2results about How to "Efficient drawing" patented technology

This invention discloses a control method for one-time fully-formed knitting, comprising the following steps: S10) Setting process sheet parameters according to the required knitting style and inputting the process sheet parameters into the pattern making system; S20) Inputting the required knitting structure instruction into the pattern making system that has pre-saved knitting structure patterns, and the pattern making system automatically generating the pattern corresponding to the knitting structure according to the instruction; S30) Determining the positions of each splicing point of the garment sleeves, front piece, and back piece; S40) Setting the width of the decrease distance, automatically generating the decrease effect, and forming a garment model to be knitted; S50) After the pattern making software compiler compiles the garment pattern drawn by the pattern making software, the pattern model is uploaded to the computer flat knitting machine to perform the knitting operation, realizing the one-time fully-formed knitting effect of the garment; This invention achieves efficient, precise, and programmable knitting operation, and provides better knitting quality and performance during the composite decrease process of the garment.

This application provides a method for determining the positions of key points on a display device and the human body. This method eliminates traditional dedicated hardware such as sensors / radar during user posture data acquisition and processing, collecting data solely through a camera and directly acquiring the video stream using WebRTC technology natively supported by the browser, without requiring additional equipment. The human posture recognition model is integrated into the user device using TensorFlow.js, enabling on-device inference and avoiding data uploads to the cloud, thus eliminating transmission latency at its source. Model inference is completed on the browser side, accelerated by a web graphics library to improve processing efficiency and ensure real-time performance. The approximate positions of key points are located using the maximum probability of a heatmap, and then corrected using offsets to improve the positioning accuracy of human key points, further optimizing transmission efficiency and solving the problem of data transmission latency and its impact on transmission efficiency in current user posture data acquisition and processing.