2results about How to "Effective distance" patented technology

The invention proposes a small sample image generation method based on semantic mask reconstruction and category semantic learning, and relates to the technical field of image processing, and the method comprises the steps: S1, constructing a network model comprising a generator and a discriminator based on a LoFGAN network; s2, extracting depth features of the input image by using a generator, and fusing the depth features of the input image into depth semantic features through local feature fusion; s3, semantic mask reconstruction is carried out on the depth semantic features, and a corresponding image is generated through a decoder; s4, sending a real image and a corresponding image generated by the decoder into a discriminator to train the network model; s5, inputting the small sample image into the trained network model to obtain a generated image similar to the input image; according to the method, the extraction precision of the semantic information can be effectively enhanced, the understanding ability of the generation model for a complex semantic scene is improved, and the fidelity and definition of the image are improved.

The utility model discloses a combined type riot steel fork, including fork rod and U -shaped prong, be equipped with with setting on the hook lock bottom seat of the hook lock on the U -shaped prong is adapted eccentric hook lock, the hook lock bottom seat is welded on the U -shaped prong, and the hook lock bottom seat is welded on the steel pipe of the anti -cutting capture net. The utility model discloses increased control area, flexible capture net, can ensure the safety of the capture object and form more effective resistant distance and area, and the capture net can form 1.5 square meters control range, and once forms control, is not easy to be shaken off.