6 results about "Pyramid" patented technology

The invention provides a relevant filtering opposite-thrust target tracking method with an adaptive scale. The method comprises: an initial position and an initial scale of a to-be-tracked target in a video frame are determined, and convolution feature graphs of different layers are extracted respectively by using the initial position as the center and using a deep convolutional neural network; for the extracted convolution feature graph of each layer, tracking is carried out by using a kernel-correlation filtering tracking method to obtain a tracking result; all tracking results are combined by using an adaptive hedging algorithm to obtain a final tracking result as a final position of the to-be-tracked target, so that the to-be-tracked target in the video frame can be localized; after obtaining of the final position of the to-be-tracked target, a final scale of the to-be-tracked target is estimated by using a scale pyramid strategy; and after obtaining of the final position and the final scale of the to-be-tracked target, a to-be-tracked target image block is extracted based on the final scale by using the final position as a center and each kernel-correlation filtering tracking method is trained again to update a coefficient and a template.

The invention discloses a real-time identification method of the live panoramic traffic signs. Aiming at the real-timely acquired large-resolution panoramic traffic images, a proposed data processingmethod is used to extract a training set, and a proposed TSNet network is trained and fine-tuned. In the detection stage, after the image is scaled based on an image pyramid, the sliding window processing method and a DS-NMS algorithm are used to ensure the real-time target identification and improve the accuracy, so that the traffic signs can be identified quickly and accurately in the panoramicstate.

The invention discloses a desktop type pyramid maze educational toy. The desktop type pyramid maze educational toy is characterized in that a base is provided, a balance plate is arranged on the top face of the base, a plurality of springs are arranged between the base and the balance plate, and the balance plate is located above the base and keeps distance from the base through the supporting of the springs; a transparent tapered container is arranged on the top face of the balance plate, a plurality of communicated plate bodies are movably arranged inside the tapered container, and a plurality of separation plates are arranged on the plate bodies, so that a plurality of communicated and not communicated maze passages are formed in a separation mode and an upper layer of the maze and a lower layer of the maze are communicated; an entrance is formed in the inlet of the uppermost maze passage on the surface of the tapered container, an exit is formed in the outlet of the lowermost maze passage, an entrance sensor and an exit sensor are arranged at the entrance and the exit respectively, and the two sensors are respectively connected with a timer on the balance plate to count the time of a ball passing through the maze passages. The desktop type pyramid maze educational toy has the advantages of being convenient to use, practical, and strong in interest, and developing the manipulative ability and thinking ability.

The invention relates to the technical field of chain teeth and in particular relates to a transparent flashing polyester chain tooth, a preparation method and a zip fastener. The transparent flashingpolyester chain tooth is prepared from PET (Polyethylene Terephthalate), TPU (Thermoplastic Polyurethane) modified master batch, a lubricant, an antioxidant and an ultraviolet absorbent, wherein theTPU modified master batch is prepared from isocyanate, polyol, a chain extender, a crosslinking agent and flashing powder; the flashing powder is composed of a micron-grade prism pyramid monomer polyacrylamide layer. According to the transparent flashing polyester chain tooth, the TPU modified master batch with relatively good toughness is added into a PET material, so that the transparent flashing polyester chain tooth has good toughness and anti-impact performance; furthermore, the surface of a micron-grade prism pyramid monomer is covered with the polyacrylamide layer and the crosslinking agent participates, so that the micron-grade prism pyramid monomer is uniformly dispersed in the PET material; compared with a manner of directly adding the micron-grade prism pyramid monomer or the flashing powder into the PET material, the transparent flashing polyester chain tooth has a more uniform and bright flashing property.

The invention relates to the technical field of chemical equipment, in particular to a combined cutting tool applied to nickel starting sheet preparation unit nail lugs. The combined cutting tool comprises a stamping knife and a riveting knife, wherein the stamping knife is divided into a supporting part, a connecting part and a punching part, and the riveting knife is divided into a supporting part, a connecting part, a pressing part and an edge turning part; the punching part and the edge turning part are rectangular pyramids, and an orifice is broken into two petals by an edge during punching, so that the punching resistance is reduced; for lifting lugs and starting sheets with different thicknesses and hardness, turned edges after punching are large, regular in shape and good in symmetry. The connecting parts are cuboids, so that the hole size can be amended further; the supporting parts and the pressing part are cylinders, so that the punching and edge turning stroke are restricted; before the turned edges are pressed, the edge turning part extends into a punched hole so as to prevent the turned edge from being folded back. The combined cutting tool is smooth in riveting edge and good in connection strength. The riveting qualified rate can reach 99.7%, so that the requirement of nailing lugs is met.

The invention discloses a scale-adaptive target object updating method and device, and belongs to the field of computer vision. The method comprises the steps: determining an optimal image scale of atarget based on a scale pyramid; updating the target model of a next image frame of the target based on the optimal image scale when the target is not shielded. Because the scale pyramid has a largerscale range, the method can adapt to the severe changes of the target scale. The gray scale distribution features serve as the features used in the estimation of the target scale, and the features aremade into a statistical histogram according to the position and gray scale of target pixels. Because the method gives consideration to the position information of the target, the gray scale distribution features can reflect the characteristics of the target better than a grey level histogram, and can achieve the more accurate estimation of the sale through the features.