Abstract: An incremental learning method and apparatus for a large Vision-Language Model for autonomous driving are provided. The incremental learning method includes: expanding a first training sample set to obtain a second training sample set, wherein the second training sample set includes a plurality of image samples annotated with road scene targets; inserting a plurality of fine-tuning sub-networks respectively into specified positions in a first large Vision-Language Model to generate a second large Vision-Language Model; processing the image samples in the second training sample set using the second large Vision-Language Model to obtain a target prediction result; calculating a loss value using the target prediction result and a target annotation result; and preserving parameters of the first large Vision-Language Model unchanged, and updating parameters of the fine-tuning sub-networks using the loss value.

Abstract: An incremental learning method and apparatus for a large Vision-Language Model for autonomous driving are provided. The incremental learning method includes: expanding a first training sample set to obtain a second training sample set, wherein the second training sample set includes a plurality of image samples annotated with road scene targets; inserting a plurality of fine-tuning sub-networks respectively into specified positions in a first large Vision-Language Model to generate a second large Vision-Language Model; processing the image samples in the second training sample set using the second large Vision-Language Model to obtain a target prediction result; calculating a loss value using the target prediction result and a target annotation result; and preserving parameters of the first large Vision-Language Model unchanged, and updating parameters of the fine-tuning sub-networks using the loss value.

Abstract: A method and an apparatus for collaborative end-to-end large model-oriented self-driving trajectory decision-making are provided. The method includes: processing an RGB image from ego vehicle, an RGB image from surrounding vehicle, and an RGB image from road-side by using a first feature extraction network to obtain a first image feature, a second image feature, and a third image feature, respectively; fusing first image feature, second image feature, and third image feature to obtain an image fusion feature; processing point cloud data of road-side to obtain a road-side point cloud feature; processing image fusion feature and road-side point cloud feature to obtain a first BEV feature and a second BEV feature; fusing first BEV feature and second BEV feature to obtain a fused BEV feature; and fusing prompt information and fused BEV feature to obtain text information, and then processing text information to obtain an ego vehicle trajectory decision-making result.

Abstract: A multimodal perception decision-making method for autonomous driving based on a large language model includes: acquiring an RGB image and an infrared image of a target area at current time; processing the RGB image using a target detection model to obtain a predicted bounding box and a corresponding target detection category; processing the infrared image and the predicted bounding box and the corresponding target detection categories by using a segmentation model to obtain a target mask image; fusing the RGB image, the target mask image and the infrared image using a fusion model to obtain a fused feature map; performing fusion processing on first prompt information representing a user intent, second prompt information representing target detection category priorities, and the fused feature map, using a large Vision-Language Model to obtain textual information; and processing the textual information using a large natural language model to obtain a perception decision-making result.

Abstract: Foldable tubular construct/element with one rigid degree of freedom is of a tubular construction formed by a number of single layered annular units which are connected in sequence; each single layered annular unit is of a prism having N ridge lines; two adjacent prisms each having N sides are connected to each other by sharing a polygon with N sides formed on an intersection plane; each prism with N ridge lines is composed of N rigid planar quadrilateral facets; two adjacent single layered annular units comprise N spherical mechanisms formed by the intersections of only four planar quadrilateral facets at each apex, where N is a number greater than 3.

Abstract: A foldable tubular construct/element with one rigid degree of freedom is of a tubular construction formed by a number of single layered annular units which are connected in sequence; each single layered annular unit is of a prism having N ridge lines; two adjacent prisms each having N sides are connected to each other by sharing a polygon with N sides formed on an intersection plane; each prism with N ridge lines is composed of N rigid planar quadrilateral facets; two adjacent single layered annular units comprise N spherical mechanisms formed by the intersections of only four planar quadrilateral facets at each apex; the polygon having N sides formed in the intersection plane of the two adjacent single layered annular units is a planar polygon with an arbitrary number of sides greater than for a triangle; the ridge lines of each prism having N ridge lines are parallel to each other; the connecting ridge lines of the tubular element are coplanar; when the polygon having N sides formed in the intersection plan

Abstract: The present invention relates to a technical field of traffic monitoring, and more particularly to a method for detecting traffic violation. The present invention includes firstly localizing vehicle salient parts through salient features including vehicle license numbers and vehicle rear lights, and representing a vehicle with the vehicle salient parts, then tracking the vehicle with a Kalman filter based on the vehicle salient parts, and finally detecting vehicle violation through moving trajectory analysis and setting violating detecting areas. The present invention solves vehicle violation detection problems in complex engineering application conditions such as illumination change and detection noise, and is suitable for city traffic management under complex conditions.

Abstract: A foldable tubular construct/element with one rigid degree of freedom is of a tubular construction formed by a number of single layered annular units which are connected in sequence; each single layered annular unit is of a prism having N ridge lines; two adjacent prisms each having N sides are connected to each other by sharing a polygon with N sides formed on an intersection plane; each prism with N ridge lines is composed of N rigid planar quadrilateral facets; two adjacent single layered annular units comprise N spherical mechanisms formed by the intersections of only four planar quadrilateral facets at each apex; the polygon having N sides formed in the intersection plane of the two adjacent single layered annular units is a planar polygon with an arbitrary number of sides greater than for a triangle; the ridge lines of each prism having N ridge lines are parallel to each other; the connecting ridge lines of the tubular element are coplanar; when the polygon having N sides formed in the intersection plan

Abstract: The present invention relates to a technical field of traffic monitoring, and more particularly to a method for detecting traffic violation. The present invention includes firstly localizing vehicle salient parts through salient features including vehicle license numbers and vehicle rear lights, and representing a vehicle with the vehicle salient parts, then tracking the vehicle with a Kalman filter based on the vehicle salient parts, and finally detecting vehicle violation through moving trajectory analysis and setting violating detecting areas. The present invention solves vehicle violation detection problems in complex engineering application conditions such as illumination change and detection noise, and is suitable for city traffic management under complex conditions.