Abstract: A method and a system for constructing a driving coordinate system for use in the field of smart transport. The method for constructing a driving coordinate system comprises: determining the road boundary line on one side of the road on which a current vehicle is situated as a reference line for constructing a driving coordinate system; in a vehicle coordinate system, determining the reference line point having the smallest distance between the reference line and the current vehicle position as an origin point OF of the driving coordinate system; on the basis of the origin point OF, determining the road guiding line direction as the XF axis of the driving coordinate system and determining the direction relative to the road guiding line direction according to the left-hand rule as the YF axis of the driving coordinate system; and, on the basis of the origin point OF, the XF axis, and the YF axis, forming a corresponding driving coordinate system.

Abstract: A lighting apparatus includes a first light source, a second light source, a first light guide plate, a second light guide plate and a driver. The first light source emits a first light. The second light source emits a second light. The first light guide plate receives the first light from a first lateral wall and guides the first light to escape via a first surface of the first light guide plate. The second light guide plate receives the second light and guides the second light to escape via a second surface of the second light guide plate. The second surface has an image pattern. The image pattern is rendered by placing multiple first light escaping dots on the second surface. The multiple first light escaping dots are divided into multiple sets for rendering multiple visual objects by arranging area intensities of the first light escaping dots.

Abstract: The present invention belongs to the field of functional materials, and particularly relates to a directly printable image recording material, a preparation method and application thereof. The image recording material comprises 25 to 78.8 parts by mass of a photopolymerizable monomer, 0.2 to 5 parts by mass of a photoinitiator, 20 to 70 parts by mass of an inert component, and 0.05 to 2 parts by mass of a thermal polymerization inhibitor, and has an initial viscosity of 200 to 800 mPa·s. The photopolymerizable monomer includes a thiol monomer and an olefin monomer, at least one of which is a silicon-based monomer with polyhedral oligomeric silsesquioxane as a silicon core.

Abstract: The disclosure discloses a visual multi-object tracking based on multi-Bernoulli filter with YOLOv3 detection, belonging to the fields of machine vision and intelligent information processing. The disclosure introduces a YOLOv3 detection technology under a multiple Bernoulli filtering framework. Objects are described by using anti-interference convolution features, and detection results and tracking results are interactively fused to realize accurate estimation of video multi-object states with unknown and time-varying number. In a tracking process, matched detection boxes are combined with object tracks and object templates to determine new objects and re-recognize occluded objects in real time. Meanwhile, under the consideration of identity information of detected objects and estimated objects, identity recognition and track tracking of the objects are realized, so that the tracking accuracy of the occluded objects can be effectively improved, and track fragments are reduced.

Abstract: The present invention belongs to the field of functional materials, and particularly relates to a directly printable image recording material, a preparation method and application thereof. The image recording material comprises 25 to 78.8 parts by mass of a photopolymerizable monomer, 0.2 to 5 parts by mass of a photoinitiator, 20 to 70 parts by mass of an inert component, and 0.05 to 2 parts by mass of a thermal polymerization inhibitor, and has an initial viscosity of 200 to 800 mPa·s. The photopolymerizable monomer includes a thiol monomer and an olefin monomer, at least one of which is a silicon-based monomer with polyhedral oligomeric silsesquioxane as a silicon core.

Abstract: The disclosure discloses a visual multi-object tracking based on multi-Bernoulli filter with YOLOv3 detection, belonging to the fields of machine vision and intelligent information processing. The disclosure introduces a YOLOv3 detection technology under a multiple Bernoulli filtering framework. Objects are described by using anti-interference convolution features, and detection results and tracking results are interactively fused to realize accurate estimation of video multi-object states with unknown and time-varying number. In a tracking process, matched detection boxes are combined with object tracks and object templates to determine new objects and re-recognize occluded objects in real time. Meanwhile, under the consideration of identity information of detected objects and estimated objects, identity recognition and track tracking of the objects are realized, so that the tracking accuracy of the occluded objects can be effectively improved, and track fragments are reduced.

Abstract: The present invention provides a visible light photoinitiating system for preparing a holographic photopolymer material with high-diffraction efficiency. The photoinitiating system comprises a photosensitizer and a co-initiator, and its mechanism is that the photosensitizer transforms from ground state to excited state after absorbing photons, and then interacts with the co-initiator through transfer of electrons and protons, which produces an alkyl (or aryl) free radical R and a ketyl radical K; wherein the free radical R initiates the addition polymerization of monomers that are capable of free radical polymerization, whereas the radical K inhibits the chain propagation of the macromolecular free radicals to a certain degree due to the steric hindrance effect, and thus delays the gelation time of the photopolymerization, which helps to increase the phase separation between the polymer and the functional components.

Abstract: The present invention provides a visible light photoinitiating system for preparing a holographic photopolymer material with high-diffraction efficiency. The photoinitiating system comprises a photosensitizer and a co-initiator, and its mechanism is that the photosensitizer transforms from ground state to excited state after absorbing photons, and then interacts with the co-initiator through transfer of electrons and protons, which produces an alkyl (or aryl) free radical R and a ketyl radical K; wherein the free radical R initiates the addition polymerization of monomers that are capable of free radical polymerization, whereas the radical K inhibits the chain propagation of the macromolecular free radicals to a certain degree due to the steric hindrance effect, and thus delays the gelation time of the photopolymerization, which helps to increase the phase separation between the polymer and the functional components.

Abstract: A method for preparing a colorful three-dimensional hologram based on holographic polymer dispersed liquid crystal gratings comprises: first, in a 441.