Abstract: The disclosure relates to the technical field of intelligent driving, and specifically provides a map matching method, a control apparatus, a non-transitory computer-readable storage medium, and a vehicle, to solve the problem of how to accurately and efficiently match data of maps of different specifications. By the method of the disclosure, a path to be matched is divided, multiple candidate path segments are obtained according to track points of segments of path to be matched and topology information of a target map, multiple candidate paths are obtained according to the multiple candidate path segments, and a final matching result of the path to be matched is obtained. Because the path to be matched is divided into multiple segments of path to be matched, a computation of a process of obtaining the candidate paths can be effectively reduced.

Abstract: The disclosure relates to a data processing device for driving assisting, a data processing method for driving assisting, and associated storage medium and vehicle. The data processing device for driving assisting includes: a data processing system configured to receive and process a plurality of vehicle data; and a processing control system configured to perform degradation control under the condition that the data processing system is degraded, to receive and process the plurality of vehicle data in a degradation mode. The data processing device for driving assisting, the data processing method for driving assisting, and the associated storage medium and vehicle perform reasonable division of processing task and degradation control on the data processing system and the processing control system, thereby under the condition that modules in the data processing device stop operating, other modules can be allocated to take over the task timely and effectively.

Abstract: The application proposes a bracket, a bracket assembly, a device arranged on vehicle roof and a vehicle, which are applied in the field of automobile technology. The bracket comprises: a first bracket body mounted to the top of the vehicle; and a connecting body comprising: a first connecting piece arranged on the left side of the first bracket body and mounted with a first image sensor, and a second connecting piece arranged on the right side of the first bracket body and mounted with a second image sensor, wherein the first connecting piece and the second connecting piece are arranged above A pillars of the vehicle.

Abstract: The disclosure relates to a data processing device for driving assisting, a data processing method for driving assisting, and associated storage medium and vehicle. The data processing device for driving assisting includes: a data processing system configured to receive and process a plurality of vehicle data; and a processing control system configured to perform degradation control under the condition that the data processing system is degraded, to receive and process the plurality of vehicle data in a degradation mode. The data processing device for driving assisting, the data processing method for driving assisting, and the associated storage medium and vehicle perform reasonable division of processing task and degradation control on the data processing system and the processing control system, thereby under the condition that modules in the data processing device stop operating, other modules can be allocated to take over the task timely and effectively.

Abstract: The application proposes a bracket, a bracket assembly, a device arranged on vehicle roof and a vehicle, which are applied in the field of automobile technology. The bracket comprises: a first bracket body mounted to the top of the vehicle; and a connecting body comprising: a first connecting piece arranged on the left side of the first bracket body and mounted with a first image sensor, and a second connecting piece arranged on the right side of the first bracket body and mounted with a second image sensor, wherein the first connecting piece and the second connecting piece are arranged above A pillars of the vehicle.

Abstract: The subject matter described herein relates to face alignment via shape regression. A method, computer storage medium, and system are provided. In one embodiment, the method comprises receiving an image including a face; and performing shape regression to estimate a facial shape in the image. For each stage in the shape regression, a local feature is extracted from a local region around each facial landmark in the image independently; and a joint projection is performed based on local features of multiple facial landmarks to predict a facial shape increment. Then, a facial shape of a current stage is generated based on the predicted facial shape increment and a facial shape of a previous stage.

Abstract: Systems, methods, and computer-readable media for providing fast and accurate object detection and classification in images are described herein. In some examples, a computing device can receive an input image. The computing device can process the image, and generate a convolutional feature map. In some configurations, the convolutional feature map can be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image. In various examples, the computing device can process the convolutional feature map with the proposals through a Fast Region-Based Convolutional Neural Network (FRCN) proposal classifier to determine a class of each object in the image and a confidence score associated therewith. The computing device can then provide a requestor with an output including the object classification and/or confidence score.

Abstract: Systems, methods, and computer-readable media for providing fast and accurate object detection and classification in images are described herein. In some examples, a computing device can receive an input image. The computing device can process the image, and generate a convolutional feature map. In some configurations, the convolutional feature map can be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image. In various examples, the computing device can process the convolutional feature map with the proposals through a Fast Region-Based Convolutional Neural Network (FRCN) proposal classifier to determine a class of each object in the image and a confidence score associated therewith. The computing device can then provide a requestor with an output including the object classification and/or confidence score.

Abstract: Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels, and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting.

Abstract: Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels, and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting.

Abstract: The subject matter described herein relates to face alignment via shape regression. A method, computer storage medium, and system are provided. In one embodiment, the method comprises receiving an image including a face; and performing shape regression to estimate a facial shape in the image. For each stage in the shape regression, a local feature is extracted from a local region around each facial landmark in the image independently; and a joint projection is performed based on local features of multiple facial landmarks to predict a facial shape increment. Then, a facial shape of a current stage is generated based on the predicted facial shape increment and a facial shape of a previous stage.