Single-stage 3-dimension multi-object detecting apparatus and method for autonomous driving
View Patent ↗According to at least one embodiment, the present disclosure provides an apparatus for single-stage three-dimensional (3D) multi-object detection by using a LiDAR sensor to detect 3D multiple objects, comprising: a data input module configured to receive raw point cloud data from the LiDAR sensor; a BEV image generating module configured to generate bird's eye view (BEV) images from the raw point cloud data; a learning module configured to perform a deep learning algorithm-based learning task to extract a fine-grained feature image from the BEV images; and a localization module configured to perform a regression operation and a localization operation to find 3D candidate boxes and classes corresponding to the 3D candidate boxes for detecting 3D objects from the fine-grained feature image.
1. An apparatus for single-stage three-dimensional (3D) multi-object detection by using a LiDAR sensor to detect 3D multiple objects, comprising:
a data input module configured to receive raw 3D point cloud data from the LiDAR sensor;
a BEV image generating module configured to:
generate four feature map images based on a height, a density, an intensity, and a distance of the raw 3D point cloud data, by encoding the raw 3D point cloud data, and
generate bird's eye view (BEV) images by projecting the raw 3D point cloud data into 2D pseudo-images and discretizing a result of the projecting;
a learning module configured to perform a deep learning algorithm-based learning task to extract a fine-grained feature image from the BEV images; and
a localization module configured to perform a regression operation and a localization operation to find 3D candidate boxes and classes corresponding to the 3D candidate boxes for detecting 3D objects from the fine-grained feature image.
2. The apparatus of claim 1 , wherein the learning module is configured to perform a convolutional neural network-based (CNN-based) learning task.
3. A method performed by an apparatus for single-stage three-dimensional (3D) multi-object detection by using a LiDAR sensor to detect 3D multiple objects, the method comprising:
performing a data input operation by receiving raw 3D point cloud data from the LiDAR sensor;
generating bird's eye view (BEV) images from the raw point cloud data, comprising:
generating four feature map images based on a height, a density, an intensity, and a distance of the raw 3D point cloud data, by encoding the raw 3D point cloud data, and
generating the BEV images by projecting the raw 3D point cloud data into 2D pseudo-images and discretizing a result of the projecting;
performing a deep learning algorithm-based learning task to extract a fine-grained feature image from the BEV images; and
performing a regression operation and a localization operation to find 3D candidate boxes and classes corresponding to the 3D candidate boxes for detecting 3D objects from the fine-grained feature image.
4. The method of claim 3 , wherein the performing of the deep learning algorithm-based learning task comprises:
performing a convolutional neural network-based (CNN-based) learning task.
5. The apparatus of claim 1 , wherein the learning module employs a center regression, offset regression, orientation regression, Z-axis location regression and a size regression.
6. The method of claim 3 , wherein the performing the regression operation comprises performing a center regression, offset regression, orientation regression, Z-axis location regression and a size regression.