Disclosed is a method for recognizing distribution network equipment based on Raspberry Pi multi-scale feature fusion. The method includes obtaining an initial sample data set; constructing an object detection network composed of EfficientNe-B0 backbone network, multi-scale feature fusion module and a regression classification prediction head; training the object detection network by taking the initial sample data set as a training sample; finally, detecting inspection pictures by using a the trained object detection network. A light-weight EfficientNet-B0 backbone network feature extraction method obtains more features of objects. Meanwhile, an introduction of multi-scale feature fusion better adapts to small object detection, and a light-weight y_pred regression classification detection head is effectively deployed and realized in Raspberry Pi embedded equipment with tight resources and limited computing power.

A landing tracking control method comprises the following contents: a tracking model training stage and an unmanned aerial vehicle real-time tracking stage. The landing tracking control method extracts a network Snet by using a lightweight feature and makes modification, so that an extraction speed of the feature is increased to better meet a real-time requirement. Weight allocation on the importance of channel information is carried out to differentiate effective features more purposefully and utilize the features, so that the tracking precision is improved. In order to improve a training effect of the network, a loss function of an RPN network is optimized, a regression precision of a target frame is measured by using CIOU, and meanwhile, calculation of classified loss function is adjusted according to CIOU, and a relation between a regression network and classification network is enhanced.

A landing tracking control method comprises the following contents: a tracking model training stage and an unmanned aerial vehicle real-time tracking stage. The landing tracking control method extracts a network Snet by using a lightweight feature and makes modification, so that an extraction speed of the feature is increased to better meet a real-time requirement. Weight allocation on the importance of channel information is carried out to differentiate effective features more purposefully and utilize the features, so that the tracking precision is improved. In order to improve a training effect of the network, a loss function of an RPN network is optimized, a regression precision of a target frame is measured by using CIOU, and meanwhile, calculation of classified loss function is adjusted according to CIOU, and a relation between a regression network and classification network is enhanced.

A method and apparatus with landmark coordinate prediction are provided. The method includes generating a multi-stage feature map for landmarks of a face image through a staged convolutional network, generating an initial query matrix by fully connecting a last-stage feature map in the multi-stage feature map using a fully connected network, where a total number of feature elements in the initial query matrix is equal to a total number of predicted landmarks of the face image, generating a memory feature matrix by flattening and connecting the multi-stage feature map, generating the predicted landmark coordinates by inputting the memory feature matrix and the initial query matrix to a decoder network of plural cascaded decoder networks.

A method and apparatus with landmark coordinate prediction are provided. The method includes generating a multi-stage feature map for landmarks of a face image through a staged convolutional network, generating an initial query matrix by fully connecting a last-stage feature map in the multi-stage feature map using a fully connected network, where a total number of feature elements in the initial query matrix is equal to a total number of predicted landmarks of the face image, generating a memory feature matrix by flattening and connecting the multi-stage feature map, generating the predicted landmark coordinates by inputting the memory feature matrix and the initial query matrix to a decoder network of plural cascaded decoder networks.

A parking slot detection method and system includes receiving a plurality of images taken from a plurality of cameras mounted on a vehicle in a parking environment; generating a top view image comprising a surrounding view of the vehicle based on the plurality of images; processing the top view image using a parking line detection model that has been trained using an annotated dataset to detect parking lines for a parking slot in the parking environment, estimate a bounding box for the parking slot and identify an occupancy state of the parking slot; and converting pixel coordinate information of the bounding box to vehicle information.

A parking slot detection method and system includes receiving a plurality of images taken from a plurality of cameras mounted on a vehicle in a parking environment; generating a top view image comprising a surrounding view of the vehicle based on the plurality of images; processing the top view image using a parking line detection model that has been trained using an annotated dataset to detect parking lines for a parking slot in the parking environment, estimate a bounding box for the parking slot and identify an occupancy state of the parking slot; and converting pixel coordinate information of the bounding box to vehicle information.

A method for generating a three-dimensional working surface of a human body, includes receiving input data corresponding to geometric data; generating a first point cloud from the input data; generating partial views of parameterised body models corresponding to a parametric body model parameterised with different parameterisation configurations, wherein the parametric body model models the human body in which a set of articulations are predefined; calculating a set of geometric parameters, and determining another parameterised model from the set of geometric parameters to generate the human body model of the human body including a first meshing.

A method for generating a three-dimensional working surface of a human body, includes receiving input data corresponding to geometric data; generating a first point cloud from the input data; generating partial views of parameterised body models corresponding to a parametric body model parameterised with different parameterisation configurations, wherein the parametric body model models the human body in which a set of articulations are predefined; calculating a set of geometric parameters, and determining another parameterised model from the set of geometric parameters to generate the human body model of the human body including a first meshing.

This document describes road modeling with ensemble Gaussian processes. A road is modeled at a first time using at least one Gaussian process regression (GPR). A kernel function is determined based on a sample set of detections received from one or more vehicle systems. Based on the kernel function, a respective mean lateral position associated with a particular longitudinal position is determined for each GPR of the at least one GPR. The respective mean lateral position for each of the at least one GPR is aggregated to determine a combined lateral position associated with the particular longitudinal position. A road model is then output including the combined lateral position associated with the particular longitudinal position. In this way, a robust and computationally efficient road model may be determined to aid in vehicle safety and performance.