to the posture of an object detected using Instance Segmentation. Shading information for each surface of the bounding box can be reflected in learning, the capital-3D bounding box is acquired through a lidar or radar, and the surface can be segmented using a camera, and the detection method is The learning device causes the pooling layer to apply the pooling operation to the 2D bounding box to generate a pooled feature map, the FC layer to apply the neural network operation, and the convolutional layer to apply the convolution operation to the surface area. And, it provides a method characterized in that it comprises the step of causing the FC layer to generate a class loss and a regression loss.
展开▼